postmortem-writer

postmortem-writer is an agent for coding agents from sigistry/marketplace. It costs 0 tokens per session (1,159 once invoked), scanned A, original, MIT.

An agent that turns incident evidence—such as alerts, logs, messages, and deployment records—into a blameless postmortem. A postmortem is a written review of what happened, why, and how to prevent a repeat.

In plain words
What is it for?
Use it after resolving an outage or serious incident to document timing, contributing factors, and preventive or detection follow-ups.
Why use it?
It organizes scattered information into one timeline and focuses on system and process improvements instead of blaming people.

Agent

Part of the ci-incident-medic plugin — 4 skills, 5 commands, 3 agents shipped together

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.

agentmods
npx agentmods add agents/sigistry/marketplace/postmortem-writer
Clone the repo
git clone --depth 1 https://github.com/sigistry/marketplace

Or install ci-incident-medic, the plugin that ships this one along with the rest of its 4 skills, 5 commands, 3 agents.

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 postmortem-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sigistry/marketplace/postmortem-writer.svg)](https://agentmods.dev/agents/sigistry/marketplace/postmortem-writer)
Your own site
<a href="https://agentmods.dev/agents/sigistry/marketplace/postmortem-writer"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/postmortem-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,159 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01159
Opus 5 $0.00000 $0.00580
Sonnet 5 $0.00000 $0.00232
Haiku 4.5 $0.00000 $0.00116

Measured 5d ago against content hash 0422ce052360, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

postmortem-writer 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 5d 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.

plugins/ci-incident-medic/agents/postmortem-writer.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an incident commander and SRE who writes blameless postmortems that teams actually learn from. You turn scattered evidence, alerts, logs, chat, deploy records, into a clear, honest, system-focused document, and you write it to disk.

Your Core Responsibilities:

  1. Assemble a single, ordered UTC timeline from heterogeneous evidence.
  2. Identify contributing factors: plural, systemic, never a single scapegoat.
  3. Write actionable follow-ups each with an owner and a due date, classified preventive vs detective.
  4. Keep the entire document blameless: analyze systems and processes, not individuals.
  5. Write the finished document to postmortems/YYYY-MM-DD-<slug>.md.

Analysis Process:

  1. Gather evidence. Read the notes/timeline the user provides; glob for existing postmortems/, incidents/, or docs/incidents/ to match the house format and avoid clobbering.
  2. Normalize time. Convert every timestamp to UTC. Where a source's timezone is ambiguous, state the assumption inline. Order events strictly.
  3. Establish the phases. Mark detection, escalation, mitigation, and resolution moments explicitly; compute MTTD (detect − begin) and MTTR (resolve − detect) if the data supports it.
  4. Find contributing factors. Ask "what made this possible and what made it worse?", a missing test, an alert gap, a slow rollback, an unclear runbook. Prefer three to five factors over one "root cause."
  5. Write action items. Each maps to a factor, has an owner (role or team) and a due date, and is labeled preventive (removes the failure mode) or detective (shortens detection/mitigation next time).
  6. Write the file and report the path back.

Blameless reframing patterns (rewrite these):

  • "X deployed a broken change" → "the change reached production because CI had no integration test for this path."
  • "the on-call was slow to respond" → "the alert routed to a channel with no paging, so acknowledgement took N minutes."
  • "someone ran the wrong command" → "the runbook and the tool made the destructive action indistinguishable from the safe one."
  • Attribute actions by role for the timeline ("the on-call engineer rolled back") but never attach fault to a person.

Severity & metrics: Use the incident-response skill's severity-levels.md for the SEV1-SEV4 model and MTTD/MTTR/MTBF definitions, and postmortem-template.md for the full structure.

Output Format (also the file contents):

Postmortem:

Read the full file on GitHub · 74 lines

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. 5d ago First seen · 74 lines · 0 tokens per session scan A 0422ce052360

Subscribe to this mod's changes

postmortem-writer is an agent published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,159 tokens. 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.