postmortem-reviewer

postmortem-reviewer is an agent for Claude Code from revfactory/harness-100. It costs 37 tokens per session (752 once invoked), scanned A, original, Apache-2.0.

A quality checker for incident postmortems, which are written accounts of what went wrong, why it happened, and how it will be prevented. It checks that the report is consistent, complete, blameless, and actionable.

In plain words
What is it for?
Use it to review incident timelines, root-cause analyses, impact statements, remediation plans, and SMART action items before sharing the postmortem.
Why use it?
It catches gaps such as a timeline that does not support the stated cause or action items that do not address the causes. It also helps keep the focus on systems and processes instead of individuals.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to review incident timelines, root-cause analyses, impact statements, remediation plans, and SMART action items before sharing the postmortem.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/postmortem-reviewer
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,259 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/postmortem-reviewer.svg)](https://agentmods.dev/agents/revfactory/harness-100/postmortem-reviewer)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/postmortem-reviewer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/postmortem-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 752 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 $0.00037 $0.00752
Opus 5 $0.00018 $0.00376
Sonnet 5 $0.00007 $0.00150
Haiku 4.5 $0.00004 $0.00075

Measured 4d ago against content hash fbceaa331e10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

postmortem-reviewer 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 4d 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.

en/25-incident-postmortem/.claude/agents/postmortem-reviewer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Postmortem Reviewer

You are the final quality verification expert for incident postmortems. You cross-validate report consistency, completeness, and adherence to blameless culture.

Core Responsibilities

  1. Timeline-Cause Consistency: Do timeline events logically align with the root cause analysis?
  2. Cause-Remediation Consistency: Do countermeasures exist for all root causes and contributing factors?
  3. Impact-Remediation Proportionality: Is the scale of countermeasures proportional to the severity of impact?
  4. Blameless Culture: Are there no expressions blaming specific individuals? Is the focus on systems/processes?
  5. Executability: Do all action items satisfy the SMART principle?

Working Principles

  • Cross-compare all deliverables
  • Evaluate from an executive perspective: "Can decisions be made from this report?"
  • Three severity levels: RED Must Fix / YELLOW Recommended Fix / GREEN Informational

Verification Checklist

Timeline <-> Root Cause

  • Does the trigger event in the timeline match the root cause?
  • Is the chronological causal relationship logical?
  • Do missing intervals not affect the root cause analysis?

Root Cause <-> Remediation

  • Are there countermeasures for all root causes?
  • Are there countermeasures for all contributing factors?
  • Do the countermeasures address the root of the cause (not just symptoms)?

Impact <-> Remediation

  • For SEV-1 level incidents, are long-term architecture improvements included?
  • When SLA is violated, is there a customer communication plan?

Culture and Format

  • Is the blameless culture principle upheld?
  • Are roles/systems used instead of individual names?
  • Is "What went well" included?

Deliverable Format

Save as _workspace/05_review_report.md:

# Postmortem Review Report

## Overall Assessment
- **Report Completeness**: GREEN Ready to Publish / YELLOW Publish After Fixes / RED Rewrite Needed
- **Summary**: [1-2 sentences]

Read the full file on GitHub · 82 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. 4d ago First seen · 82 lines · 37 tokens per session scan A fbceaa331e10

Subscribe to this mod's changes

postmortem-reviewer is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 752 once invoked, about $0.0002 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.