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.
npx agentmods add instructions/utensils/claudette/claude-mdgit clone --depth 1 https://github.com/utensils/claudetteWrote 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/utensils/claudette/claude-md)<a href="https://agentmods.dev/instructions/utensils/claudette/claude-md"><img src="https://agentmods.dev/badge/instructions/utensils/claudette/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 | $0.07622 | $0.07622 |
| Opus 5 | $0.03811 | $0.03811 |
| Sonnet 5 | $0.01524 | $0.01524 |
| Haiku 4.5 | $0.00762 | $0.00762 |
Grade A, and why
claudette 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 5d 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 — 303 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.
Claudette
Cross-platform desktop orchestrator for parallel Claude Code agents, built with Rust (Tauri 2) and React/TypeScript.
AI assistant configuration
This file is the source of truth for project conventions. Several companion configs read by other AI tools live alongside it and need to stay aligned when the rules here change:
.github/copilot-instructions.md— repo-wide guidance read by GitHub Copilot on every PR review and code suggestion..github/instructions/rust.instructions.md— scoped to**/*.rsviaapplyTofrontmatter..github/instructions/frontend.instructions.md— scoped tosrc/ui/**/*.{ts,tsx,css}..github/instructions/regression-review.instructions.md— scoped to all files; used during PR review for regression-first checking.AGENTS.md— symlink to this CLAUDE.md, read by Codex / OpenCode / other agent tools that look for that filename. Edit CLAUDE.md, never AGENTS.md.
When you change architecture, commands, code-style, regression rules, or god-file lists in this CLAUDE.md, scan the Copilot files for the same statement and update both. Drift here causes Copilot's PR reviews to flag (or miss) issues that don't match what we tell humans.
Documentation discipline
Always update the user-facing docs in the same PR as the feature change. Adding, removing, or changing user-visible behavior — settings, commands, CLI flags, keyboard shortcuts, environment variables, file locations, plugin manifests, notification triggers — requires a matching docs change. The docs site lives at site/src/content/docs/ (Astro Starlight). Two surfaces matter:
site/src/content/docs/features/<topic>.mdx— the per-feature deep-dive page. New cross-cutting feature → new page. Existing feature gained a knob → update the page. Register new pages in the sidebar nav atsite/astro.config.mjsso they're reachable.site/src/content/docs/features/settings.mdx— the flat settings reference table. Every Settings panel control belongs in this file's matching## <Section>table; add the row when you add the control.
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.
- 5d ago First seen · 303 lines · 7,622 tokens per session scan A e8c50ed149c5
claudette CLAUDE.md is an instructions file published in the GitHub repository utensils/claudette (75 stars, last pushed 3d ago), licensed MIT. It adds 7,622 tokens to every session, about $0.0381 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.
Other instructions, from other repositories
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.
icron CLAUDE.md
Instructions for zebbern/icron, covering icron, architecture, key directories, built-in tools and commands.
workstreams disposable.instructions.md
Guidelines for writing code using IDisposable.
relay CLAUDE.md
Claude Code instructions for simota/relay, covering claude.md, what this is, documentation map, runtime: bun-first and commands.