Borrowing it
Nothing to install: this file belongs to madeye/mcp-cli. 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/madeye/mcp-cli/main/CLAUDE.mdgit clone --depth 1 https://github.com/madeye/mcp-cliWrote 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/madeye/mcp-cli/claude-md)<a href="https://agentmods.dev/instructions/madeye/mcp-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/madeye/mcp-cli/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/madeye/mcp-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/madeye/mcp-cli/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 | $0.01978 | $0.01978 |
| Opus 5.5 | $0.00791 | $0.00791 |
| Sonnet 5.5 | $0.00396 | $0.00396 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
mcp-cli 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 99 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.
Commands
CI gates (must pass before pushing — see user global rules):
cargo fmt --all -- --check
cargo clippy --workspace --all-targets -- -D warnings
cargo test --workspace --all-targets
Other common commands:
cargo build --release # build both binaries
cargo run -p daemon -- --root /path/to/project # run daemon (default socket: /tmp/mcp-cli.sock)
cargo run -p mcp-bridge # run stdio bridge
cargo test -p daemon changelog::tests::push_advances_version # single test by path
cargo test -p daemon -- --nocapture # see tracing output from tests
RUST_LOG=debug cargo run -p daemon # bump log level (daemon defaults to info, bridge to warn)
Daemon flags worth knowing: --socket, --root, --changelog-capacity (ring size, default 4096), --search-cache-capacity (LRU size, default 64; 0 disables), --parse-cache-capacity (tree-sitter parse LRU, default 256; 0 disables), --no-prewarm (skip startup page-cache walk — useful in tests/benchmarks).
Architecture
Three-crate Cargo workspace implementing a sidecar daemon + thin MCP bridge pattern. The point is to amortize kernel overhead: agents make hundreds of small fs.read / git.status / search.grep calls, and each one hits a long-lived in-process daemon instead of forking cat/git/rg.
MCP client (Claude Code / Codex) ──stdio──> mcp-cli-bridge ──UDS──> mcp-cli-daemon
(crates/mcp-bridge) (crates/daemon)
↑ owns project state:
mmap, libgit2, grep-searcher,
notify-rs watcher + ChangeLog
Crates
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.
- 2mo ago First seen · 99 lines · 1,978 tokens per session scan A 0507ab079d76
mcp-cli CLAUDE.md is an instructions file published in the GitHub repository madeye/mcp-cli (117 stars, last pushed 6mo ago), licensed MIT. It adds 1,978 tokens to every session, about $0.0079 per session on Opus 5.5. 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.
mcp-cli CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-cli CLAUDE.mdmadeye/mcp-cli | Instructions file | 117 | 6mo ago | MIT | A | 1,978 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |