causetrace: Instructions file for Claude Code

CLAUDE.md

causetrace CLAUDE.md is an instructions file for Claude Code from milkoor/causetrace. It costs 2,858 tokens per session, scanned A, original, MIT.

Repository instructions for causetrace, a tool that records actions taken by coding agents and links each action to the event that caused it. It includes guidance for checking dependencies, installing the project, running tests, and using its command-line views.

In plain words
What is it for?
Checking change impact, installing causetrace in editable mode, running its test suite, viewing agent sessions as timelines or cause-and-effect trees, and running its demo.
Why use it?
A flat activity log shows what happened but not why. These instructions help developers understand causetrace’s structure and verify changes safely before modifying the code.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is milkoor/causetrace's own configuration. It tells Claude Code how to work on causetrace 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 causetrace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to milkoor/causetrace. 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/milkoor/causetrace/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/milkoor/causetrace

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 causetrace CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/milkoor/causetrace/claude-md.svg)](https://agentmods.dev/instructions/milkoor/causetrace/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/milkoor/causetrace/claude-md"><img src="https://agentmods.dev/badge/instructions/milkoor/causetrace/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,858 This file is loaded in full into every session.
When invoked 2,858 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 $0.02858 $0.02858
Opus 5 $0.01429 $0.01429
Sonnet 5 $0.00572 $0.00572
Haiku 4.5 $0.00286 $0.00286

Measured 6d ago against content hash d732f489000d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

causetrace 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 6d 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 · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 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 causetrace does

causetrace is an Agent Runtime Observation primitive — it captures tool calls from coding agents (Claude Code, OpenCode, Aider, Continue.dev, Codex CLI, GitHub Copilot) and links them into causal trees and DAGs via parent_event_id chains. Instead of flat timelines, every event records why it happened, enabling replay, root-cause analysis, and behavior explanation.

Before making changes

Read docs/dependency-map.md first — it shows which modules depend on what. Use it to assess change impact before modifying any file.

Build & test

# Install (editable)
pip install -e .

# Run all tests
python -m pytest tests/ -v

# Run a single test
python -m pytest tests/test_invariants.py::test_causality_chain_links -v

# Run the installed first-run path
causetrace demo

CLI

causetrace timeline [session_id]    # Flat chronological view
causetrace tree [session_id]            # Causal parent→child tree
causetrace tree [session_id] --quality  # Tree with causal quality report
causetrace tree [session_id] --compress # Compress consecutive same-tool runs ([×N])
causetrace graph [session_id]       # Multi-parent DAG (fan-in)
causetrace sessions                 # List recorded sessions
causetrace export <session_id>      # Export as JSON
causetrace replay [session_id]      # Replay trace with provenance
causetrace why <session_id> <eid>   # Trace causal chain from event
causetrace enrich-sessions                # List Claude Code project sessions
causetrace enrich <session_id> [--save]   # Enrich from Claude Code project session
causetrace enrich-opencode-sessions       # List OpenCode DB sessions
causetrace enrich-opencode <id> [--save]  # Enrich from OpenCode DB session
causetrace enrich-codex-sessions          # List Codex CLI rollout sessions
causetrace enrich-codex <id> [--save]     # Enrich from Codex CLI rollout session
causetrace opencode [--save]              # Scan OpenCode logs
causetrace aider [--save] -- [args]       # Run aider with tracing
causetrace continue [--save]              # Scan Continue.dev logs
causetrace codex [--save]                 # Legacy scan path; prefer enrich-codex
causetrace copilot [--save]               # Scan GitHub Copilot agent logs
causetrace doctor                         # Diagnose agent configuration and data sources
causetrace stats [session]                # Structural session statistics
causetrace roots [session]                # Root events with downstream metrics
causetrace critical-path [session]        # Longest root-to-leaf causal chain
causetrace patterns [session]             # Repeated tool patterns & transitions
causetrace patterns [session] --csv       # Causal transitions as CSV
causetrace validate [session]             # Check JSONL/references/cycles
causetrace validate --all                 # Validate all stored sessions
causetrace annotate <session> [...]       # Store sidecar metadata
causetrace compare <a> <b>                # Compare session topology
causetrace demo                            # Create an inspectable sample trace
causetrace install-claude-hook             # Configure recording hooks safely
causetrace uninstall-claude-hook           # Remove only managed hooks

Read the full file on GitHub · 194 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. 6d ago First seen · 194 lines · 2,858 tokens per session scan A d732f489000d

Subscribe to this mod's changes

causetrace CLAUDE.md is an instructions file published in the GitHub repository milkoor/causetrace (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,858 tokens to every session, about $0.0143 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.

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 · 5,182 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