The plugin had a single named agent (`agents/code-reviewer.md`) used by
two skills, while every other reviewer/implementer subagent in the repo
is dispatched as `general-purpose` with the prompt template living
alongside its skill. That asymmetry had no upside and several costs:
- Two sources of truth for the code review checklist (the agent file
and `requesting-code-review/code-reviewer.md`), both drifting
independently.
- `Codex` users could not use the named agent directly; the codex-tools
reference doc had a workaround section explaining how to flatten the
named agent into a `worker` dispatch.
- No third-party reliance on `superpowers:code-reviewer` inside this
repo.
Changes:
- Merge `agents/code-reviewer.md` (persona + checklist) and
`skills/requesting-code-review/code-reviewer.md` (placeholder
template) into a single self-contained Task-dispatch template,
matching the shape of `implementer-prompt.md`,
`spec-reviewer-prompt.md`, etc.
- Update `skills/requesting-code-review/SKILL.md` and
`skills/subagent-driven-development/code-quality-reviewer-prompt.md`
to dispatch `Task (general-purpose)` instead of the named agent.
- Drop the now-obsolete "Named agent dispatch" workaround sections from
`codex-tools.md` and `copilot-tools.md` — superpowers no longer ships
any named agents, so those instructions documented nothing.
- Delete `agents/code-reviewer.md` and the empty `agents/` directory.
Tier 3 coverage for the change: a new behavioral test
`tests/claude-code/test-requesting-code-review.sh` plants real bugs
(SQL injection, plaintext password handling, credential logging) into
a tiny project, runs the actual `requesting-code-review` skill against
the working tree, and asserts the dispatched reviewer flags every
planted issue at Critical/Important severity and refuses to approve
the diff.
Verified end-to-end on this branch:
- The new test passes (5/5 assertions; reviewer caught all planted
bugs and several others).
- The existing SDD integration test still passes (7/7 subagents
dispatched, all as `general-purpose`; spec compliance still
rejects extra features; produced code is correct).
- Session JSONLs confirm zero remaining `superpowers:code-reviewer`
dispatches anywhere in the SDD pipeline.
The SDD integration test silently bailed before printing any verification
results. Three independent bugs caused this:
1. `WORKING_DIR_ESCAPED` was computed from `$SCRIPT_DIR/../..` without
resolving `..` segments. The resulting "directory" name contained
literal `..` so `find` was looking in a path that doesn't exist.
2. With `set -euo pipefail`, the `find ... | sort -r | head -1` pipeline
could exit non-zero (SIGPIPE on the producer when head closes early),
killing the script silently before assertions ran.
3. The `claude -p` invocation never passed `--plugin-dir`, so it loaded
the installed plugin instead of the working tree. Local edits to
skills under test were not actually being tested.
Other adjustments:
- Run claude from inside the unique TEST_PROJECT directory instead of
from the plugin root, so its session JSONL lives in its own
`~/.claude/projects/` folder and doesn't race other concurrent
claude sessions for "most recent file".
- Use the same character-normalization claude does (every non-alphanumeric
becomes `-`) when computing the session dir name; macOS-resolved
`/private/var/...` paths and tmp dirs with `.`/`_` in their names need
this to round-trip correctly.
- Accept either `"name":"Agent"` or `"name":"Task"` in the subagent count
— the harness renamed the tool but the test wasn't updated.
Verified on this branch: all six verification tests now pass against a
real end-to-end SDD run (skill invoked, 7 subagents dispatched, 6
TodoWrite calls, working code produced, tests pass, no extra features).
Step 1a failed at 2/6 with the spec's original abstract text ("use your
native tool"). Three REFACTOR iterations found what works (50/50 runs):
1. Explicit tool naming — "do you have EnterWorktree, WorktreeCreate..."
transforms interpretation into factual toolkit check
2. Consent bridge — "user's consent is your authorization" directly
addresses EnterWorktree's "ONLY when user explicitly asks" guardrail
3. Red Flag entry naming the specific anti-pattern
File split was tested but proven unnecessary — the fix is the Step 1a
text quality, not physical separation of git commands. Control test
with full 240-line skill (all git commands visible) passed 20/20.
