The SDD skill tests still asserted on pre-rename skill text, so correct
model answers failed the suite:
- "Read at beginning" asserted "Step 1|beginning|start|Load Plan";
the current skill has no numbered steps or Load Plan phase (setup
covers it: "Read the plan once" during Setup). A live run today
failed this assertion when the model correctly answered "during
setup". Pattern now accepts setup/before-dispatch paraphrases while
still requiring an at-the-start answer.
- "Provides text directly" asserted the removed provide-full-task-text
behavior; SDD now routes task requirements through brief files
(scripts/task-brief). The test now asks brief-file-vs-whole-plan and
asserts the brief-based flow.
- The integration test's prompt and summary told the agent to
"provide full task text to subagents (don't make them read files)",
contradicting the skill it verifies; reworded to the task-brief flow.
Also gave its direct `timeout 1800 claude -p` the same </dev/null
stdin guard as run_claude.
Live-LLM tests; verified with bash -n on every touched file.
Part of #2130; defects documented in PR #2071 by @ericyen97903-lab.
run_claude ran `timeout "$timeout" "${cmd[@]}"` with the suite's stdin
inherited by the spawned CLI. When the suite is run from a terminal (or
any open stdin), claude -p can block reading stdin and each test stalls
for its full timeout instead of completing.
Verified deterministically with a stub `claude` that reads stdin (cat):
with an open stdin pipe the old helper blocks until timeout kills it
(exit 124); with the redirect it exits immediately with output.
Part of #2130; defect documented in PR #2071 by @ericyen97903-lab.
* fix(codex): suppress SessionStart hook auto-discovery with empty hooks object
Codex auto-discovers a plugin's hooks/hooks.json whenever the Codex
manifest has no `hooks` field: load_plugin_hooks falls back to a
hardcoded DEFAULT_HOOKS_CONFIG_FILE = "hooks/hooks.json" and registers
it. hooks/hooks.json is the Claude Code SessionStart hook, it is tracked
in this repo, and the Codex marketplace installs the whole repo root
(source url "./"), so the fallback re-registered the SessionStart hook
and its install-time trust prompt on Codex.
Removing the Codex hook file and the manifest `hooks` pointer (commit
"Remove Codex hooks") did not disable the hook on Codex — it removed the
explicit declaration that was overriding the fallback, so the fallback
took over and found the Claude hooks/hooks.json.
Declare an empty inline hooks object ({}) in .codex-plugin/plugin.json.
It parses as an empty inline hook set and stops Codex reaching the
auto-discovery fallback. An absent field, an empty array ([]), and an
empty inline list all collapse back to the fallback, so the value must
be exactly {}.
Update the test to assert the manifest declares hooks: {} (and that
hooks/hooks.json exists, which is what makes the declaration necessary),
replacing the prior assertion that the field was absent — which passed
while the hook was still being auto-discovered.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* Add Codex portal package script
* Harden Codex package script checks
* Default Codex portal package to zip
* Fix Codex plugin category
* chore(codex): remove orphaned session-start-codex hook + refresh hook docs
hooks/session-start-codex has had no caller since "Remove Codex hooks"
(#1845) deleted hooks-codex.json and its manifest registration; the
Codex manifest now declares an empty hooks object so Codex registers no
session-start hook at all. The script is Codex-specific dead code —
nothing executes it on Codex or any other harness.
- Delete hooks/session-start-codex.
- tests/hooks/test-session-start.sh: drop the two Codex cases that are
redundant with the generic session-start tests (nested-format and the
legacy-warning omission are already covered by the Claude Code cases).
Re-point the "wrapper dispatches" case to the live `session-start`
script so run-hook.cmd dispatch coverage — used by Claude Code and
Cursor in production — is preserved rather than lost.
- docs/porting-to-a-new-harness.md: Codex is no longer a Shape A
(shell-hook) harness, so re-anchor that worked example to Cursor (a
live shell-hook harness that demonstrates the same per-harness field,
schema, and matcher variance) and mark Codex as native skill discovery
with no session-start hook. Clears the references to the deleted
hooks-codex.json.
- docs/windows/polyglot-hooks.md: the "check hooks-codex.json" pointer
referenced a file deleted in #1845; re-point to hooks-cursor.json.
RELEASE-NOTES.md keeps its historical mention of hooks-codex.json (it
accurately records what that release did). The tests/codex-plugin-sync
fixtures build their own synthetic session-start-codex and test the sync
mechanism generically, so they are intentionally left as-is.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs: re-anchor Shape A examples away from Codex
* Strip hooks from Codex portal package
* Preserve hooks in Codex package manifest
* Release v6.1.1: fix Codex SessionStart hook re-registration, add Codex portal packaging
* Revert "Remove Gemini CLI support"
This reverts commit 711d895ce7.
* refactor(skills): fold Integration skill lists into points of use
The list-style Integration sections in subagent-driven-development and
executing-plans duplicated references that already exist where the flow
uses them (process digraph, When to Use, prompt templates, Step 3), so
they added maintenance cost without carrying behavior. The one entry not
duplicated anywhere — the using-git-worktrees isolated-workspace
requirement — moves to its point of use: SDD's Pre-Flight Plan Review and
executing-plans' Step 1. Micro-tested 5/5: controllers at skill start
establish or verify the worktree before reading the plan or dispatching
Task 1, including under skip-the-ceremony pressure. The prose Integration
sections in requesting-code-review and other skills are unchanged — they
carry placement content, not an index.
* refactor(skills): fold systematic-debugging Related-skills block into Phase 4
Same treatment as subagent-driven-development and executing-plans: the
test-driven-development entry duplicated the reference already at Phase 4
Step 1, and the verification-before-completion entry was a sole carrier —
it moves to its point of use in Phase 4 Step 3 (Verify Fix). Micro-tested
2/2: subjects at the just-implemented-a-fix point invoke
verification-before-completion before any success claim, including under
ship-pressure.
* refactor(skills): stop offering to discard work in finishing-a-development-branch
The completion menu dates from when throwing away branches was routine;
offering 'Discard this work' beside 'Merge' on every completion advertised
destroying finished, passing work. The menu is now 3 options (2 detached
HEAD); discard survives as an explicit-request-only path with the same
typed-confirmation ritual and cleanup mechanics. Fresh-eyes fixes in the
same pass: Option 2 actually creates the pull/merge request
(platform-neutral tooling) and reports the URL; Step 3's base-branch
detection drops a command that printed a SHA instead of choosing a branch
(ask when not known); Option 1 gains a failure branch (merged-result test
failures stop cleanup); description trimmed to trigger-only. Micro-tested
4/4: both menus verbatim with no discard, no discard offer even when the
human sounded lukewarm about the feature, and a prose 'throw it all away'
still required the typed confirmation before any deletion.
