incident-response

incident-response is a skill for Claude Code, Codex from int2t05/engineering-skills. It costs 68 tokens per session (1,462 once invoked), scanned A, original, MIT.

A guide for handling a live or recently resolved production incident, meaning a failure affecting a running service or its users.

In plain words
What is it for?
Classifying incident severity, coordinating on-call response, containing outages, managing updates, choosing rollback versus repair, and writing a blameless postmortem.
Why use it?
It provides an order for containing the damage, deciding whether to roll back or fix forward, communicating clearly, and learning from the failure without blaming individuals.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also agents/openai.yaml present.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the engineering-skills plugin — 47 skills, 1 hook shipped together

Good fit Classifying incident severity, coordinating on-call response, containing outages, managing updates, choosing rollback versus repair, and writing a blameless postmortem.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add int2t05/engineering-skills
Claude Code
/plugin install engineering-skills

Made for: Claude Code, Codex.

Or install engineering-skills, the plugin that ships this one along with the rest of its 47 skills, 1 hook.

Wrote 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.

agentmods badge for incident-response

README.md
[![agentmods](https://agentmods.dev/badge/skills/int2t05/engineering-skills/incident-response/github.svg)](https://agentmods.dev/skills/int2t05/engineering-skills/incident-response)
Your own site
<a href="https://agentmods.dev/skills/int2t05/engineering-skills/incident-response"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/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.

agentmods 80×15 button for incident-response

Your own site · 80×15
<a href="https://agentmods.dev/skills/int2t05/engineering-skills/incident-response"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/incident-response.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.01462
Opus 5 $0.00034 $0.00731
Sonnet 5 $0.00014 $0.00292
Haiku 4.5 $0.00007 $0.00146

Measured 9d ago against content hash d417e5c3e2ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 9d 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.

skills/09-operate/incident-response/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incident Response

When production is failing, the first job is containment, not root cause. This skill structures the live-incident workflow: classify severity, stop the bleeding, communicate, then diagnose — the inverse of debugging, which builds a red loop first. A blameless postmortem follows every incident so the system improves, not just the symptom.

When to use

  • A production incident is live (page fired, users affected, error spike)
  • An incident just resolved and needs a postmortem
  • Reviewing or rehearsing incident response readiness

Not for: diagnosing a dev-time bug (use debugging); adding telemetry after the fact (use observability); launching a new release (use shipping). This skill is for when something already running has broken.

Steps

1. Declare and classify severity

Assign a severity within the first 5 minutes — severity drives everything downstream (who wakes up, how fast you respond, what comms are required). Use a fixed scale, not ad-hoc:

  • SEV1 — user-facing outage or data loss. Page everyone. Incident commander assigned.
  • SEV2 — significant degradation, partial outage. Page on-call. IC assigned.
  • SEV3 — minor degradation, workaround exists. Ticket, address in business hours.

Record the declaration: start time, severity, initial symptom, who is IC. Verify: severity is written down with a timestamp, not just in someone's head.

2. Contain (stop the bleeding)

The first decision is containment vs. fix. Containment is faster and safer — rollback, disable the offending feature flag, route around the failing dependency, shed load. A fix under pressure is a second incident waiting to happen.

  • Rollback to the last known-good deploy (fastest). Platform commands: kubectl rollout undo deployment/<name> (Kubernetes), aws deploy create-deployment --revision REVISION<prev> (AWS CodeDeploy), gcloud run services update-traffic --to-revisions (Cloud Run), vercel rollback <url> (Vercel). The shipping skill documents when to roll back (trigger conditions); these are the how commands for a live SEV1.
  • Disable the feature flag that triggered the issue
  • Fail over to a healthy replica or region
  • Rate-limit or circuit-break the failing path

Read the full file on GitHub · 118 lines

Files

What ships with it

4 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.

Changes

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.

  1. 9d ago First seen · 118 lines · 68 tokens per session scan A d417e5c3e2ca

Subscribe to this mod's changes

incident-response is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 8d ago), licensed MIT. It adds 68 tokens to every session and 1,462 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.

Related

Other skills, from other repositories

pr-workflow

Crear pull requests completas con descripcion, labels y reviewers.

686f6c61/alfred-dev · 14 tokens

sonarqube

Levantar SonarQube con Docker, analizar el código y proponer mejoras. También: análisis estático, deuda técnica, code smells, cobertura, calidad automatizada.

686f6c61/alfred-dev · 39 tokens

brooks-sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…

hyhmrright/brooks-lint · 178 tokens

critical-code-reviewer

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.

posit-dev/skills · 67 tokens

second-pass-review

Independent audit of sanitized specs in workspace/output/. Three parallel LLM-based reviewer roles check structural leakage, content contamination, and behavioral completeness. Run AFTER Layer 5 sanitization, BEFORE implementation handoff.

prime-radiant-inc/greenfield · 44 tokens

check-pr

Read-only inspection of a single GitHub PR lifecycle — checks CI, review threads, description sync, and mergeability, and returns PASS or FAIL with per-gate findings. Never invokes the merge button. Use when verifying a PR is ready to merge, polling lifecycle progress, checking mergeability, or babysitting a GitHub PR…

doodledood/manifest-dev · 74 tokens