perfetto-mcp-rs: Instructions file for Claude Code

CLAUDE.md

perfetto-mcp-rs CLAUDE.md is an instructions file for Claude Code from tooluse-labs/perfetto-mcp-rs. It costs 1,885 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a Rust server that lets coding agents query Perfetto trace files with SQL. Perfetto is a tool for examining performance traces, and MCP is a standard way for AI tools to call external services.

In plain words
What is it for?
Working on the server, compiling its Protocol Buffers definitions, running Rust tests and lint checks, and using PerfettoSQL against performance traces.
Why use it?
It explains how to build, test, lint, and install this server so an agent can inspect trace data consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is tooluse-labs/perfetto-mcp-rs's own configuration. It tells Claude Code how to work on perfetto-mcp-rs 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 perfetto-mcp-rs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tooluse-labs/perfetto-mcp-rs. 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/tooluse-labs/perfetto-mcp-rs/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tooluse-labs/perfetto-mcp-rs

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 perfetto-mcp-rs CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tooluse-labs/perfetto-mcp-rs/claude-md/github.svg)](https://agentmods.dev/instructions/tooluse-labs/perfetto-mcp-rs/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tooluse-labs/perfetto-mcp-rs/claude-md"><img src="https://agentmods.dev/badge/instructions/tooluse-labs/perfetto-mcp-rs/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 perfetto-mcp-rs CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tooluse-labs/perfetto-mcp-rs/claude-md"><img src="https://agentmods.dev/badge/instructions/tooluse-labs/perfetto-mcp-rs/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,885 This file is loaded in full into every session.
When invoked 1,885 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 $0.01885 $0.01885
Opus 5 $0.00942 $0.00942
Sonnet 5 $0.00377 $0.00377
Haiku 4.5 $0.00188 $0.00188

Measured 12d ago against content hash b50f6cfe94a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

perfetto-mcp-rs 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 12d 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 · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 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 is

An MCP (Model Context Protocol) server, written in Rust, that wraps Perfetto's trace_processor_shell so LLM agents can run PerfettoSQL queries against trace files (.pftrace, .perfetto-trace, .bin, …). The server speaks JSON-RPC over stdio via the rmcp crate. It is shipped as a single binary that also self-registers with Claude Code, Codex, and (manually) Qoder via its own install / uninstall subcommands.

Build / test / lint

protoc (Protocol Buffers compiler) is required — build.rs invokes prost-build to compile proto/trace_processor.proto. Install via apt install protobuf-compiler, brew install protobuf, or choco install protoc. On Unix, if $HOME/chromium/src/out/Default/protoc exists it is auto-used.

cargo build --release           # release binary at target/release/perfetto-mcp-rs
cargo test --all-targets        # unit + integration tests
cargo test <name>               # single test by substring (e.g. `cargo test e2e_smoke`)
cargo clippy --all-targets -- -D warnings    # CI lint (warnings are errors)
cargo fmt --all --check          # CI format check

CI runs with RUSTFLAGS: -D warnings on Ubuntu / macOS / Windows. Match that locally before pushing.

Integration tests under tests/ actually spawn trace_processor_shell against real fixtures in tests/fixtures/. On first run they download the binary (~35 MB, pinned to v54.0) from the Perfetto LUCI bucket into dirs::data_local_dir()/perfetto-mcp-rs/<version>/. To short-circuit: export PERFETTO_TP_PATH=/path/to/trace_processor_shell. CI intentionally does not cache this download — every PR exercises the atomic-persist + Windows-rename-retry path.

To run the server manually (without an MCP client) for ad-hoc debugging: RUST_LOG=debug cargo run. stdout is reserved for JSON-RPC; logs go to stderr.

Architecture

Five files carry the load. Read them in this order before making non-trivial changes:

Read the full file on GitHub · 126 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. 12d ago First seen · 126 lines · 1,885 tokens per session scan A b50f6cfe94a6

Subscribe to this mod's changes

perfetto-mcp-rs CLAUDE.md is an instructions file published in the GitHub repository tooluse-labs/perfetto-mcp-rs (21 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,885 tokens to every session, about $0.0094 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

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 · 7,126 tokens

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

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

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