Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/ao92265/claude-code-playbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ao92265/claude-code-playbook/r)<a href="https://agentmods.dev/commands/ao92265/claude-code-playbook/r"><img src="https://agentmods.dev/badge/commands/ao92265/claude-code-playbook/r/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ao92265/claude-code-playbook/r"><img src="https://agentmods.dev/badge/commands/ao92265/claude-code-playbook/r.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00012 | $0.00469 |
| Opus 5.5 | $0.00005 | $0.00188 |
| Sonnet 5.5 | $0.00002 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
r scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Resume work from a handoff and CONTINUE it. This is not a status report.
1. Pick the handoff
Run the picker. It never guesses across sessions:
~/.claude/scripts/resume-pick.sh "$ARGUMENTS"
With a fragment it takes the newest filename match. Without one it takes the newest
reboot whose - Session: line belongs to THIS session's name. If it prints nothing,
say so with its stderr reason and ask which handoff, do NOT fall back to the newest.
Read the whole file. Also read any handover doc it points at.
2. Verify before trusting it
A handoff records what a previous session believed, not what is true now. Before acting, confirm the branch, the working tree state and anything it claims is running. A claim in a handoff is a lead, not a fact.
3. Continue
Find what is still outstanding and build it. Sources, in order:
- the handoff's own next-intent or remaining-work section
- any handover or plan document it points at, especially sections headed "remaining", "outstanding", "left undone", "open", "to fix next"
- the branch's own uncommitted or half-finished work
Split what you find into two piles:
- Buildable now: a clear defect or a stated next task with a known fix. Do these. Follow the branch's own house rules if the handoff lists any.
- Needs a ruling from the user: anything where the fix depends on a product decision nobody has made. Do NOT decide these silently. Collect them and ask at the end, as one short list.
If the handoff explicitly says the work is finished and to stop, respect that, but still check the documents it points at for outstanding items before concluding there is nothing to do.
4. Report
Lead with what you built. End with the rulings you need, if any.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 52 lines · 12 tokens per session scan A 561f05f33a37
r is a command published in the GitHub repository ao92265/claude-code-playbook (12 stars, last pushed 6d ago), licensed MIT. It adds 12 tokens to every session and 469 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.
stuck
You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.
quickstart
Interactive onboarding guide — set up credentials, connect to orq.ai, and learn every command and skill.
crear-skill
Crear, probar y mejorar skills de forma iterativa. Usa cuando el usuario dice "crear skill", "crear habilidad", "build skill", "create a skill", "skill development", "desarrollar skill", "nueva habilidad". Usa el workflow: draft → test → review → improve → repeat con evaluación cuantitativa y qualitative review.