Test script updated: supports batch runs (./test.sh green 20), "all"
phase, and checks absence of git worktree add (reliable signal) rather
than presence of EnterWorktree text (agent sometimes omits tool name).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Gate test for Step 1a — validates agents prefer EnterWorktree over
git worktree add on Claude Code. Must pass before skill rewrite.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Specs (brainstorming output) now go to docs/superpowers/specs/
- Plans (writing-plans output) now go to docs/superpowers/plans/
- User preferences for locations override these defaults
- Update all skill references and test files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Instead of prohibiting main branch work entirely, allow it with explicit
user consent. This is more flexible while still ensuring users are aware
of the implications.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
TDD: Test verifies that subagent-driven-development skill warns
against starting implementation directly on main/master branch.
Test expects skill to recommend worktree or feature branch instead.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add Test 8 to verify that using-git-worktrees is mentioned as a required
skill for subagent-driven-development. This test will initially fail per
TDD approach - the skill file needs to be updated to pass this test.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The assertion now matches "subagent-driven-development", "Subagent-Driven
Development", and "Subagent Driven" since Claude's responses may use
different casing and formatting styles.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rewrote analyze-token-usage.py to parse main session file correctly
- Extracts usage from toolUseResult fields for each subagent
- Shows breakdown by agent with descriptions
- Integrated into test-subagent-driven-development-integration.sh
- Displays token usage automatically after each test run
The skill instructions are internal and don't appear in user-facing
output. Updated verification to parse the session JSONL transcript
and check for actual tool usage:
- Skill tool invocation
- Task tool (subagents)
- TodoWrite (tracking)
- Implementation results
The superpowers-dev marketplace makes skills available only when running
from the plugin directory. Updated test to run claude from superpowers
directory while working on the test project.
Claude Code headless mode requires --allowed-tools flag to actually
execute tool calls. Without it, Claude only responds as if it's doing
things but doesn't actually use tools.
Changes:
- Updated run_claude helper to accept allowed_tools parameter
- Updated integration test to use --allowed-tools=all
- This enables actual tool execution (Write, Task, Bash, etc.)
Now the integration test should actually execute the workflow instead
of just talking about it.
Simplified command substitution to avoid shell parsing issues.
Instead of nested heredoc in command substitution, write prompt
to file first then read it.
Created full end-to-end integration test that executes a real plan
and verifies the new workflow improvements actually work.
New test: test-subagent-driven-development-integration.sh
- Creates real Node.js test project
- Generates implementation plan (2 tasks)
- Executes using subagent-driven-development skill
- Verifies 8 key behaviors:
1. Plan read once at beginning (not per task)
2. Full task text provided to subagents (not file reading)
3. Subagents perform self-review
4. Spec compliance review before code quality
5. Spec reviewer reads code independently
6. Working implementation produced
7. Tests pass
8. No extra features added (spec compliance)
Integration tests are opt-in (--integration flag) due to 10-30 min runtime.
Updated run-skill-tests.sh:
- Added --integration flag
- Separates fast tests from integration tests
- Shows note when integration tests skipped
Updated README with integration test documentation.
Run with:
./run-skill-tests.sh # Fast tests only
./run-skill-tests.sh --integration # Include integration tests
Created automated test suite for testing superpowers skills using
Claude Code CLI in headless mode.
New files:
- tests/claude-code/run-skill-tests.sh - Main test runner
- tests/claude-code/test-helpers.sh - Helper functions for testing
- tests/claude-code/test-subagent-driven-development.sh - First test
- tests/claude-code/README.md - Documentation
Test framework features:
- Run Claude Code with prompts and capture output
- Assertion helpers (contains, not_contains, count, order)
- Test project creation helpers
- Timeout support (default 5 minutes)
- Verbose mode for debugging
- Specific test selection
First test verifies subagent-driven-development skill:
- Skill loading
- Workflow ordering (spec compliance before code quality)
- Self-review requirements
- Plan reading efficiency (read once)
- Spec compliance reviewer skepticism
- Review loops
- Task context provision
Run with: cd tests/claude-code && ./run-skill-tests.sh
