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 fmind/dot --skill incident-responsegit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/incident-response)<a href="https://agentmods.dev/skills/fmind/dot/incident-response"><img src="https://agentmods.dev/badge/skills/fmind/dot/incident-response/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/fmind/dot/incident-response"><img src="https://agentmods.dev/badge/skills/fmind/dot/incident-response.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 | $0.00017 | $0.00611 |
| Opus 5.5 | $0.00007 | $0.00244 |
| Sonnet 5.5 | $0.00003 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
incident-response 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 7d 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Response
Coordinate diagnosis, containment, recovery, and learning during an active outage, breach, or degradation. Preserve evidence and operate within the incident's established authority.
Rules
- Resolve authority before mutating: a request for help does not authorize production mutation, credential rotation, customer or external communication, disclosure, or destructive containment. Before acting, present the exact target, expected signal, abort condition, and rollback. Reuse established approval within its scope; ask only for authority that is missing.
- Prefer the safest reversible mitigation: rank options by time to relief, reversibility, and secondary risk; preserve forensic evidence before containment changes it.
- Freeze unrelated work: no unrelated changes or speculative fixes while the incident is active.
- Treat silence as a gap: missing telemetry, stale dashboards, and a quiet alert are unknowns, not recovery. Recovery means critical journeys, data correctness, and queued work verified over a predeclared window.
- Never promise recovery times: updates state impact, current state, actions, next checkpoint, and known unknowns; the responsible owner sends anything external.
- Keep one incident record: severity, impact, roles, a UTC timeline separating facts from hypotheses, each mitigation with its authority and result, and residual risks with owners. Close only after sustained recovery, with temporary safeguards kept until an owner and test cover their removal; postmortems are blameless and stay inside the evidence.
Documentation
- Companion skills: cloud-run (revision rollback), gcloud (logs, audits, and IAM reads), systematic-debugging (root cause after stabilization), threat-model (security design follow-up), production-readiness (pre-launch gate).
- Adapted from agency-agents incident response and gstack canary.
What ships with it
1 file 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.
- 7d ago Changed 0db21197c1c7
- 12d ago Changed · -15 lines f2aaf27add9b
- 14d ago Changed 6171250500c3
- 15d ago Changed · +7 lines · -3 tokens per session b2bf55064a56
- 1mo ago Changed · +1 lines · -20 tokens per session 30c176708ba4
- 1mo ago Changed e555c8d93e56
- 1mo ago Changed · -7 lines 13ffeb4b5677
- 1mo ago First seen · 44 lines · 40 tokens per session scan A db6649bf2094
incident-response is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 611 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Diagnose unknown-cause bugs, test/build or auth failures, flakes, and runtime performance regressions. Investigate, reduce, localize, falsify hypotheses, and explain root cause before implementation.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
diagnose-ci
Investigate failing REMOTE CI runs on GitHub Actions: find the failed run, pull the failed-step logs with gh, identify the root cause (compile error, test failure, lint, missing secret, timeout), and recommend a fix. Read-only: it does not commit, push, or edit. Use when CI is red, a GitHub Actions run failed, or the…
taste
Martin's judgement on task-shaped decisions — how to debug, how far to build, what to simplify, what to delete, how to test, what to spend, how to roll out, and how to ask him a question. Load before asking him anything with AskUserQuestion, at any fork where two reasonable approaches diverge, when deciding how much…
gather-context
Build comprehensive understanding of a problem by gathering context from GitHub issues, codebase exploration, git history, and linked references. Use when starting work on an issue or investigating a problem.