Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jtprogru/bear-skillsnpx agentmods add skills/jtprogru/bear-skills/srekit-runbookWrote 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/jtprogru/bear-skills/srekit-runbook)<a href="https://agentmods.dev/skills/jtprogru/bear-skills/srekit-runbook"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/srekit-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/jtprogru/bear-skills/srekit-runbook"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/srekit-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 | $0.00122 | $0.04261 |
| Opus 5 | $0.00061 | $0.02131 |
| Sonnet 5 | $0.00024 | $0.00852 |
| Haiku 4.5 | $0.00012 | $0.00426 |
Grade A, and why
srekit-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 11d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
srekit-runbook
Скаффолдит runbook через srekit runbook и помогает наполнить его секции прескриптивно (что делать в следующий раз), а не нарративно (что мы делали в этот раз).
Когда использовать
- Пользователь просит написать/оформить/сделать runbook (любая формулировка).
- Пользователь только что починил что-то на проде и хочет зафиксировать процедуру для on-call.
- Пользователь упоминает алерт, под который сейчас runbook'а нет, и хочет завести.
- Известный failure mode, который надо документировать проактивно — до того, как он повторится в 3 ночи.
Не использовать:
- Постмортем разбираемого инцидента → навык
srekit-postmortem. - Investigation log про незакрытое расследование → команда
taskв общем навыкеsrekit. - RFC про архитектурное решение → команда
rfcв общем навыкеsrekit.
Главный принцип: прескриптивно, не нарративно
Это самая частая ошибка при генерации runbook'ов из контекста сессии. Если пользователь рассказывает «мы зашли на ноду w1, увидели stale DRBD primary, сделали drbdadm secondary, и створки разлетелись», есть соблазн транскрибировать это как есть. Не надо. Это incident-лог, а не runbook. Runbook должен переписать то же знание в форме инструкции для будущего читателя.
| ❌ Нарратив (что было) | ✅ Прескрипция (что делать) |
|---|---|
| «Мы зашли на w1 и увидели stale primary» | «На каждой ноде проверь drbdadm status | grep -E 'Primary|StandAlone' — лишний Primary при отсутствии VM = stale» |
| «Алиса откатила деплой к v1.4.2» | «Откати деплой к последнему good-known тегу: kubectl rollout undo deploy/<svc>» |
| «После рестарта csi-controller всё разъехалось» | «Перезапусти csi-controller: kubectl rollout restart deploy/csi-controller -n storage. Verify: pod в Running, в логах нет connection refused в течение 60 секунд» |
| «Это случилось 3 июня в 14:25» | (вырезать; timestamps не место в runbook'е) |
Конкретные временные отметки и личные имена инцидента в runbook не попадают — это не транскрипт. Если хочешь сохранить «вот пример, как это случилось в прошлый раз» — это ссылка на постмортем под References, не пересказ.
What ships with it
2 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.
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.
- 11d ago First seen · 223 lines · 122 tokens per session scan A ea1a631c9fa3
srekit-runbook is a skill published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 23d ago), licensed MIT. It adds 122 tokens to every session and 4,261 once invoked, about $0.0006 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
OCR Review-to-Approval Loop
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…
debug
Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing…
paper-writing
Use when the user wants to write, structure, or revise academic paper sections, improve notation consistency, or refine figures and tables. Triggers on phrases like "write the abstract", "structure the methods", "improve this section", "notation consistency", "figure refinement", or "paper structure".
research-publishing
Use when the user wants to prepare code for open-source release, create reproducible research artifacts, or structure a repository for publication. Triggers on phrases like "publish code", "open source release", "reproducibility", "research repository", "code release", or "prepare for publication".
write-detection-rule
This skill teaches Claude Code how to write detection rules for the AI Traffic Control rule engine. Read this before creating or modifying anything in rules/. The full rule schema is Rule in packages/schema/src/zod/rule.ts — it is the source of truth for every field below.
dataset-curation
Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset collection. Triggers on phrases like "dataset bias", "stratified sample", "class imbalance", "data distribution", "fairness analysis", or "ethical review".