* refactor(skills): make PR creation forge-agnostic in finishing-a-development-branch
Naming gh and glab implicitly blessed two forges; Gitea, Forgejo,
Bitbucket and others are equally valid. Point at the forge's CLI or the
creation URL printed on push instead of naming tools.
* refactor(skills): compress finishing-a-development-branch, adopt rationalization table
Red Flags and Common Mistakes fold into one Common Rationalizations table
(house Excuse/Reality form); every prior entry maps to a table row or an
inline sentence in the step it guards. Instructions rephrase positively —
what to do rather than what to avoid — with negations remaining only in
statements of fact. Workflow prose tightens throughout; menus, detection
mechanics, cleanup provenance, and the typed-discard ritual are unchanged.
Re-verified 4/4 after the rewrite: both menus verbatim, the lukewarm-human
pressure arm cited the rationalizations table when declining to offer
discard, and a prose discard request still required the literal typed
word.
* fix(skills): capture worktree path before Step 5 changes directory
Step 6 recomputed WORKTREE_PATH after Option 1 and discard had already
cd'd to the main repo root, so --show-toplevel returned the main root:
the provenance check could never match, cleanup silently no-oped, and the
branch delete failed with the worktree still attached. A test subject had
to deviate from the literal skill to produce a working sequence. The
capture moves to Step 2 (still inside the workspace); Step 6 consumes
Step 2's values and drops its redundant recompute and MAIN_ROOT
derivation. Also: Option 2 gains the detached-HEAD push variant its menu
advertises, and the stale-green rationalization row states what a green
run proves instead of asserting the tree changed. Re-verified: merge-flow
and discard-flow subjects both walk the literal skill to correct cleanup
with concrete paths and no deviations.
* refactor(skills): reframe testing-anti-patterns as writing-good-tests
The disclosure doc becomes a catalog of what to do: six positively named
rules (assert on real behavior, cleanup in test utilities, mock at the
right level, mirror real data, tests ship with implementation, prefer
real components), each leading with the GOOD example and keeping the
violation as contrast. Iron Laws, gate functions, human-partner lines,
and warning signs all survive; The Bottom Line recap and the
TDD-prevents-these section fold into one Overview sentence. SKILL.md's
pointer moves into the Good Tests section it belongs with. Micro-tested
2/2: a mock-existence assertion got rewritten to a real-behavior
assertion citing Rule 1, and a test-only teardown method plus a
to-be-safe mock were both rejected citing Rules 2 and 3.
* fix(skills): broaden writing-good-tests trigger to any test writing
The pointer fired only on adding mocks or test utilities; the doc's own
load-when line already says writing or changing tests. The narrow trigger
would skip the rules exactly when an agent thinks no mocks are involved.
* feat(skills): absorb falsifiability discipline into writing-good-tests
Generalized from agentsview's testing-without-tautologies skill: a new
Iron Law and lead rule (name the production change that would fail the
test, derive expectations independently of the code under test), a
test-your-code-not-the-framework rule with the characterization-test
exception and the trivial-code guidance, branch-specific doubles folded
into Mock at the Right Level, a closing Mutation Check, and six new
warning-sign smells. Rule 1 carries the string-presence trap by name:
grep-style tests on scripts, skills, and prompts counterfeit
falsifiability — the observable is the artifact's behavior, never its
text — with a hard stop in the gate function. Repo-specific content
(testify, backend parity, test-level ladder) stays in the source skill.
Micro-tested: 3/3 tautology verdicts with correct rule citations and the
mutation check named unprompted; a RED-pressure subject refused the
10-second grep test and wrote a behavioral one citing the trap.
* fix(skills): close the change-detector hole in writing-good-tests
Fresh-eyes review found falsifiable-but-worthless tests passed every
rule: a constant assertion can fail, uses a literal, mocks nothing — and
protects nothing, firing on intentional decisions while sleeping through
bugs. Rule 1 gains the what-break-would-this-catch question (absorbed
from the source skill's quality gate, missed in the first pass) with a
gate stop for change detectors; Rule 6's trivial-code list regains
constants; Rule 7 gains the release valve that trivial-only changes earn
no ceremonial test; the coverage-theater and change-detector smells join
Warning Signs; the Rule 6 example stops modeling exact-copy brittleness.
Micro-tested: under a tests-with-every-PR norm, a subject rejected both
draft constant tests citing the new gate and replaced them with a test of
the retry behavior the constant controls.
* refactor(skills): compress writing-good-tests additions; doc changes earn no tests
Prose additions from the last two passes tightened to the terse guard
form: change-detector rule, string-presence trap, and Rule 7's release
valve each drop to a few sentences. Rule 7 now settles the jurisdiction
question outright: trivial code and human prose earn no test; skills and
prompts are pressure-tested per writing-skills when edits change
behavior, never text-asserted. Micro-tested: a subject with a README
rewrite plus a skill typo fix, under tests-with-every-PR pressure,
shipped zero tests — declining the string assertions and the ceremonial
subagent pressure-test alike.
* experiment: ground-up two-principle rewrite of writing-good-tests
Re-derived from scratch: every rule becomes a corollary of two principles
(every test names the break it catches; every test exercises the real
thing), one consolidated gate per principle, four example pairs kept, the
rest carried by prose. Scratch branch for comparison against the accreted
eight-rule version.
* refactor(skills): drop social proof from dispatching-parallel-agents
Real-World Impact restated the Real Example from Session as statistics;
Key Benefits and the time-saved line sold the skill to a reader already
executing it. Instructions unchanged.
* refactor(skills): drop social proof from systematic-debugging
Real-World Impact was statistics; the Overview opener restated the core
principle as motivation. The 95%-of-no-root-cause line stays: it guards
the bail-out point, which is rationalization control, not social proof.
Supporting Techniques/Related skills untouched (PR #1932 owns that).
* refactor(skills): drop persuasion sections from verification-before-completion
Why This Matters (failure-memory testimonials), the dishonesty reframing
in the Overview, and The Bottom Line recap all restate stakes the Iron
Law, gate function, and rationalization table already enforce. This is
the eval-gated class: the bet is that discipline holds without the
persuasion prose — evals on this branch decide.
* refactor(skills): trim quality claim from executing-plans subagent note
The tell-your-partner directive and the prefer-SDD instruction stay; the
significantly-higher-quality sentence restated them as a claim.
Integration section untouched (PR #1932 owns it).
* refactor(skills): drop Advantages section from subagent-driven-development
Five blocks of benefits and cost/benefit selling aimed at a reader who
has already invoked the skill; the vs-Executing-Plans comparison also
duplicates the one under When to Use. Integration section untouched
(PR #1932 owns it).
* refactor(skills): trim requesting-code-review, keep review guards as a table
Integration with Workflows restated the When to Request Review triggers
grouped by caller (each-task / before-merge / when-stuck all appear at
point of use) — detritus, so it goes.
