post-mortem

A code-review command that examines a Claude Code conversation, either the current session or an imported chat record. It looks for what worked, what failed, and where the agent could improve.

In plain words
What is it for?
Use it to review a chat after a bug, missed setup step, or poor build process. Provide a chat file, shared-chat URL, or extra focus such as testing problems.
Why use it?
It turns a failed or inefficient coding session into specific changes for CLAUDE.md, the project instructions file, or system prompts. This helps reduce repeated mistakes in later sessions.

Command

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 commands/walterra/claude-code-helpers/post-mortem
Clone the repo
git clone --depth 1 https://github.com/walterra/claude-code-helpers
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 994 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 $0.00014 $0.00994
Opus 5 $0.00007 $0.00497
Sonnet 5 $0.00003 $0.00199
Haiku 4.5 $0.00001 $0.00099

Measured 2d ago against content hash 4cf3574d12ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

post-mortem 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 2d 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.

commands/post-mortem.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Claude Code chat histories to identify successes, failures, and improvement opportunities. Generate actionable recommendations for updating CLAUDE.md and system prompt files to prevent similar issues.

If no arguments provided: Analyze the current chat session

Arguments can contain:

  • Path to chat export file (JSON, markdown, or text format) OR URL to shared chat export
  • Optional additional context, focus areas, or specific concerns

Examples:

  • /post-mortem (analyzes current chat)
  • /post-mortem ~/Downloads/chat-export.json
  • /post-mortem https://claude.ai/chat/abc123 focus on build process issues
  • /post-mortem ./failed-session.md Claude kept missing test setup

Actual arguments provided:

==== ARGUMENTS START

$ARGUMENTS

==== ARGUMENTS END

Process

Phase 1: ANALYSIS

  1. Load and analyze chat:

    • If no arguments: Analyze the current conversation history and interactions
    • If file path provided: Use Read tool to load chat export
    • If URL provided: Use WebFetch tool to fetch chat export
    • Use any additional context provided to guide analysis focus
    • Parse the conversation flow and identify key interactions
    • Extract tool and command usage patterns and decision points
    • Note any error messages, confusion, or repeated attempts
  2. Categorize interactions:

    • Successful patterns: What worked well and why
    • Failed patterns: What went wrong and root causes
    • Missed opportunities: Where Claude could have been more effective
    • User friction points: Where the user had to provide additional guidance

Phase 2: ASSESSMENT

  1. Command usage:

    • Identify Claude Code custom commands used
    • Locate and read the command markdown files in ./.claude/commands or ~/.claude/commands
    • Treat the command markdown files as system prompt files to be assessed and possibly improved
  2. Identify root causes:

    • Missing context in CLAUDE.md and other system prompt files
    • Unclear or ambiguous instructions
    • Missing commands or workflow guidance
    • Tool selection issues
    • Architecture understanding gaps

Read the full file on GitHub · 138 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. 2d ago First seen · 138 lines · 14 tokens per session scan A 4cf3574d12ca

Subscribe to this mod's changes

post-mortem is a command published in the GitHub repository walterra/claude-code-helpers (5 stars, last pushed 12mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 994 once invoked, about $0.0001 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.