ワンクリックで
brewcode-e2e
Orchestrates e2e testing: BDD scenarios, Playwright autotests. Triggers: e2e tests, BDD scenarios, write autotest.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Orchestrates e2e testing: BDD scenarios, Playwright autotests. Triggers: e2e tests, BDD scenarios, write autotest.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
SSH server management — connect, configure, deploy, administer Linux servers with safety gates.
Manager mode. on installs+arms a HARD delegation wall into THIS project (PreToolUse denies Write/Edit/Bash in main session, subagents free); off disarms; uninstall removes it. Codeword ++m auto-injects a delegate-everything prompt (plan-aware: adds the plan supplement in plan mode); ++a auto-injects an architecture-first directive (mode-agnostic); ++rr/++r auto-inject review discipline (anti-regression / two-phase double-check), all independent of this skill. level strict|balanced, status, edit, reset. Triggers: manager, менеджер, hard mode, хард режим, delegate.
Installs or removes the think-short terse-mode hooks. Triggers: think-short, be terse, terse mode, инжект терс-режим.
Creates and improves Claude Code subagents. Triggers: create agent, improve agent, scaffold agent, fix agent.
Extracts etalon classes, patterns, architecture into convention docs. Triggers: extract conventions, etalon classes.
Syncs KNOWLEDGE.jsonl or session learnings to project rules. Triggers: rules, knowledge sync, extract rules.
| name | brewcode:e2e |
| description | Orchestrates e2e testing: BDD scenarios, Playwright autotests. Triggers: e2e tests, BDD scenarios, write autotest. |
| user-invocable | true |
| disable-model-invocation | true |
| argument-hint | [setup|create|update|review|rules|status] [prompt] |
| allowed-tools | ["Read","Write","Edit","Glob","Grep","Bash","Task","AskUserQuestion","Skill","WebSearch","WebFetch"] |
| model | opus |
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}