claudette copilot-instructions.md

claudette copilot-instructions.md is an instructions file for GitHub Copilot from utensils/claudette. It costs 1,119 tokens per session, scanned A, original, MIT.

Project instructions for Claudette, a desktop application that coordinates multiple Claude Code agents. The project uses a Rust backend, a React and TypeScript interface, a local database, terminal sessions, plugins, and separate Git workspaces.

In plain words
What is it for?
Use them when changing or reviewing Claudette code, especially backend commands, frontend state, database fields, CLI behavior, plugin handling, settings, terminal sessions, or Git worktree operations.
Why use it?
They help contributors preserve existing behavior across the app's database, commands, settings, terminals, worktrees, and user interface. They emphasize finding the current contract and adding tests when behavior changes.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/utensils/claudette/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/utensils/claudette

Made for: GitHub Copilot.

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 claudette copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/utensils/claudette/copilot-instructions.svg)](https://agentmods.dev/instructions/utensils/claudette/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/utensils/claudette/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/utensils/claudette/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,119 This file is loaded in full into every session.
When invoked 1,119 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01119 $0.01119
Opus 5 $0.00560 $0.00560
Sonnet 5 $0.00224 $0.00224
Haiku 4.5 $0.00112 $0.00112

Measured 3d ago against content hash 5340c7d7c6b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claudette copilot-instructions.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 3d 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.

.github/copilot-instructions.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claudette Repository Instructions

Claudette is a cross-platform desktop orchestrator for parallel Claude Code agents. It uses a Tauri 2 Rust backend, a React/TypeScript frontend, SQLite via rusqlite, Tokio process management, git worktrees, xterm.js terminals, Lua plugins, and a local CLI that talks to the running GUI over IPC.

Follow the existing architecture. Core behavior belongs in the claudette crate under src/. src-tauri/src/commands/ should stay thin Tauri wrappers. Shared data types belong in src/model/ and must derive Serialize. Frontend state lives in Zustand slices under src/ui/src/stores/slices/, not ad hoc globals.

Treat regressions as the main risk. Before changing behavior, identify the current contract: persisted DB fields, Tauri command payloads, CLI output, plugin manifests, settings keys, localized strings, terminal/session semantics, worktree behavior, and visible UI workflows. Do not remove, rename, or silently reinterpret any of these unless the task explicitly asks for that change.

If a behavior change is intentional, call it out plainly in the PR summary or review response and add/update tests that pin the new behavior. If the change was incidental, preserve compatibility instead.

Do not fix type, lint, or test failures by deleting tests, removing UI controls, dropping state fields, weakening assertions, or broadening types. Fix the underlying mismatch and keep existing user-visible capabilities intact.

Control god files. Do not make already-large files the default destination for new behavior. Prefer a focused module, helper, slice, hook, or component near the owning feature, then wire it through the existing entry point. Be especially cautious with src/diff.rs, src/git.rs, src/plugin.rs, src/mcp.rs, src/mcp_supervisor.rs, the largest siblings of the recently-split src-tauri/src/commands/agent_backends/ directory (gateway_translate.rs, runtime_dispatch.rs, discovery.rs, config.rs), src-tauri/src/commands/*, src-tauri/src/voice.rs, src-tauri/src/ipc.rs, src/ui/src/components/sidebar/Sidebar.tsx, src/ui/src/components/chat/ChatPanel.tsx, src/ui/src/components/chat/ChatInputArea.tsx, src/ui/src/components/terminal/TerminalPanel.tsx, src/ui/src/services/tauri.ts, and large CSS modules.

When touching a god file, keep the diff surgical or extract cohesive behavior first. New code should reduce or isolate complexity, not add another unrelated responsibility.

For subprocess spawns (agent, MCP, setup scripts), use crate::env::enriched_env().apply(&mut cmd) to forward the user's captured shell environment. The capture happens at app launch via prewarm_shell_env in src/env.rs and merges into the env-provider dispatcher at precedence 0 (direnv / mise / dotenv / nix-devshell layer on top). enriched_path() is kept as a backwards-compat accessor returning just PATH — new code should prefer enriched_env() to inherit the full set.

Use the repo's tools. Rust CI expects cargo fmt --all --check, cargo clippy -p claudette -p claudette-server -p claudette-cli --all-targets --all-features with RUSTFLAGS=-Dwarnings, and cargo test --all-features. Frontend CI expects cd src/ui && bun install --frozen-lockfile, bunx tsc --noEmit, bun run lint:css, bun run build, and bun run test.

Always run cd src/ui && bunx tsc -b after TypeScript changes. Vitest uses esbuild and does not type-check the project.

Never edit, rename, or delete released SQL migrations under src/migrations/*.sql. Add a new forward migration and register it in src/migrations/mod.rs.

Use bun, not npm. Keep TypeScript strict and avoid any. Keep Rust cross-platform with explicit #[cfg(...)] gates for OS-specific code.

When spawning subprocesses, never use a raw std::process::Command::new / tokio::process::Command::new. On Windows a GUI process spawns a child with no CREATE_NO_WINDOW flag and a blank cmd.exe window flashes on screen — a bug invisible in dev builds and only seen in release. Use the claudette::process command helper, or CommandWindowExt::no_console_window(). Flag any raw Command::new in review as a Windows console-flash regression unless it is a deliberate user-facing terminal launch using .new_console_window().

Read the full file on GitHub · 30 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. 3d ago First seen · 30 lines · 1,119 tokens per session scan A 5340c7d7c6b6

Subscribe to this mod's changes

claudette copilot-instructions.md is an instructions file published in the GitHub repository utensils/claudette (75 stars, last pushed 4d ago), licensed MIT. It adds 1,119 tokens to every session, about $0.0056 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

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.

kungfu-systems/kungfu · 45 tokens

superset CLAUDE.md

Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

superset-sh/superset · 4 tokens

growmos AGENTS.md

Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.

codician-team/growmos · 606 tokens

ideate AGENTS.md

Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.

paultyng/ideate · 641 tokens

omk CLAUDE.md

Claude Code instructions for dmae97/omk, covering claude.md, precedence (read this first), omk runtime map (what you're operating inside), this repo: open-multi-agent-kit / omk monorepo and build / test / check commands.

dmae97/omk · 1,841 tokens

orchestrator CLAUDE.md

Instructions for c9r-io/orchestrator, covering claude.md, forbidden operations, never delete the runtime database and starting a daemon.

c9r-io/orchestrator · 690 tokens