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 aneja5/forge-skills --skill incident-response-and-postmortemsgit clone --depth 1 https://github.com/aneja5/forge-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/aneja5/forge-skills/incident-response-and-postmortems)<a href="https://agentmods.dev/skills/aneja5/forge-skills/incident-response-and-postmortems"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/incident-response-and-postmortems/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/aneja5/forge-skills/incident-response-and-postmortems"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/incident-response-and-postmortems.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 | $0.00058 | $0.01837 |
| Opus 5 | $0.00029 | $0.00919 |
| Sonnet 5 | $0.00012 | $0.00367 |
| Haiku 4.5 | $0.00006 | $0.00184 |
Grade A, and why
incident-response-and-postmortems 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 8d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incident Response and Postmortems
Overview
Define how the team detects, mitigates, communicates about, and learns from production incidents — before the first one. Output is .forge/incident-response.md — severity definitions with response times, the declare-mitigate-communicate-resolve-review flow, runbook template, blameless postmortem template, and the comms templates (internal and external). Pairs with observability (alerts feed the declare step) and error-handling-and-resilience (the failure modes alerts watch for).
When to Use
- A service is going to production and there's no on-call process
- An incident just happened and the team handled it ad-hoc — write the process before the next one
- A postmortem is due and there's no template
- Severity levels are inconsistent across teams
- A runbook is needed for a critical service
When NOT to Use
- Localhost-only or pre-prod systems with no users
- A trivial bug fix — that's
debugging-and-recovery - A near-miss that didn't affect users — log it, learn from it, but don't fire the full process
Common Rationalizations
| Thought | Reality |
|---|---|
| "We're too small for an incident process" | Incidents don't wait for headcount. The first Sev1 at 4 staff is when you learn the process you didn't build. |
| "We'll write the postmortem later" | Memory fades within 48h. Two weeks later the timeline is a guess. |
| "It was their fault" | Blame ends learning. Every "someone clicked the wrong button" is a system that allowed the wrong button to be clicked. |
| "Action items can wait until we have time" | Unowned action items are wishes. They never ship. |
| "We don't need severity levels — just fix everything fast" | Without severity, every alert pages every human. Fatigue sets in. The real Sev1 gets missed. |
| "Comms can be informal during the incident" | "Informal" means three different stories reaching three different audiences. Customers, board, and team need consistent, scheduled updates. |
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.
- 8d ago First seen · 144 lines · 58 tokens per session scan A fbef216ced60
incident-response-and-postmortems is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 1,837 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 2026-09-03.
Other skills, from other repositories
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
implement
Use when implementing a spec or GitHub ticket in this checkout.
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
tdd
Use when implementing features or bug fixes test-first.