The intro's crafted-context sentence guarded two things at once, so keep
both as Common Rationalizations rows (house Excuse/Reality form) rather
than deleting the sentence. The skill's reader is the coordinator, not
the code's author:
- Don't review the diff inline — that burns the coordinator's context
window; dispatch a subagent so the diff and evaluation live in its
context and only findings return. ("preserves your own context for
continued work")
- Don't hand the reviewer your session history — crafted context keeps it
on the work product, not your thought process.
* refactor(skills): convert using-git-worktrees guard sections to rationalization table
Common Mistakes and Red Flags restated Steps 0-3 wholesale; both fold
into one Common Rationalizations table (house Excuse/Reality form) whose
five rows carry the tempting-thought version of each rule, including the
#1-mistake emphasis on bypassing native tools. Quick Reference stays as
the compact decision aid.
* refactor(skills): fold brainstorming Key Principles into points of use
Five of six principles restated the Checklist and Process sections
verbatim-in-spirit. The sixth, YAGNI, appeared nowhere else — it moves to
the Exploring approaches list where designs get shaped; the recap section
goes.
* refactor(skills): drop Remember recap from writing-plans
All four lines restate the Overview (DRY/YAGNI/TDD/frequent commits),
Task Structure (exact paths, commands with expected output), and No
Placeholders (complete code in every step).
* refactor(skills): drop The Bottom Line recap from writing-skills
Restates the Iron Law, the RED-GREEN-REFACTOR mapping, and the
TDD-for-docs framing, all stated in full earlier in the file.
* refactor(skills): drop The Bottom Line recap from receiving-code-review
Restates the evaluate-don't-obey frame, verification rule, and
no-performative-agreement rule, each detailed earlier at point of use.
The Common Mistakes table stays: it is the skill's one compact guard
table, the class this cleanup standardizes toward rather than deletes.
* refactor(skills): fold TDD Why Order Matters rebuttals into rationalization table
The eval verdict on this cut: deleting Why Order Matters and trusting the
compressed one-line table rows measurably degrades test-first behavior under
the exact pressure the section rebutted ("just write it, tests after") —
control 8/10 → treatment 5/10 at n=10, corroborated on both Claude and Codex.
Normal TDD triggering did not move (PPPPP → PPPPP both arms); the damage is
purely the pressure case.
So instead of trusting the compressed rows, fold the section's five prose
rebuttals into their Common Rationalizations rows so each row carries the
argument, not just the excuse label:
- "I'll test after" — passing immediately proves nothing (wrong thing /
implementation-not-behavior / missed edge; you never saw it fail).
- "Already manually tested" — ad-hoc, no record, can't re-run, forgotten
under pressure.
- "Deleting X hours is wasteful" — sunk cost; rewrite-high-confidence vs
bolt-tests-on-after-low-confidence.
- "TDD will slow me down" — TDD is the pragmatic path; shortcuts mean
debugging in production.
- "Tests after achieve same goals (spirit not ritual)" — what-does vs
what-should; biased by the code you wrote; coverage without proof.
Still removes the 50-line section (~200 words / 45 lines net); the
arguments survive where an agent hits them mid-rationalization. Revalidate
with the tdd-holds-under-tests-later-pressure probe before merge.
* test: realign antigravity + pi mapping assertions with pruned references
Commit e7ddc25 ('Prune per-harness tool-mapping boilerplate') deliberately
removed the skill-loading explainers and generic action->tool tables from
antigravity-tools.md and pi-tools.md, keeping only the harness-specific
notes (subagent dispatch, task tracking). It did not touch tests/, so two
content-assertion tests kept asserting the removed tokens and now fail on
both dev and main:
- tests/antigravity/test-antigravity-tools.sh: asserted view_file,
IsSkillFile, run_command, grep_search (all pruned)
- tests/pi/test-pi-extension.mjs: asserted read/write/edit/bash (pruned)
Update both to assert only the surviving harness-specific mappings. No
reference or skill content is changed; only the stale test assertions.
* test(pi): scope mapping assertions to the table, not whole file
The pi tokens (subagent, pi-subagents, Task, TODO.md) also appear in the
surrounding prose, so matching the whole file passed even with the mapping
table deleted — the exact regression this test exists to catch. Filter to
table rows (lines starting with '|') so the assertion fails when the table
is gone and passes on dev.
Reported by @muunkky on #1987 (approach from #1983); verified failing-first
by stripping the table rows from pi-tools.md.
* docs: fix dead references to pruned claude-code-tools.md/copilot-tools.md
e7ddc25 deleted claude-code-tools.md and copilot-tools.md but left
writing-skills and the porting guide's reference-integration table
pointing at them. State the current architecture instead: Claude Code's
personal-skills path inline, and "no adapter file needed" for the
harnesses that ride the Claude Code-compatible tool surface.
Reported by @rasibintang (#1969, with a fix proposed in #1970).
Fixes#1969
* docs(brainstorming): correct Copilot CLI backgrounding guidance for Windows
* docs(specs): SDD plan-scoped workspace design
The .superpowers/sdd workspace has no plan identity and no end-of-life:
follow-up plans in the same worktree read the previous plan's ledger as
their own progress, and artifacts leak into git (observed in serf, three
contamination rounds and ad-hoc progress-p2/p3 workarounds). Structural
fix: per-plan workspace subdirs, ledger names its plan, delete the
workspace when the final review is clean.
* docs(plans): SDD plan-scoped workspace implementation plan
Five tasks: RED baseline eval (writing-skills Iron Law — before any
skill edit), plan-scoped scripts via TDD, SKILL.md durable-progress
rewrite with mismatch guard and end-of-plan cleanup, GREEN eval with
refinement loop, consistency sweep. Eval = 5 fresh sonnet subagents per
scenario per arm, hand-scored.
* docs(plans): fixture v2 — real cited commits, matched task counts
Fixture v1 tripped the Task 1 STOP gate for the right reason: its
ledgers cited fabricated hashes, so RED agents dismissed them via git
forensics (S1 passed for the wrong mechanism, the S2 resume control
failed 5/5). v2 executes plan A's tasks as real commits, gives both
plans five tasks so numbering is ambiguous, adds a symmetric
resume-uncertainty line to the scenario prompt, hard-stops if the S2
control fails twice, and drops rm -rf from cleanup (hook-gated here).
* docs(plans): re-scope eval per maintainer decision — RED compiled, GREEN measures cost
Three RED rounds (25 reps, three framings incl. faithful compaction
resume) never reproduced blind stale-ledger adoption: sonnet controllers
forensically refuse foreign ledgers, spending 6-13 tool calls per resume
doing it. Jesse approved shipping the full change with the eval re-scoped
to what is true: Task 1 compiles the existing RED evidence, Task 4 runs
GREEN on a truthful v3 fixture (real implementations, rotating authors)
with an S2 released-text control, measuring regression safety and the
disambiguation-cost delta instead of an error rate.
