agent-playbook 플러그인
Nine rules, six workflow skills, a PR screenshot skill, a read-only reviewer and guard hooks for coding agents, tested head-to-head against the plain model.
agent-playbook 플러그인 설치 방법
두 명령을 모두 Claude Code 안에서 실행하십시오. 첫 번째는 마켓플레이스를 한 번 추가하고, 두 번째는 플러그인을 설치합니다.
/plugin marketplace add NickolasBenakis/agent-playbook
/plugin install agent-playbook@agent-playbookagent-playbook 구성 요소
플러그인 파일에서 읽어온 13개의 항목입니다.
Agents 1
@agent-agent-playbook:name 으로 호출- @agent-agent-playbook:playbook-reviewer
Independent, read-only reviewer for a finished change. Give it the acceptance criteria (or plan) and the path to a diff file; it reports security holes, correctness bugs and spec gaps, not style. Use before reporting non-trivial work.
Skills 7
작업이 일치하면 Claude가 로드합니다- audit
Audit past agent sessions for wasted effort and playbook misfires - steps that added nothing, loops, rules that were skipped or followed for no benefit - and propose concrete rule changes. Use when the human asks to audit, review or measure a session, a thread, or the playbook itself.
- delegate
Decide whether to hand work to a subagent or child thread, and write the brief - what context to pass, what to leave out, and what to ask back. Use before launching any subagent, reviewer, or bb child thread.
- factory
Put a feature or epic on rails - plan, approve, build in an isolated worktree, self-review, get CI green, open a PR - with only two optional human checkpoints (plan and PR). Use for high-impact work with clear acceptance criteria, or when the human says "factory" or "auto".
- fanout
Human-in-the-loop workflow for high-impact, high-attention work. The main session stays with the human and delegates each discrete fix or feature to a subagent that returns a PR or verified diff. Use for core product work and dogfooding sessions.
- oneshot
Low-attention workflow for experiments, internal tools, prototypes, and mechanical migrations. Define a machine-checkable finish line, then loop autonomously until it is met. Use when work is off the critical path and the model's judgment can stand in for the human's.
- pr-screenshots
Attach screenshots or screen recordings to a GitHub pull request, issue or comment without leaking them - uses `gh --attach`, never gists, public repos or outside image hosts. Use whenever a PR or issue should show a UI change, a before/after, a visual bug, a test failure screenshot or a demo video, especially on private repos.
- triage
Classify a task or backlog by impact and required human attention, and route each item to the fanout, factory, or oneshot workflow. Use when starting work, when handed a list of tasks, or when unsure which workflow fits.
Hooks 5
다음 이벤트에서 실행됩니다- PostToolUsecommand
Read|Bash|Grep|WebFetch|WebSearch|mcp__.*
- PreToolUsecommand
Bash, Bash|Read|Grep|Edit|Write|MultiEdit|NotebookEdit
- SessionStartcommand
파일에 설명이 없습니다.
- Stopcommand
파일에 설명이 없습니다.
- UserPromptSubmitcommand
파일에 설명이 없습니다.
Claude Code에서 agent-playbook 사용하기
이름으로 agent를 요청하세요:
@agent-agent-playbook:playbook-reviewerSkills는 명령어가 필요하지 않습니다. 요청이 설명과 일치하면 Claude가 이를 읽습니다.
업데이트, 비활성화 또는 삭제
- 플러그인 업데이트 (shell)
- claude plugin update agent-playbook@agent-playbook
- marketplace 새로고침
- /plugin marketplace update agent-playbook
- 일시적으로 비활성화
- /plugin disable agent-playbook@agent-playbook
- 삭제
- /plugin uninstall agent-playbook@agent-playbook
agent-playbook의 스킬
- auditNickolasBenakis/agent-playbook
Audit past agent sessions for wasted effort and playbook misfires - steps that added nothing, loops, rules that were skipped or followed for no benefit - and propose concrete rule changes. Use when the human asks to audit, review or measure a session, a thread, or the playbook itself.
2개 파일5스타 - delegateNickolasBenakis/agent-playbook
Decide whether to hand work to a subagent or child thread, and write the brief - what context to pass, what to leave out, and what to ask back. Use before launching any subagent, reviewer, or bb child thread.
5스타 - factoryNickolasBenakis/agent-playbook
Put a feature or epic on rails - plan, approve, build in an isolated worktree, self-review, get CI green, open a PR - with only two optional human checkpoints (plan and PR). Use for high-impact work with clear acceptance criteria, or when the human says "factory" or "auto".
5스타 - oneshotNickolasBenakis/agent-playbook
Low-attention workflow for experiments, internal tools, prototypes, and mechanical migrations. Define a machine-checkable finish line, then loop autonomously until it is met. Use when work is off the critical path and the model's judgment can stand in for the human's.
5스타 - pr-screenshotsNickolasBenakis/agent-playbook
Attach screenshots or screen recordings to a GitHub pull request, issue or comment without leaking them - uses `gh --attach`, never gists, public repos or outside image hosts. Use whenever a PR or issue should show a UI change, a before/after, a visual bug, a test failure screenshot or a demo video, especially on private repos.
5스타 - fanoutNickolasBenakis/agent-playbook
Human-in-the-loop workflow for high-impact, high-attention work. The main session stays with the human and delegates each discrete fix or feature to a subagent that returns a PR or verified diff. Use for core product work and dogfooding sessions.
5스타 - triageNickolasBenakis/agent-playbook
Classify a task or backlog by impact and required human attention, and route each item to the fanout, factory, or oneshot workflow. Use when starting work, when handed a list of tasks, or when unsure which workflow fits.
5스타
agent-playbook 플러그인 질문
agent-playbook 플러그인은 어떻게 설치하나요?
Claude Code에서 /plugin marketplace add NickolasBenakis/agent-playbook를 실행한 다음 /plugin install agent-playbook@agent-playbook을 실행하십시오.
agent-playbook 플러그인에는 무엇이 포함되나요?
agent-playbook은(는) 1개 에이전트, 7개 스킬, 훅을(를) 묶습니다.
agent-playbook에는 어떤 agent가 포함되어 있나요?
playbook-reviewer입니다. @agent-agent-playbook:playbook-reviewer로 호출하세요.
agent-playbook 플러그인을 어떻게 업데이트하거나 삭제하나요?
shell에서 claude plugin update agent-playbook@agent-playbook를 사용하여 업데이트하거나 /plugin의 Installed 탭에서 수행하세요. 삭제하려면 /plugin uninstall agent-playbook@agent-playbook을 사용하세요.
agent-playbook 플러그인의 라이선스는 무엇인가요?
플러그인 manifest에 명시된 대로 MIT입니다.