Borrowing it
Nothing to install: this file belongs to S-Nakamur-a/conductor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/S-Nakamur-a/conductor/main/CLAUDE.mdgit clone --depth 1 https://github.com/S-Nakamur-a/conductorWrote 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.
[](https://agentmods.dev/instructions/s-nakamur-a/conductor/claude-md)<a href="https://agentmods.dev/instructions/s-nakamur-a/conductor/claude-md"><img src="https://agentmods.dev/badge/instructions/s-nakamur-a/conductor/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.
<a href="https://agentmods.dev/instructions/s-nakamur-a/conductor/claude-md"><img src="https://agentmods.dev/badge/instructions/s-nakamur-a/conductor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.06152 | $0.06152 |
| Opus 5 | $0.03076 | $0.03076 |
| Sonnet 5 | $0.01230 | $0.01230 |
| Haiku 4.5 | $0.00615 | $0.00615 |
Grade A, and why
conductor 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 373 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.
Project Overview
Conductor is a terminal-based Git workspace and code review TUI written in Rust. It manages multiple git worktrees, launches Claude Code sessions via embedded PTYs, reviews diffs, and provides structured inline review comments — designed for an AI-assisted development workflow.
Commands
cargo build · cargo run [-- <repo-path>] · cargo test --workspace ·
cargo clippy --workspace · cargo check --workspace · make fmt.
Set RUST_LOG=debug for logging.
Always pass --workspace — bare cargo test / cargo clippy only cover the
root conductor package, which is a five-line main.rs; everything else is in
crates/. default-members is left alone so cargo run stays unambiguous.
CI checks cargo fmt --all -- --check and cargo clippy --workspace -- -D warnings
on every pull request — a warning is a failure, including one inherited from main. .githooks/pre-commit runs the same fmt check locally, but wiring
it up is each developer's own business — the repository does not install it.
MCP Server (conductor mcp-serve, crates/conductor-mcp/)
The review DB tools and the code-index tools (search_symbols / read_symbol,
crates/conductor-mcp/src/tools/symbols.rs) are served by the conductor binary
itself over stdio — no separate build step, no Node. cargo install --path . updates the binary and its
MCP tools together, which is the point: they used to be two artifacts on two
release channels and drifted apart. plugins/conductor/.mcp.json starts it for
the Claude Code sessions inside the TUI, resolving the DB from
$CONDUCTOR_DB_PATH (injected by conductor-svc's pty/spawn.rs). The AI review
does not go through MCP — its artifact is a JSON file written by revidere.
- Tool contract: the
#[tool]handlers incrates/conductor-mcp/src/tools.rs. Their doc comments become the JSON Schema descriptions the model reads, so changing one changes the tool's public contract — treat them as API, not commentary. - Never print to stdout from anything reachable by
mcp-serve; it would corrupt the protocol. Logging goes to stderr, andconductor-mcp/tests/no_stdout.rsguards it.
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.
- today Changed · +6 lines · +153 tokens per session ef1420d43ff2
- yesterday Changed · +6 lines · +138 tokens per session c00ee57c00bb
- 2d ago Changed · +9 lines · -99 tokens per session 5dcbdf15b9be
- 4d ago Changed · +32 lines · +615 tokens per session 43917096cf40
- 9d ago First seen · 320 lines · 5,345 tokens per session scan A 8ffbade70cc4
conductor CLAUDE.md is an instructions file published in the GitHub repository S-Nakamur-a/conductor (2 stars, last pushed yesterday), licensed MIT. It adds 6,152 tokens to every session, about $0.0308 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.
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.