* docs(specs): record eval re-scope — blind adoption did not reproduce, claims narrowed
25/25 baseline reps refused the stale foreign ledger via git forensics;
the spec's evaluation section now states the honest claims: structural
fix + measured disambiguation-cost delta + same-plan-resume regression
gate, shipping with explicit maintainer sign-off in place of a failing
S1 baseline.
* eval(sdd): RED baseline — 25/25 controllers refuse stale ledgers, at a forensic cost
* feat(sdd): plan-scoped workspace — one .superpowers/sdd/<plan> dir per plan
sdd-workspace now requires the plan file and resolves
.superpowers/sdd/<plan-basename>/; task-brief and review-package write
into their plan's directory (review-package gains PLAN_FILE as its first
argument). Follow-up plans in the same working tree can no longer collide
with a previous plan's briefs, reports, or ledger.
* feat(sdd): plan-scoped durable progress — ledger names its plan, workspace dies at plan end
The start-of-skill ledger check is now scoped to the plan's own
workspace and keyed to the ledger's first line. Baseline eval (25/25
reps) showed controllers already refuse foreign ledgers — at a cost of
6-13 tool calls of cross-plan forensics per resume; plan-scoping makes
the answer structural instead. The workspace is deleted once the final
review is clean — git history is the durable record.
* eval(sdd): GREEN results — plan-scoped resolution replaces cross-plan forensics
* chore(sdd): consistency sweep for plan-scoped workspace signatures
* fix(hooks): dispatch the SessionStart hook via Git Bash on Windows
The SessionStart command string starts with a quoted path, which breaks
both Windows shells Claude Code may hand it to: PowerShell parses the
leading quoted string as an expression and dies on the next bareword
('Unexpected token session-start', #1751), and cmd.exe's /c quote rule
drops the outer quotes when the path contains a metacharacter, so a
profile dir like C:\Users\Name(External) truncates the command at the
'(' (#1918). Either way the bootstrap silently never loads.
Declare shell: "bash" on the hook. Claude Code >= 2.1.81 then resolves
Git for Windows and runs the polyglot's bash path directly — the same
route it already picks when it detects Git Bash — and when Git Bash is
missing it surfaces an actionable install prompt instead of a parser
error. Older versions ignore the unknown key and behave exactly as
before (verified live on 2.0.77 and 2.1.80).
Verified end-to-end with real claude sessions: Linux (hook fires,
bootstrap injected), Windows 11 + Git Bash under a path containing
'(' and a space (fires, 3276-char context), and Windows 11 without
Git Bash (actionable error replaces the #1751 ParserError, reproduced
verbatim as control).
Fixes#1751Fixes#1918
* docs(windows): document shell:bash hook dispatch and the PowerShell/CMD fallback hazards
* fix(codex): make package script and its test portable beyond macOS/bsdtar
The packaging pipeline only worked on a Mac with default umask, for
three stacked reasons:
- The deterministic-metadata tar flags (--uid/--gid/--uname/--gname)
are bsdtar spellings; GNU tar rejects them, so the tar.gz archive
step died on Linux. Detect the tar flavor and use --owner=:0
--group=:0 --numeric-owner on GNU tar, which writes byte-identical
ustar headers (uid/gid 0, empty uname/gname).
- Staged file modes depended on two umasks canceling out: git archive
masks entry modes with tar.umask (git default 0002 -> 775), and the
unflagged tar extraction re-masked with the process umask (022 on
macOS -> 755, but 002 elsewhere -> 775). Pin tar.umask=0022 on the
archive call and extract with -p so staged modes are canonical
755/644 on every machine.
- The test's timestamp assertion parsed bsdtar's -tv column layout and
expected epoch 0 rendered in a US timezone ("Dec 31 1969"); GNU tar
uses different columns and UTC hosts render "1970-01-01". Assert
mtime == 0 via python3 tarfile instead, matching how the test
already checks zip timestamps.
tests/codex/test-package-codex-plugin.sh now passes on Linux/GNU tar;
the bsdtar branch preserves the exact flags that passed on macOS.
* fix(tests): stop the SDD skill test flaking on timing and prose case
tests/claude-code/test-subagent-driven-development.sh failed
intermittently for two independent reasons:
- Budget mismatch: the file runs 9 prompts with a 90s timeout each
(810s worst case) inside the runner's 600s per-file ceiling, so slow
backend days produced spurious timeouts. Raise the runner default to
900s and fix the help text, which claimed the default was 300.
- Case-sensitive prose matching: the assert helpers grepped free-form
model output case-sensitively, but models capitalize the skill's own
headings — observed failures include "Do Not Trust the Report"
missing pattern "not trust" and a structured answer missing
"First:.*spec.*compliance". Match case-insensitively in
assert_contains/assert_not_contains/assert_count/assert_order, widen
two Test 5 keyword patterns to phrasings observed in real runs, and
make assert_order dump the output on failure the way assert_contains
already does, so the next flake is diagnosable.
Observed 3 failures across 4 runs before the change (timeout, two
distinct pattern misses); 3/3 consecutive full runs pass after it.
* docs(specs): SDD fix-loop redesign design spec
Review-fix loop gets resume-the-implementer semantics, scoped
re-reviews, a five-round circuit breaker, and controller adjudication
at trip. SKILL.md reorganizes by lifecycle; Red Flags converts to a
rationalization table. Brainstormed with Jesse 2026-07-15.
* docs(plans): SDD fix-loop redesign implementation plan
Eight tasks across two repos: new re-review template, template/reference
alignment, full SKILL.md lifecycle restructure with move map, two
seeded-ledger fixture helpers, three quorum scenarios, and the RED/GREEN/
regression live-run campaign.
* feat(sdd): add scoped re-review prompt template
* feat(sdd): align templates and codex reference with resume-based fix rounds
* feat(sdd): lifecycle restructure with resume-based fix loop, five-round breaker, and rationalization table
* docs(using-superpowers): drop dangling subagent-support anchor (#2010)
The prune in e7ddc25e removed the `## Subagent support` section from
antigravity-tools.md but left the inline cross-reference to it in the
dispatch table, so `[Subagent support](#subagent-support)` resolves to
nothing. An agent following the pointer to learn the difference between
the `self` and `research` subagent types lands nowhere.
Drop the dangling parenthetical. The guidance it pointed at survives in
the same table cell -- `self` for full-capability work, `research` for
read-only -- so no content is lost and the row still answers the
question the removed section answered.
gemini-tools.md carries the same cross-reference but retains its
`## Subagent support` heading, so its link is valid and is left alone.
* fix(systematic-debugging): match find -path ./ prefix in find-polluter.sh (#2011)
find . emits ./-prefixed paths, so -path "src/**/*.test.ts" matched
nothing; wc -l on empty stdin then lied as "Found 1". Fixes#2008.
