Borrowing it
Nothing to install: this file belongs to pmbrull/claustre. 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/pmbrull/claustre/main/CLAUDE.mdgit clone --depth 1 https://github.com/pmbrull/claustreWrote 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/pmbrull/claustre/claude-md)<a href="https://agentmods.dev/instructions/pmbrull/claustre/claude-md"><img src="https://agentmods.dev/badge/instructions/pmbrull/claustre/claude-md.svg" alt="Measured on agentmods" 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 | $0.07719 | $0.07719 |
| Opus 5 | $0.03860 | $0.03860 |
| Sonnet 5 | $0.01544 | $0.01544 |
| Haiku 4.5 | $0.00772 | $0.00772 |
Grade B, and why
claustre CLAUDE.md scanned grade B with 1 finding 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep "stop_hook_summary" ~/.claude/projects/<dir>/<session>.jsonl How it starts
The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claustre Development Guide
Build & Test
cargo build # Debug build (CLI + lib)
cargo build --workspace # Build everything including Tauri app
cargo build --release # Release build
cargo test # Run all tests (skills, store, config modules)
cargo test --workspace # Run all tests including Tauri app tests
cargo clippy # Lint (strict: clippy::all denied, pedantic warned)
cargo fmt --check # Check formatting
The project must compile cleanly with zero clippy warnings before committing.
Tauri App
cargo build -p claustre-app # Build the Tauri desktop app
cargo test -p claustre-app # Run Tauri app tests
The Tauri app is at app/src-tauri/ and shares the claustre library. Launch via claustre app.
Architecture Overview
Cargo workspace with a shared library (src/lib.rs) and two binaries:
claustre(CLI + TUI) —src/main.rsclaustre-app(Tauri desktop app) —app/src-tauri/
Both binaries share the same library modules. Eleven modules, one responsibility each:
| Module | Purpose |
|---|---|
main.rs |
CLI entry point (clap). Dispatches to TUI or subcommands |
config/ |
Config loading (config.toml), CLAUDE.md merge, path helpers |
store/ |
SQLite database: schema, models, CRUD queries |
tui/ |
ratatui terminal UI: app state, event loop, rendering |
session/ |
Git worktree lifecycle + session setup |
pty/ |
Native PTY embedding via portable-pty + vt100 |
skills/ |
skills.sh CLI wrapper, ANSI parser |
scanner/ |
Passive scanner for external Claude Code sessions |
session_host.rs |
Detached PTY owner + Unix socket server for session IPC |
update.rs |
Auto-update: GitHub release check, download, rollback |
Entity Model
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.
- 7d ago First seen · 488 lines · 7,719 tokens per session scan B 7805de77e116
claustre CLAUDE.md is an instructions file published in the GitHub repository pmbrull/claustre (2 stars, last pushed 5mo ago), licensed MIT. It adds 7,719 tokens to every session, about $0.0386 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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).
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.