agtrace CLAUDE.md

agtrace CLAUDE.md is an instructions file for coding agents from lanegrid/agtrace. It costs 1,434 tokens per session, scanned A, original, Apache-2.0.

An instruction file for an AI coding agent working on agtrace, a Rust-based tool that records and analyzes AI-agent activity. It defines required project workflows, coding rules, and the repository structure.

In plain words
What is it for?
Use it to orient work in the agtrace codebase, which collects logs from agents such as Claude Code, Codex, and Gemini into a common timeline. The excerpt also requires checking available tasks and using a pull-request workflow.
Why use it?
It gives the agent the project's rules before it changes code, including how commands must be run and how changes should be submitted.

Instructions file

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 instructions/lanegrid/agtrace/claude-md
Clone the repo
git clone --depth 1 https://github.com/lanegrid/agtrace

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 agtrace CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lanegrid/agtrace/claude-md.svg)](https://agentmods.dev/instructions/lanegrid/agtrace/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lanegrid/agtrace/claude-md"><img src="https://agentmods.dev/badge/instructions/lanegrid/agtrace/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,434 This file is loaded in full into every session.
When invoked 1,434 The same file — it is already loaded in full.
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 $0.01434 $0.01434
Opus 5 $0.00717 $0.00717
Sonnet 5 $0.00287 $0.00287
Haiku 4.5 $0.00143 $0.00143

Measured 3d ago against content hash d3f0fe7627b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agtrace 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 3d 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 · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance for Claude Code when working in this repository.

Required

  • Always load /git-workflow first regardless of the conversation topic (before any other task)
  • Before starting work -> mise tasks to see available tasks
  • All commands MUST be run via mise run (works from any directory)
  • Prefer root-cause fixes over shortcuts (step back, reflect, take the senior engineer approach)
  • All changes go through PRs via /git-workflow (never commit directly to main)
  • Commit messages must be one-line, Conventional Commits format
  • Write everything in English (OSS project)

Project Overview

Rust-based local-first observability platform for AI agents. Normalizes diverse agent log formats (Claude Code, Codex, Gemini) into a unified AgentEvent timeline.

./
├── crates/
│   ├── agtrace-types/       # Type definitions (no deps)
│   ├── agtrace-core/        # File paths, env, workspace utils
│   ├── agtrace-providers/   # Log parsers (claude/, codex/, gemini/)
│   ├── agtrace-index/       # SQLite pointer index
│   ├── agtrace-engine/      # Session assembly, token calc
│   ├── agtrace-runtime/     # Orchestration layer
│   ├── agtrace-sdk/         # Public SDK
│   ├── agtrace-cli/         # CLI (depends on sdk only)
│   └── agtrace-testing/     # Shared test utilities
└── docs/                    # Design documents

Quick Reference

mise run verify              # fmt + clippy + test + build (full check)
mise run test                # run all tests
mise run clippy              # lint
mise run fmt                 # format code
mise run build:release       # release build
mise run git:status          # git workflow state + next action
mise tasks                   # list all tasks

Skills

Detailed knowledge is separated into .claude/skills/. Loaded automatically or manually via /skill-name.

Skill Purpose
/git-workflow Git workflow, branch management, PR creation
/agtrace-provider-normalization Provider schema investigation and domain abstraction

Read the full file on GitHub · 140 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. 3d ago First seen · 140 lines · 1,434 tokens per session scan A d3f0fe7627b2

Subscribe to this mod's changes

agtrace CLAUDE.md is an instructions file published in the GitHub repository lanegrid/agtrace (59 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,434 tokens to every session, about $0.0072 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.