Co-authored-by: arimu1 <19286898+arimu1@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(systematic-debugging): find-polluter accepts ./-prefixed patterns and matches top-level tests
Follow-up to #2011 (which fixed the ./-prefix mismatch for the documented
pattern form): strip a leading ./ from the caller's pattern instead of
double-prefixing it into a never-matching ././ form, and also match the
pattern with '**/' collapsed, since find -path cannot match '**/' against
zero directory levels and silently skipped files directly under the base
directory (src/top.test.ts vs src/**/*.test.ts).
Adds a deterministic test suite for the script with a stubbed npm.
* fix(finishing): check in with human partner when worktree removal hits untracked files
git worktree remove refuses when the tree holds modified or untracked
files, and the skill gave no guidance for that refusal — the natural
agent response was --force, permanently destroying files that exist
nowhere else (uncommitted plans, notes, scratch work). Reported twice
from real sessions (#2016's plan loss, #1223's dirty-tree ambiguity).
Step 6 now treats the refusal as a stop-and-ask moment: show the
untracked files, offer commit / relocate / delete, and only remove the
worktree after the human partner chooses. Adds a matching rationalization
row so --force-as-cleanup is named as the failure it is.
* feat(hermes): Hermes Agent harness support, rebased to a Hermes-only diff
Rebase of PR #1922 onto current dev: the ~14 files of v6.1.0-era
codex/release drift are dropped, the porting-guide edits (stale against
the post-prune rewrite, no Hermes content) are dropped, and the Hermes
surface is kept intact: .hermes-plugin/ (on_session_start bootstrap
injection), tests/hermes/ (20 tests, passing), docs/README.hermes.md,
references/hermes-tools.md, the Platform Adaptation row, README section,
and Python ignores.
Known open items from review, unchanged by this rebase: the injection
mechanism uses ctx.inject_message from on_session_start, which the
official plugin guide does not document (pre_llm_call returning
{"context": ...} is the sanctioned path), skills are not registered via
ctx.register_skill, and the acceptance transcript predates the fix.
Co-authored-by: kumarabd <kumarabd@users.noreply.github.com>
* fix(hermes): working bootstrap injection via pre_llm_call + native skill registration
Empirical findings from the quorum eval bring-up (superpowers-evals
docs/experiments/2026-07-23-hermes-target-bringup.md):
- ctx.inject_message exists but returns False when called from
on_session_start — nothing reaches the model. The documented path,
a pre_llm_call hook returning {"context": ...} on is_first_turn,
verifiably delivers (probe model echoed an injected codeword).
- ctx.register_skill requires a pathlib.Path; passing a str raises
AttributeError inside hermes, which silently disables the entire
plugin (no log line anywhere). This also means any exception in
register() is invisible — keep register() failure-proof.
- Registered skills are namespaced by plugin name: models invoke
skill_view("superpowers:brainstorming") and receive the stock
SKILL.md — verified live on GLM 5.2, both install layouts.
The plugin now: resolves skills/ for both the git-clone layout
(.hermes-plugin/ and skills/ as siblings) and a flattened install,
raising loudly when neither matches; registers every stock skill with
Hermes' native loader (no per-harness skill copies); injects the
using-superpowers bootstrap via pre_llm_call on the first turn; and
sources the tool mapping from references/hermes-tools.md instead of
duplicating it. Injected context is transient (API-call time only, never
persisted in the session export) — verification of injection must be
behavioral.
* test(hermes): realign suite with the pre_llm_call mechanism; slim docs to the README section
The 20-test suite still exercised the dead on_session_start/inject_message
mechanism (17 failures against the rewritten plugin). Rewritten for the
real contract: pre_llm_call registration + first-turn-only context return,
register_skill receiving pathlib.Path (the conftest mock now raises on str,
mirroring hermes' AttributeError that silently disables a plugin), both
install layouts resolving skills, loud failure when skills are missing,
tool mapping sourced verbatim from hermes-tools.md, and a bootstrap-size
guard against hermes' 10k-char context spill threshold. 19 tests, passing.
Install docs collapse into the README section per maintainer direction:
docs/README.hermes.md and .hermes-plugin/INSTALL.md are gone; the README
carries the two-line install plus the compaction caveat. plugin.yaml
version aligned to 6.1.1.
* Release v6.2.0: SDD plan-scoped workspace and resume-based fix loop, skills compression sweep, Windows SessionStart fix (#2026)
Release notes for everything on dev since v6.1.1, plus the version bump
to 6.2.0 across all seven declared manifest files (bump-version.sh,
audit clean). Tagging and marketplace publication happen after the
dev -> main merge.
* docs: remove the "We're Hiring" section from the README
The community engineer role has a candidate on trial, so the posting no
longer needs to be at the top of the README.
* feat(brainstorming): three-path router — ceremony scales, approval never does
Spike / bounded / architectural classification said out loud, one-way
upgrade ratchet, approval gate on every path. The measured pathology:
the absolute hard-gate wording forced bounded tasks into the full
two-document ritual 5/5 while a no-guidance control differentiated
paths natively.
* fix(sdd): implementers never dispatch subagents
Depth-2 worker-spawned reviewers were 9/9 same-task duplicate reviews
across four corpora in the codex-efficiency eval campaign.
* fix(brainstorming): bounded-path approval is a hard stop
Live ceremony battery: bounded reps produced zero doc ritual (the
measured win) but 2/3 implemented before any approval turn; the
bounded path now states the stop explicitly.
* fix(codex): correct multi-agent guidance against Codex source
Five claims contradicted by the Codex CLI source (V2 has no
close_agent; followup_task always reaches a child; role files attach
via agent_type; full-history forks accept model/effort; V2 spawn
allowlist). Citations: superpowers-autoresearch
docs/2026-07-29-codex-multiagent-v2-capabilities.md.
* fix(sdd): reviewers never dispatch subagents either
The first fix-cycle battery moved the depth-2 leak from implementers
(9/9 baseline -> 0/6) to a final reviewer that spawned two
sub-reviewers; the contract now reaches every dispatched role.
* fix(brainstorming): bounded means existing code in this repo, not a familiar app genre
Triggering battery: Claude Code classified a brand-new project bounded
3/3 by reading 'existing, understood flow' as genre familiarity — once
while explicitly noting the repo was empty. Gemini routed the same
prompt architectural 3/3.
* fix(codex): event-driven waiting instead of short polls
60-78% of wait_agent calls timed out across every measured corpus;
waits are event subscriptions, so one long wait replaces dozens of
polls at identical wake latency.
* fix(sdd): controllers wait long or not at all
Docs-only wait guidance in the platform reference changed nothing
(65.1% vs 67.1% baseline wait-timeout rate); the discipline now lives
in the controller loop the session actually re-reads.
* fix(sdd,codex): bounded wait stretches with reconciliation
Round 2 proved the long-wait mechanism (65.1%->0.0% timeouts) but
20-38 min silent waits starved graders and let 1/51 children vanish;
bounded 5-10 min stretches with a status line and list_agents
reconcile keep the efficiency and restore observability.
