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 skills add mostafa-drz/claude-skills --skill make-it-runbookgit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote 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/mostafa-drz/claude-skills/make-it-runbook)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/make-it-runbook"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/make-it-runbook/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/skills/mostafa-drz/claude-skills/make-it-runbook"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/make-it-runbook.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 | $0.00199 | $0.02156 |
| Opus 5.5 | $0.00080 | $0.00862 |
| Sonnet 5.5 | $0.00040 | $0.00431 |
| Haiku 4.5 | $0.00020 | $0.00216 |
Grade A, and why
make-it-runbook 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 28d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make it a runbook
You worked something out in the chat: an email setup, a migration, a move. The steps are scattered across twenty messages, some were corrected halfway, and a couple of them have to wait a day. This turns that into one page you can work through: tick as you go, come back tomorrow, and never follow the advice that was later taken back.
In Claude Desktop and claude.ai the skill starts automatically on a matching request, with no slash command. "Make it a runbook" is the natural trigger.
Two references, loaded when a step needs them:
distill.md (turning a messy conversation into the final agreed
steps: read it every time) · runbook-schema.md (the
data the page renders from, and the id rules).
The flow
conversation → distill → runbook.json → validate → page. Copy this checklist into your
reply and tick it off, because the distillation is where a confident-looking runbook goes
wrong:
Runbook progress:
- [ ] 1. Distill: ledger → final agreed steps, execution order, waits, notes, literals
- [ ] 2. Ask only what blocks the shape (≤3 questions, defaults) or flag it on the step
- [ ] 3. Write runbook.json
- [ ] 4. Validate
- [ ] 5. Render and deliver
1. Distill
This is the job; the page is the easy half. Follow
distill.md. The rules that matter most:
- Read the whole conversation first, including everything after the plan first looked done. Corrections come late.
- The last agreed word wins. A correction replaces, it doesn't add: when advice went from X to Y, only Y is in the runbook. A changed value is changed everywhere.
- Execution order, not conversation order. Every step comes after what it depends on.
- A forced wait goes right after the step that starts its clock, blocking the first step it holds up, and says what to do meanwhile.
- Warnings and decisions are notes, not checkboxes. Tangents are dropped.
- Literal values are copied exactly, character for character, into
values. Never paraphrased, completed or invented. - Reorganise, don't re-advise. Nothing goes in that the conversation didn't agree. A real problem you spot is raised once, in the closing lines.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/runbook-template.html 15 KB
- evals/evals.json 4.0 KB
- evals/expected-runbook.json 4.4 KB
- evals/fixture-conversation.md 4.7 KB
- icon.svg 677 B
- README.md 7.5 KB
- references/distill.md 7.1 KB
- references/runbook-schema.md 5.5 KB
- scripts/render_page.py 1.7 KB runs code
- scripts/validate_runbook.py 13 KB runs code
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.
- 28d ago First seen · 187 lines · 199 tokens per session scan A caaa89f11f36
make-it-runbook is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed 20d ago), licensed MIT. It adds 199 tokens to every session and 2,156 once invoked, about $0.0008 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 2026-09-23.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
rudder-data-graphs
Produces Data Graph YAML from RETL sources for Audiences. Use when designing Data Graphs, mapping RETL to entities/events, or assessing customer fit for Audiences.
rudder-typer-workflow
Generates type-safe SDKs (Swift/Kotlin) from tracking plans with compile-time validation. Use when generating type-safe event tracking code from tracking plans using RudderTyper.
rudder-instrumentation-planning
Designs event taxonomies and instrumentation strategies from business requirements. Use when designing event taxonomy from scratch or restructuring existing instrumentation strategy.
rudder-instrumentation-debugging
Diagnoses and fixes validation errors, schema issues, and instrumentation problems. Use when debugging validation errors, schema issues, or instrumentation problems.
rudder-ai-events-verify
Verifies RudderStack AI events locally: captures what an instrumented app or MCP server sends, validates it against the AI events v0.3 schema, and checks joins, counts, identity and content. Use when testing AI events, or when AI or MCP events look wrong or missing.