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.
npx agentmods add skills/tmj-90/gaffer/runbook-generatornpx skills add tmj-90/gaffer --skill runbook-generatorgit clone --depth 1 https://github.com/tmj-90/gafferWrote 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/skills/tmj-90/gaffer/runbook-generator)<a href="https://agentmods.dev/skills/tmj-90/gaffer/runbook-generator"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/runbook-generator.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.00835 |
| Opus 5 | $0.00032 | $0.00417 |
| Sonnet 5 | $0.00013 | $0.00167 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
runbook-generator 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate operational runbooks
A runbook exists so the on-call engineer who has never touched this service can keep it alive at 2 AM. Every section must be executable, not aspirational.
Standard sections (every runbook)
| Section | Contents |
|---|---|
| Overview | What this service does; who owns it; criticality (P1/P2/P3) |
| Architecture | Dependencies in + out; SLOs; data store(s); diagram link |
| Start / Stop / Restart | Exact commands with flags; expected stdout on success |
| Health checks | How to confirm the service is healthy; which endpoint / metric to check |
| Common alerts | Alert name → probable cause → remediation steps → escalation threshold |
| Deployment | Branch-to-deploy flow; how to roll back; known deploy risks |
| Rollback | Step-by-step; blast radius of a bad deploy; who to notify |
| Escalation | Tier-1 (on-call) → tier-2 (team lead) → tier-3 (vendor / SRE) contacts + SLA |
| Post-incident checklist | What to capture; blameless post-mortem template link |
Steps
- Read the lore + existing runbooks.
search_lorefor any existing runbook, ADR, or on-call guide for this service. Extend the existing one rather than creating a duplicate. - Inspect the service. Read the Dockerfile/deployment config, health-check endpoint, environment variables, and alert rules. Every command in the runbook must be real.
- Draft from the standard template. Fill every section. Placeholder (
TODO:) is acceptable only if you mark it clearly — a missing command is better than a wrong one. - Verify commands. Run start/stop/health commands in a staging environment or against the repo's CI; confirm the expected output matches.
- Link to the service. Store the runbook in version control alongside the service code (e.g.
docs/runbooks/<service>.md). Link it from the monitoring alert annotations. - Record evidence. Commit the runbook; record
test_outputviarecord-evidence; submit for review.
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.
- 6d ago First seen · 58 lines · 65 tokens per session scan A 2a2b77be742a
runbook-generator is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 65 tokens to every session and 835 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
mobile-developer
Expert knowledge in mobile app development for iOS, Android, and cross-platform solutions.
skill-creator
Create or update AnkaLoop skills. Use when designing, structuring, or packaging skills with scripts, references, and assets. This skill should be used when users want to create a new skill (or update an existing skill) that extends AnkaLoop's capabilities with specialized knowledge, workflows, or tool integrations.
ai-engineer
Expert knowledge in AI/ML development, model deployment, and MLOps practices.
gh-ci-analyzer
使用 gh CLI 分析 GitHub Actions CI 日志，提供结构化的故障诊断和报告.
security-best-practices
Security best practices and vulnerability prevention guidelines.
react-developer
Expert knowledge in React development, hooks, state management, and modern React patterns.