* fix(codex): explicit model+effort on every spawn, config backstop
Depth-2 child-issued spawns omitted model 2/2 at CLI 0.146; model
without reasoning_effort resets effort to the model default.
* docs: codex-efficiency fix-cycle spec and plan (campaign record)
* fix(sdd): rule and continue — non-catastrophic conflicts get ledgered rulings, not blocking questions
A donated session sat dormant 8h48m waiting for a plan-conflict answer
that cost ~zero tokens to decide. Wrong-ruling rework is bounded;
stalls are not. This encodes the never-stall doctrine: plan conflicts,
ambiguities, and cap exceptions get a controller ruling recorded in
the ledger and work proceeds; only irreversible/destructive actions,
security-sensitive actions, out-of-worktree side effects (merge/push/
publish), and totally-broken plans remain hard stops. Rulings surface
in the Finish report instead of as mid-run questions.
Evals: 3/3 no-stall vs control 3/3 stall-at-preflight on a
seeded-conflict SDD plan; catastrophic guard 5/5 (every rep reaching a
seeded DROP TABLE step refused it); re-validated 3/3 after rebase onto
the current fix-PR text; composes cleanly with the evidence-bearing
preflight treatment.
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
* fix(sdd): batch small same-shape tasks into one dispatch
Plans sometimes enumerate many tiny, same-shape edits (one-line fixes,
constant changes, a field added across files) as separate tasks. The
current loop dispatches a fresh implementer plus review per task, so a
12-micro-task plan costs ~24 subagent seats for what one subagent could
do in a single pass. In controlled evals on a micro-task plan, batching
cut cost 73% and dispatches 87% with better completion than control; on
a 5-non-trivial-task plan the rule correctly never batched (dispatch
counts and completion identical to control).
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
* fix(sdd): preflight emits its pairwise checks as a ledger table and rules on what it surfaces
The pre-Task-1 conflict scan currently permits 'the scan is clean' with
no evidence the scan happened — mined sessions show controllers skipping
straight to dispatch and plan conflicts surfacing mid-execution as
blocking questions. Requiring the scan to emit one row per task pair
sharing a file/interface and one row per task's self-consistency turns
the claim into an artifact; in controlled evals the table appeared 3/3
with conflicts surfaced pre-dispatch, and the mechanism held 3/3 when
composed with the never-stall ruling change (#2077).
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
* fix(planning): the spec travels with the plan — Spec: header pointer + SDD reads it at setup
In controlled evals, an identical seeded-incoherence plan yielded 0-1/5
correct conflict resolutions when executed specless (controllers ruled
the conflicts 'internally explained') and 4-5/5 with the spec merely
present and named — even with no other skill-text changes. Cross-task
coherence turns out to be adjudicable only against ground truth above
the plan; this change makes that ground truth travel with the plan.
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
* fix(sdd): one Ruling: token everywhere, exhaustive finish roll-up
The breaker's two ledger formats wrote lowercase 'ruling' (parked
findings, load-bearing adjudications), so the Finish section's
collect-every-`Ruling:`-line step missed exactly the rulings made under
the most pressure. Field evidence from an independent eval rep: a
breaker-cap run adjudicated correctly, wrote everything to the
plan-scoped ledger, deleted the workspace at finish, and left no durable
trace of the adjudication.
Capitalize the two breaker formats to the canonical token, and make the
finish roll-up explicitly exhaustive across preflight, parked, and
breaker rulings.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(sdd): batch reviews check the diff against the brief's file list
Batching moves N edits under one review, which changes the review's
failure profile: an implementer that silently skips one file of twelve
produces a diff full of correct, uniform edits — nothing conspicuous is
missing, and no seat in the pipeline was assigned to notice. The single
combined review is the only net for a dropped edit, but the reviewer
template never told it to count.
The batch brief already lists every file with its change, so the reviewer
reconciles the diff against that list file by file; a listed file with no
hunk is a Missing finding regardless of how clean the rest of the batch
looks. Conditional on a multi-file brief, so single-task reviews are
unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(sdd): task reviewers re-read illegible evidence instead of re-running to regenerate it
Interrogation of reviewers who bypassed test-evidence leases showed a
convergent driver: when the report or receipt looked truncated or
couldn't be located, re-running the suite felt cheaper than re-reading —
evidence got regenerated instead of read. This paragraph names that
moment: re-read at the stated path, report a genuine gap to the
controller, and never re-run to regenerate what wasn't read.
Battery: 0/31 reviewer re-runs across 4 treatment reps vs 7/~59
reviewers in 5/8 control reps on the same scenario and classifier.
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
* Moves Community up, and adds ToC.
* chore(hermes): align plugin version with dev
Update the Hermes plugin manifest from 6.1.1 to 6.2.0 so PR #2025 matches the current release version at the tip of origin/dev.\n\nThis intentionally does not change the version bump tooling. The existing release script supports JSON manifests only; YAML support will be handled separately on its own branch.
* fix(writing-skills): run graphviz without a shell in render-graphs.js
The `dot` availability check shelled out to `which dot`, which is not a
command on Windows, so render-graphs.js reported graphviz as missing on
Windows even when it was installed. Replace it with a direct `dot -V`
probe via execFileSync.
Also switch the SVG render call from execSync to execFileSync('dot',
['-Tsvg']). Behavior is identical on macOS/Linux — the diagram source
was already passed via stdin, never interpolated into the command — but
running the binary directly removes the shell entirely.
* test(writing-skills): cover render-graphs execution
* fix(finishing): name the actual files in the refusal prompt
`git status --porcelain` collapses a wholly-untracked directory to a single
`?? docs/` line. In the shape of the incident this step exists for (#2016 — an
uncommitted plan document under an untracked `docs/` tree), the file list we
show the human partner therefore names no file at all:
$ git -C "$WORKTREE_PATH" status --porcelain
?? docs/
$ git -C "$WORKTREE_PATH" status --porcelain -uall
?? docs/superpowers/plans/2026-08-04-csv-export-rollout.md
Both forms produce identical (empty) output on a clean worktree, so this adds
no over-trigger surface.
Found while running this PR's behavioral micro-tests. Every treatment agent
dug past `?? docs/` unprompted and named the document, so the step did work —
but on the agent's own initiative rather than because the text asked for it.
That initiative is not reliable one tier down: Claude Haiku 4.5 on the control
arm failed for exactly this shape, asking a question that never named the file
and then deciding for the human when they deferred. Nothing in the prior
wording stopped a treatment agent from relaying `?? docs/` verbatim and
satisfying the letter of the instruction.
Re-ran the treatment cells against this amended text — Opus pass (refusal
fired, named the file), Haiku 4.5 pass (named the file) — no regression.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
* docs: design Hermes version-bump wiring
Document the agreed follow-up to PR #2025 on a branch based on its merged dev commit. The design registers the Hermes YAML manifest, keeps jq for existing JSON files, and uses Mike Farah yq v4 for a narrow top-level YAML field rather than adding a Bash parser.\n\nDefine focused failure behavior and behavioral tests while explicitly excluding nested YAML, Hermes runtime changes, and unrelated release-script refactors. This captures Drew's request to keep the implementation small and avoid process or abstraction overhead.
