Compare commits

..

1 Commits

Author SHA1 Message Date
Jesse Vincent bac79da8f1 docs: add Qwen Code install instructions to README
Rebased from PR #2108 onto the reworked README. Differences from the PR:
the Hermes TOC entry and Quickstart-line changes are obsolete (the v6.3.0
README rework already added the former and removed the latter), and the
Hermes post-compaction caveat stays: .hermes-plugin injects the bootstrap
only on is_first_turn, so the caveat is still accurate.

Install/update commands and the acceptance transcript are from PR #2108
(@arittr, tested interactively on Qwen Code).

Co-authored-by: Drew Ritter <arittr@users.noreply.github.com>
2026-08-12 23:35:41 +00:00
4 changed files with 30 additions and 14 deletions
+17
View File
@@ -20,6 +20,7 @@ Superpowers is a complete software development methodology for your coding agent
- [Kimi Code](#kimi-code)
- [OpenCode](#opencode)
- [Pi](#pi)
- [Qwen Code](#qwen-code)
- [Hermes Agent](#hermes-agent)
- [The Basic Workflow](#the-basic-workflow)
- [Community](#community)
@@ -246,6 +247,22 @@ pi -e /path/to/superpowers
The Pi package loads the Superpowers skills and a small extension that injects the `using-superpowers` bootstrap at session startup and again after compaction. Pi has native skills, so no compatibility `Skill` tool is required. Subagent and task-list tools remain optional Pi companion packages.
### Qwen Code
Qwen Code installs plugins from Claude Code marketplaces directly.
- Install the plugin from this repository, and pick `superpowers` when prompted:
```bash
qwen extensions install obra/superpowers
```
- Update later:
```bash
qwen extensions update superpowers
```
### Hermes Agent
Install Superpowers as a Hermes plugin from this repository:
+2 -3
View File
@@ -15,9 +15,8 @@ run_claude() {
cmd+=(--allowed-tools="$allowed_tools")
fi
# Run Claude in headless mode with timeout. Redirect stdin from
# /dev/null so the CLI can't block waiting for input and hang the suite.
if timeout "$timeout" "${cmd[@]}" > "$output_file" 2>&1 < /dev/null; then
# Run Claude in headless mode with timeout
if timeout "$timeout" "${cmd[@]}" > "$output_file" 2>&1; then
cat "$output_file"
rm -f "$output_file"
return 0
@@ -23,7 +23,7 @@ echo "========================================"
echo ""
echo "This test executes a real plan using the skill and verifies:"
echo " 1. Plan is read once (not per task)"
echo " 2. Task requirements routed to subagents via brief files"
echo " 2. Full task text provided to subagents"
echo " 3. Subagents perform self-review"
echo " 4. Spec compliance review before code quality"
echo " 5. Review loops when issues found"
@@ -136,7 +136,7 @@ I want you to execute the implementation plan at docs/superpowers/plans/implemen
IMPORTANT: Follow the skill exactly. I will be verifying that you:
1. Read the plan once at the beginning
2. Route each task's requirements to subagents via a task brief file (don't make them read the whole plan)
2. Provide full task text to subagents (don't make them read files)
3. Ensure subagents do self-review before reporting
4. Run spec compliance review before code quality review
5. Use review loops when issues are found
@@ -150,7 +150,7 @@ PROMPT="Execute the implementation plan at docs/superpowers/plans/implementation
IMPORTANT: Follow the skill exactly. I will be verifying that you:
1. Read the plan once at the beginning
2. Route each task's requirements to subagents via a task brief file (don't make them read the whole plan)
2. Provide full task text to subagents (don't make them read files)
3. Ensure subagents do self-review before reporting
4. Run spec compliance review before code quality review
5. Use review loops when issues are found
@@ -164,7 +164,7 @@ PLUGIN_DIR=$(cd "$SCRIPT_DIR/../.." && pwd)
# other concurrent claude sessions.
echo "Running Claude (plugin-dir: $PLUGIN_DIR, cwd: $TEST_PROJECT)..."
echo "================================================================================"
cd "$TEST_PROJECT" && timeout 1800 claude -p "$PROMPT" --plugin-dir "$PLUGIN_DIR" --allowed-tools=all --permission-mode bypassPermissions < /dev/null 2>&1 | tee "$OUTPUT_FILE" || {
cd "$TEST_PROJECT" && timeout 1800 claude -p "$PROMPT" --plugin-dir "$PLUGIN_DIR" --allowed-tools=all --permission-mode bypassPermissions 2>&1 | tee "$OUTPUT_FILE" || {
echo ""
echo "================================================================================"
echo "EXECUTION FAILED (exit code: $?)"
@@ -316,7 +316,7 @@ if [ $FAILED -eq 0 ]; then
echo ""
echo "The subagent-driven-development skill correctly:"
echo " ✓ Reads plan once at start"
echo " ✓ Routes task requirements via brief files"
echo " ✓ Provides full task text to subagents"
echo " ✓ Enforces self-review"
echo " ✓ Runs spec compliance before code quality"
echo " ✓ Spec reviewer verifies independently"
@@ -4,7 +4,7 @@
#
# No drill coverage: this test asks the agent to *describe* SDD (string-
# matches its verbal explanation against expected keywords like
# "self-review", "skeptical", "worktree", "setup", "loop"). Drill scenarios
# "self-review", "skeptical", "worktree", "Step 1", "loop"). Drill scenarios
# test behavior (real subagent dispatch, plan-following, review loops),
# not description-recall. Kept by design.
set -euo pipefail
@@ -83,7 +83,7 @@ else
exit 1
fi
if assert_contains "$output" "beginning\|start\|setup\|before.*dispatch\|before.*task" "Read at beginning"; then
if assert_contains "$output" "Step 1\|beginning\|start\|Load Plan" "Read at beginning"; then
: # pass
else
exit 1
@@ -133,16 +133,16 @@ echo ""
echo "Test 7: Task context provision..."
output=$(run_claude "In subagent-driven-development, how does the controller provide task information to the implementer subagent? Answer using exactly this structure:
Controller provides: <brief file or whole plan file>
Implementer must read whole plan file: <yes or no>" "$CLAUDE_PROMPT_TIMEOUT")
Controller provides: <directly or by file>
Implementer must read plan file: <yes or no>" "$CLAUDE_PROMPT_TIMEOUT")
if assert_contains "$output" "task-brief\|brief file\|brief.*path\|Controller provides:.*brief" "Provides task brief file"; then
if assert_contains "$output" "provide.*directly\|full.*text\|paste\|include.*prompt" "Provides text directly"; then
: # pass
else
exit 1
fi
if assert_contains "$output" "Implementer must read whole plan file:.*no" "Doesn't make subagent read whole plan"; then
if assert_contains "$output" "Implementer must read plan file:.*no" "Doesn't make subagent read file"; then
: # pass
else
exit 1