agent-playbook plugin
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.
How to install the agent-playbook plugin
Run both commands inside Claude Code. The first adds the marketplace once; the second installs the plugin.
/plugin marketplace add NickolasBenakis/agent-playbook
/plugin install agent-playbook@agent-playbookWhat's inside agent-playbook
13 parts read from the plugin's own files.
Agents 1
Call as @agent-agent-playbook:name- @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
Claude loads it when the task matches- 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
Runs on these events- PostToolUsecommand
Read|Bash|Grep|WebFetch|WebSearch|mcp__.*
- PreToolUsecommand
Bash, Bash|Read|Grep|Edit|Write|MultiEdit|NotebookEdit
- SessionStartcommand
No description in the file.
- Stopcommand
No description in the file.
- UserPromptSubmitcommand
No description in the file.
Using agent-playbook in Claude Code
Ask for an agent by name:
@agent-agent-playbook:playbook-reviewerSkills need no command. Claude reads them when your request matches what they describe.
Update, turn off or remove
- Update the plugin (shell)
- claude plugin update agent-playbook@agent-playbook
- Refresh the marketplace
- /plugin marketplace update agent-playbook
- Turn it off for now
- /plugin disable agent-playbook@agent-playbook
- Remove it
- /plugin uninstall agent-playbook@agent-playbook
Skills in agent-playbook
- 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.
2 files5stars - 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.
5stars - 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".
5stars - 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.
5stars - 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.
5stars - 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.
5stars - 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.
5stars
agent-playbook plugin questions
How do I install the agent-playbook plugin?
In Claude Code run /plugin marketplace add NickolasBenakis/agent-playbook, then /plugin install agent-playbook@agent-playbook.
What does the agent-playbook plugin include?
agent-playbook bundles 1 agent, 7 skills, hooks.
Which agents come with agent-playbook?
playbook-reviewer. Call one with @agent-agent-playbook:playbook-reviewer.
How do I update or remove the agent-playbook plugin?
Update it with claude plugin update agent-playbook@agent-playbook in your shell, or from the Installed tab of /plugin. Remove it with /plugin uninstall agent-playbook@agent-playbook.
What license is the agent-playbook plugin under?
MIT, as stated in the plugin's manifest.