* docs: reduce Hermes version-bump design
Incorporate the adversarial design review without turning the Hermes wiring follow-up into a general release-script refactor. Keep the existing jq path, add Mike Farah yq v4 only for .yaml, and retain one read-only preflight to prevent deterministic partial bumps.\n\nReduce the test contract to three behavioral cases and explicitly defer .yml support, nested YAML, rollback machinery, audit/status redesign, exhaustive failure matrices, and the separately discovered JSON-expression issue. This follows Drew's direction to avoid ceremony and overengineering.
* docs: plan Hermes version-bump wiring
Record Drew's approved reduced design after the second staff review. Limit preflight to the mutating bump path, cover audit's independent read path, and require byte-for-byte proof that deterministic YAML failures cannot partially update earlier JSON manifests.
Provide one TDD implementation task for the Hermes registry entry, jq/yq dispatch, focused preflight, and three behavioral checks. Explicitly defer rollback, audit-status changes, nested YAML, runtime changes, and broader release-tool refactoring.
* fix(release): wire Hermes into version bumps
Register the Hermes YAML manifest alongside the existing JSON manifests. Route manifest reads and writes by extension through jq or Mike Farah yq v4, with field names and values passed as data.
Preflight every present manifest before the mutating bump loop so a deterministic YAML read failure cannot leave earlier JSON manifests partially updated. Cover check, audit, bump, registry wiring, and byte-for-byte no-partial-write behavior with one focused fixture test.
* docs: add Grok Build CLI to README.md
* feat: add Devin CLI support
Devin CLI's `devin plugins install obra/superpowers` fails today because the
repo has no `.devin-plugin/plugin.json` manifest. Add the manifest (skills are
auto-discovered from the co-located skills/ directory), a Devin tool mapping
linked from using-superpowers' Platform Adaptation section, a README install
section, version tracking in .version-bump.json, a Codex-sync exclude for the
new dotdir, and a CI-safe test mirroring the kimi/antigravity test style.
Bootstrap rides Devin's native skill surfacing: every installed skill's
name + description is injected into the system prompt at session start with a
standing instruction to invoke matching skills via the native skill tool.
Acceptance test ("Let's make a react todo list") passes in a clean session:
using-superpowers and brainstorming auto-trigger before any code is written.
* Drop devin-tools.md — not needed for correct operation
Re-ran the clean-session acceptance test with the mapping file and the
SKILL.md Platform Adaptation pointer removed: using-superpowers and
brainstorming still auto-trigger first, and the full workflow chain
(writing-plans, executing-plans, TDD, verification) resolves every action
to Devin's native tools. Devin CLI's own system prompt already documents
its tools (skill invocation, subagent profiles, todo tracking, question
prompts), so the mapping was redundant. Test now validates the manifest only.
* docs: streamline README getting started navigation
Remove the redundant Quickstart entry and section now that the README has a table of contents. Rename the Installation label in the table of contents to Getting Started while retaining the existing installation anchor and section heading.
* docs: keep Hermes in installation navigation
Add Hermes Agent to the installation entries in the table of contents. The removed Quickstart section was the README's only direct link to that existing installation section, so preserving the link avoids a navigation regression.
* docs: release notes for v6.3.0
* chore: bump version to 6.3.0
---------
Co-authored-by: Drew Ritter <drew@primeradiant.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Ada Sen <ada@sen.dev>
Co-authored-by: Gaurav Dubey <gauravdubey0107@gmail.com>
Co-authored-by: arimu1 <19286898+arimu1@users.noreply.github.com>
Co-authored-by: Mark Rada <markrada26@gmail.com>
Co-authored-by: dev_Hakaze <af.nawfal@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: kumarabd <kumarabd@users.noreply.github.com>
Co-authored-by: Drew Ritter <drew@ritter.dev>
Co-authored-by: Kattni <kattni@kattni.com>
Co-authored-by: Georgii Perepechko <georgiiperepechko@gmail.com>
Co-authored-by: Caio Lopes <caiodesalopes@gmail.com>
Add Hermes Agent to the installation entries in the table of contents. The removed Quickstart section was the README's only direct link to that existing installation section, so preserving the link avoids a navigation regression.
Remove the redundant Quickstart entry and section now that the README has a table of contents. Rename the Installation label in the table of contents to Getting Started while retaining the existing installation anchor and section heading.
Re-ran the clean-session acceptance test with the mapping file and the
SKILL.md Platform Adaptation pointer removed: using-superpowers and
brainstorming still auto-trigger first, and the full workflow chain
(writing-plans, executing-plans, TDD, verification) resolves every action
to Devin's native tools. Devin CLI's own system prompt already documents
its tools (skill invocation, subagent profiles, todo tracking, question
prompts), so the mapping was redundant. Test now validates the manifest only.
Devin CLI's `devin plugins install obra/superpowers` fails today because the
repo has no `.devin-plugin/plugin.json` manifest. Add the manifest (skills are
auto-discovered from the co-located skills/ directory), a Devin tool mapping
linked from using-superpowers' Platform Adaptation section, a README install
section, version tracking in .version-bump.json, a Codex-sync exclude for the
new dotdir, and a CI-safe test mirroring the kimi/antigravity test style.
Bootstrap rides Devin's native skill surfacing: every installed skill's
name + description is injected into the system prompt at session start with a
standing instruction to invoke matching skills via the native skill tool.
Acceptance test ("Let's make a react todo list") passes in a clean session:
using-superpowers and brainstorming auto-trigger before any code is written.
Register the Hermes YAML manifest alongside the existing JSON manifests. Route manifest reads and writes by extension through jq or Mike Farah yq v4, with field names and values passed as data.
Preflight every present manifest before the mutating bump loop so a deterministic YAML read failure cannot leave earlier JSON manifests partially updated. Cover check, audit, bump, registry wiring, and byte-for-byte no-partial-write behavior with one focused fixture test.
Record Drew's approved reduced design after the second staff review. Limit preflight to the mutating bump path, cover audit's independent read path, and require byte-for-byte proof that deterministic YAML failures cannot partially update earlier JSON manifests.
Provide one TDD implementation task for the Hermes registry entry, jq/yq dispatch, focused preflight, and three behavioral checks. Explicitly defer rollback, audit-status changes, nested YAML, runtime changes, and broader release-tool refactoring.
Incorporate the adversarial design review without turning the Hermes wiring follow-up into a general release-script refactor. Keep the existing jq path, add Mike Farah yq v4 only for .yaml, and retain one read-only preflight to prevent deterministic partial bumps.\n\nReduce the test contract to three behavioral cases and explicitly defer .yml support, nested YAML, rollback machinery, audit/status redesign, exhaustive failure matrices, and the separately discovered JSON-expression issue. This follows Drew's direction to avoid ceremony and overengineering.
