cc-user-autopsy: Instructions file for Claude Code

CLAUDE.md

cc-user-autopsy CLAUDE.md is an instructions file for Claude Code from Imbad0202/cc-user-autopsy. It costs 1,410 tokens per session, scanned A, original, MIT.

Repository instructions for cc-user-autopsy, a Claude Code skill that reviews local coding-agent transcripts and usage data, then creates an HTML peer-review report. They describe the project, commands, tests, and known test status.

In plain words
What is it for?
Use them when working on this repository to run the full or filtered Python tests, run chart-layout tests, regenerate synthetic demo data, or understand the manual pipeline.
Why use it?
They give an agent the project context and the commands needed to check changes before merging. They also distinguish the Python test suite from the separate JavaScript chart-layout tests.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is Imbad0202/cc-user-autopsy's own configuration. It tells Claude Code how to work on cc-user-autopsy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cc-user-autopsy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Imbad0202/cc-user-autopsy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Imbad0202/cc-user-autopsy/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Imbad0202/cc-user-autopsy

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 cc-user-autopsy CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/imbad0202/cc-user-autopsy/claude-md/github.svg)](https://agentmods.dev/instructions/imbad0202/cc-user-autopsy/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/imbad0202/cc-user-autopsy/claude-md"><img src="https://agentmods.dev/badge/instructions/imbad0202/cc-user-autopsy/claude-md/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 cc-user-autopsy CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/imbad0202/cc-user-autopsy/claude-md"><img src="https://agentmods.dev/badge/instructions/imbad0202/cc-user-autopsy/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,410 This file is loaded in full into every session.
When invoked 1,410 The same file — it is already loaded in full.
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 $0.01410 $0.01410
Opus 5 $0.00705 $0.00705
Sonnet 5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured 9d ago against content hash eebe1d79342e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cc-user-autopsy CLAUDE.md 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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

A public Claude Code skill (SKILL.md is the skill entry point) that analyzes a user's local ~/.claude/projects/ transcripts and ~/.claude/usage-data/ metadata, then produces a self-contained HTML peer-review report. Python 3.9+, standard library only — no third-party runtime dependencies (pytest is used for testing only).

Commands

# Python test suite (the merge gate)
python3 -m pytest tests/ -q

# Single file / filtered tests
python3 -m pytest tests/test_locales.py -q
python3 -m pytest tests/test_build_html_additions.py -k zh_tw -q

# JS chart-layout tests (separate suite — run BOTH suites when touching js/chart_layout.js)
node --test tests/chart_layout.test.mjs

# Regenerate synthetic demo data (tests/demos never use real usage data)
python3 scripts/generate_demo_data.py    # writes to /tmp/cc-autopsy-demo/

The manual 4-step pipeline run (no skill/LLM involved, useful for debugging) is documented in README.md § "Running manually".

Known baseline as of 2026-07-14: 2 tests in tests/test_build_html_additions.py fail on clean main (test_zh_tw_build_contains_localized_strings, test_disclaimer_placeholder_in_template) — stale expectations from the story-first template redesign (PR #24), not something you broke. Check against clean main before assuming a failure there is yours.

Architecture

Two cooperating layers, orchestrated by SKILL.md:

  1. Deterministic Python pipeline (scripts/) — computes every number.
  2. LLM-authored narrative — Claude (running the skill) writes markdown files (peer-review, try-this-week, case-study) between pipeline steps; build_html.py injects them into the report.

Dataflow:

scan_transcripts.py → transcript-rows.jsonl   walks ~/.claude/projects/; merges agent-*.jsonl
                                              subagent runs into their parent session rows
scan_codex.py /       → *-rows.jsonl          optional adapters; feed aggregate.py via
scan_grok.py / scan_antigravity.py            repeated --cross-llm-rows flags
aggregate.py        → analysis-data.json      + session-meta + facets; 9-dim rule-based
                                              scoring; API-cost estimate via PRICING dict;
                                              also emits additive top-level cross_llm + ledger
                                              blocks when --cross-llm-rows is passed
sample_sessions.py  → samples.json            ≤24 representative sessions across 7 buckets
[Claude writes peer-review / try-this-week / case-study markdown]
build_html.py       → standalone HTML         thin CLI only; all rendering in report_render.py;
                                              SELF builds also append a snapshot to
                                              ~/.claude/usage-data/autopsy-history.jsonl

Read the full file on GitHub · 78 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. 9d ago First seen · 78 lines · 1,410 tokens per session scan A eebe1d79342e

Subscribe to this mod's changes

cc-user-autopsy CLAUDE.md is an instructions file published in the GitHub repository Imbad0202/cc-user-autopsy (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,410 tokens to every session, about $0.0070 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens