npx claudepluginhub kochetkov-ma/claude-brewcode --plugin brewcodeThis skill is limited to using the following tools:
<instructions>
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Full-cycle E2E testing orchestration: setup agents, create BDD scenarios, write autotests, quorum review.
Arguments: $ARGUMENTS
EXECUTE using Bash tool:
bash "${CLAUDE_SKILL_DIR}/scripts/detect-mode.sh" "$ARGUMENTS" && echo "OK" || echo "FAILED"
Output: MODE:xxx and optionally PROMPT:xxx. Store both.
STOP if FAILED -- fix detect-mode.sh before continuing.
Output detection result:
Mode: {MODE}
Prompt: {PROMPT or "none"}
Read the mode-specific reference file:
| MODE | Reference File |
|---|---|
| setup | ${CLAUDE_SKILL_DIR}/references/mode-setup.md |
| create | ${CLAUDE_SKILL_DIR}/references/mode-create.md |
| update | ${CLAUDE_SKILL_DIR}/references/mode-update.md |
| review | ${CLAUDE_SKILL_DIR}/references/mode-review.md |
| rules | ${CLAUDE_SKILL_DIR}/references/mode-rules.md |
| status | ${CLAUDE_SKILL_DIR}/references/mode-status.md |
Also load core references (always):
${CLAUDE_SKILL_DIR}/references/e2e-rules.md -- rules for all agents${CLAUDE_SKILL_DIR}/references/e2e-architecture.md -- architecture referenceSTOP if mode reference not found -- report missing file.
Follow the loaded mode reference step by step. Pass PROMPT as context where indicated.
Common patterns across all modes:
.claude/agents/e2e-*.md count must be >=3. If not -> "Run /brewcode:e2e setup first." STOP.
Status mode reports missing infrastructure instead of blocking.
MAX_CYCLES=3. Pattern: execute -> reviewer validates -> different agent re-checks -> fix confirmed -> repeat.
All agent work through Task tool. Spawn parallel agents in ONE message when possible.
AskUserQuestion at every key decision point. PROMPT is initial context, not a replacement for confirmation.
| Condition | Action |
|---|---|
| Rules file missing | "E2E rules not found at ${CLAUDE_SKILL_DIR}/references/. Re-install plugin." STOP |
| Agents missing (non-setup/status mode) | "Run /brewcode:e2e setup first." STOP |
| Config missing (non-setup mode) | "Run /brewcode:e2e setup first." STOP |
| Review cycle limit (3) reached | AskUserQuestion with remaining issues |
| Compilation fails after fix | Report to user, suggest manual intervention |
| Agent refuses task | Re-assign to suggested colleague, max 2 retries |
# e2e [{MODE}]
## Detection
| Field | Value |
|-------|-------|
| Arguments | `{raw args}` |
| Mode | `{MODE}` |
| Prompt | `{PROMPT or none}` |
## Results
{Mode-specific output}
## Next Steps
- {recommendations based on mode}