incident-postmortem-report

incident-postmortem-report is a skill for Claude Code, Codex from caipe-io/ai-platform-engineering. It costs 76 tokens per session (906 once invoked), scanned A, original, Apache-2.0.

A guide for writing a blameless post-mortem: a factual review of an outage or other incident that affected customers. It covers what happened, why it happened, and how to prevent a repeat.

In plain words
What is it for?
Use it to draft or complete an incident report for engineers, leaders, compliance teams, or customers, using details such as logs, metrics, deployments, and communications.
Why use it?
It gives teams a consistent way to record impact, timelines, causes, contributing factors, and follow-up work after an incident.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to draft or complete an incident report for engineers, leaders, compliance teams, or customers, using details such as logs, metrics, deployments, and communications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/caipe-io/ai-platform-engineering/incident-postmortem-report
Install

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.

Any agent
npx skills add caipe-io/ai-platform-engineering --skill incident-postmortem-report
Clone the repo
git clone --depth 1 https://github.com/caipe-io/ai-platform-engineering

Made for: Claude Code, Codex.

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-postmortem-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/incident-postmortem-report/github.svg)](https://agentmods.dev/skills/caipe-io/ai-platform-engineering/incident-postmortem-report)
Your own site
<a href="https://agentmods.dev/skills/caipe-io/ai-platform-engineering/incident-postmortem-report"><img src="https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/incident-postmortem-report/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-postmortem-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/caipe-io/ai-platform-engineering/incident-postmortem-report"><img src="https://agentmods.dev/badge/skills/caipe-io/ai-platform-engineering/incident-postmortem-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 906 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00076 $0.00906
Opus 5 $0.00038 $0.00453
Sonnet 5 $0.00015 $0.00181
Haiku 4.5 $0.00008 $0.00091

Measured 9d ago against content hash 376a8b95a474, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

incident-postmortem-report 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.

charts/ai-platform-engineering/data/skills/incident-postmortem-report/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Incident Post-Mortem Report

Guide the user through producing a blameless, audit-ready post-mortem suitable for engineering leadership, compliance, and future incident prevention.

Instructions

Phase 1: Scope and audience

  1. Confirm what incident is in scope (ticket ID, time window, service, or free-text summary).
  2. Identify audience (internal engineering only vs. includes executives or customers) and adjust depth of business impact language.
  3. List facts already known vs. gaps that need research (logs, metrics, deploys, comms).

Phase 2: Structure the report

Use the sections below in order unless the organization mandates a different template. Fill each section with concrete data; avoid vague statements.

  1. Executive summary — 2–4 sentences: what broke, who was affected, how long, current status.
  2. Impact — Quantify: duration, error rates, revenue/users affected if known, SLA breach yes/no.
  3. Timeline — UTC timestamps, short event labels. Include detection, escalation, mitigation, full recovery.
  4. Root cause — Single primary cause, explained clearly. Use 5 Whys or equivalent if helpful.
  5. Contributing factors — Environment, process, tooling, or communication issues that amplified impact (not blame).
  6. What went well — Detection, runbooks, teamwork, rollback, comms.
  7. What went wrong — Gaps in monitoring, deploy process, testing, on-call routing, documentation.
  8. Corrective actions — Short-term fixes with owners and dates.
  9. Preventive actions — Longer-term hardening (tests, SLOs, chaos, capacity).
  10. Lessons learned — 2–5 bullet takeaways for the org.
  11. References — Links to incidents, PRs, dashboards, chat threads (no secrets).

Phase 3: Tone and quality bar

  • Blameless: describe systems and processes, not individuals.
  • Specific: numbers, tool names, versions, ticket keys.
  • Actionable: every action item has an owner and a target date when possible.

Output Format

Read the full file on GitHub · 100 lines

Files

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.

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 · 100 lines · 76 tokens per session scan A 376a8b95a474

Subscribe to this mod's changes

incident-postmortem-report is a skill published in the GitHub repository caipe-io/ai-platform-engineering (407 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 906 once invoked, about $0.0004 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 2026-08-30.