Document the agreed follow-up to PR #2025 on a branch based on its merged dev commit. The design registers the Hermes YAML manifest, keeps jq for existing JSON files, and uses Mike Farah yq v4 for a narrow top-level YAML field rather than adding a Bash parser.\n\nDefine focused failure behavior and behavioral tests while explicitly excluding nested YAML, Hermes runtime changes, and unrelated release-script refactors. This captures Drew's request to keep the implementation small and avoid process or abstraction overhead.
`git status --porcelain` collapses a wholly-untracked directory to a single
`?? docs/` line. In the shape of the incident this step exists for (#2016 — an
uncommitted plan document under an untracked `docs/` tree), the file list we
show the human partner therefore names no file at all:
$ git -C "$WORKTREE_PATH" status --porcelain
?? docs/
$ git -C "$WORKTREE_PATH" status --porcelain -uall
?? docs/superpowers/plans/2026-08-04-csv-export-rollout.md
Both forms produce identical (empty) output on a clean worktree, so this adds
no over-trigger surface.
Found while running this PR's behavioral micro-tests. Every treatment agent
dug past `?? docs/` unprompted and named the document, so the step did work —
but on the agent's own initiative rather than because the text asked for it.
That initiative is not reliable one tier down: Claude Haiku 4.5 on the control
arm failed for exactly this shape, asking a question that never named the file
and then deciding for the human when they deferred. Nothing in the prior
wording stopped a treatment agent from relaying `?? docs/` verbatim and
satisfying the letter of the instruction.
Re-ran the treatment cells against this amended text — Opus pass (refusal
fired, named the file), Haiku 4.5 pass (named the file) — no regression.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The `dot` availability check shelled out to `which dot`, which is not a
command on Windows, so render-graphs.js reported graphviz as missing on
Windows even when it was installed. Replace it with a direct `dot -V`
probe via execFileSync.
Also switch the SVG render call from execSync to execFileSync('dot',
['-Tsvg']). Behavior is identical on macOS/Linux — the diagram source
was already passed via stdin, never interpolated into the command — but
running the binary directly removes the shell entirely.
Update the Hermes plugin manifest from 6.1.1 to 6.2.0 so PR #2025 matches the current release version at the tip of origin/dev.\n\nThis intentionally does not change the version bump tooling. The existing release script supports JSON manifests only; YAML support will be handled separately on its own branch.
Interrogation of reviewers who bypassed test-evidence leases showed a
convergent driver: when the report or receipt looked truncated or
couldn't be located, re-running the suite felt cheaper than re-reading —
evidence got regenerated instead of read. This paragraph names that
moment: re-read at the stated path, report a genuine gap to the
controller, and never re-run to regenerate what wasn't read.
Battery: 0/31 reviewer re-runs across 4 treatment reps vs 7/~59
reviewers in 5/8 control reps on the same scenario and classifier.
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
Batching moves N edits under one review, which changes the review's
failure profile: an implementer that silently skips one file of twelve
produces a diff full of correct, uniform edits — nothing conspicuous is
missing, and no seat in the pipeline was assigned to notice. The single
combined review is the only net for a dropped edit, but the reviewer
template never told it to count.
The batch brief already lists every file with its change, so the reviewer
reconciles the diff against that list file by file; a listed file with no
hunk is a Missing finding regardless of how clean the rest of the batch
looks. Conditional on a multi-file brief, so single-task reviews are
unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Both PRs rewrote the same preflight paragraph. Resolution is the composed
text published in #2080's description — the configuration the 3/3+3/3
composed eval grades ran.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The breaker's two ledger formats wrote lowercase 'ruling' (parked
findings, load-bearing adjudications), so the Finish section's
collect-every-`Ruling:`-line step missed exactly the rulings made under
the most pressure. Field evidence from an independent eval rep: a
breaker-cap run adjudicated correctly, wrote everything to the
plan-scoped ledger, deleted the workspace at finish, and left no durable
trace of the adjudication.
Capitalize the two breaker formats to the canonical token, and make the
finish roll-up explicitly exhaustive across preflight, parked, and
breaker rulings.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
In controlled evals, an identical seeded-incoherence plan yielded 0-1/5
correct conflict resolutions when executed specless (controllers ruled
the conflicts 'internally explained') and 4-5/5 with the spec merely
present and named — even with no other skill-text changes. Cross-task
coherence turns out to be adjudicable only against ground truth above
the plan; this change makes that ground truth travel with the plan.
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
The pre-Task-1 conflict scan currently permits 'the scan is clean' with
no evidence the scan happened — mined sessions show controllers skipping
straight to dispatch and plan conflicts surfacing mid-execution as
blocking questions. Requiring the scan to emit one row per task pair
sharing a file/interface and one row per task's self-consistency turns
the claim into an artifact; in controlled evals the table appeared 3/3
with conflicts surfaced pre-dispatch, and the mechanism held 3/3 when
composed with the never-stall ruling change (#2077).
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
Plans sometimes enumerate many tiny, same-shape edits (one-line fixes,
constant changes, a field added across files) as separate tasks. The
current loop dispatches a fresh implementer plus review per task, so a
12-micro-task plan costs ~24 subagent seats for what one subagent could
do in a single pass. In controlled evals on a micro-task plan, batching
cut cost 73% and dispatches 87% with better completion than control; on
a 5-non-trivial-task plan the rule correctly never batched (dispatch
counts and completion identical to control).
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
A donated session sat dormant 8h48m waiting for a plan-conflict answer
that cost ~zero tokens to decide. Wrong-ruling rework is bounded;
stalls are not. This encodes the never-stall doctrine: plan conflicts,
ambiguities, and cap exceptions get a controller ruling recorded in
the ledger and work proceeds; only irreversible/destructive actions,
security-sensitive actions, out-of-worktree side effects (merge/push/
publish), and totally-broken plans remain hard stops. Rulings surface
in the Finish report instead of as mid-run questions.
Evals: 3/3 no-stall vs control 3/3 stall-at-preflight on a
seeded-conflict SDD plan; catastrophic guard 5/5 (every rep reaching a
seeded DROP TABLE step refused it); re-validated 3/3 after rebase onto
the current fix-PR text; composes cleanly with the evidence-bearing
preflight treatment.
Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
Round 2 proved the long-wait mechanism (65.1%->0.0% timeouts) but
20-38 min silent waits starved graders and let 1/51 children vanish;
bounded 5-10 min stretches with a status line and list_agents
reconcile keep the efficiency and restore observability.
Docs-only wait guidance in the platform reference changed nothing
(65.1% vs 67.1% baseline wait-timeout rate); the discipline now lives
in the controller loop the session actually re-reads.
Jesse Vincent