agentmods.dev

copilot-governance: Instructions file for Claude Code

.github/copilot-instructions.md

copilot-governance copilot-instructions.md is an instructions file for Claude Code, GitHub Copilot from chf3198/copilot-governance. It costs 3,614 tokens per session, scanned B, original, MIT.

A shared set of instructions for installing and keeping AI coding rules, skills, and lifecycle hooks consistent across VS Code Copilot, Claude Code, Google Antigravity, and machines.

In plain words
What is it for?
Use it to manage cross-platform AI coding configuration and add support for other tools that use file-based rules and skill folders.
Why use it?
It removes repeated manual setup and reduces differences between coding tools and computers.

Instructions file for Claude CodeGitHub Copilot

Written for Claude Code and GitHub Copilot: ${CLAUDE_PLUGIN_ROOT} variable, but also a Copilot instructions file. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is chf3198/copilot-governance's own configuration. It tells Claude Code and GitHub Copilot how to work on copilot-governance itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything copilot-governance configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 2repo 3mo ago B scan ✓ AI review 3,614 tokens original MIT
View source ↗ chf3198/copilot-governance
Reuse

Borrowing it

Nothing to install: this file belongs to chf3198/copilot-governance. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/chf3198/copilot-governance/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/chf3198/copilot-governance

Made for: Claude Code, 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 copilot-governance copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chf3198/copilot-governance/copilot-instructions/github.svg)](https://agentmods.dev/instructions/chf3198/copilot-governance/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/chf3198/copilot-governance/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/chf3198/copilot-governance/copilot-instructions/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.

agentmods 80×15 button for copilot-governance copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chf3198/copilot-governance/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/chf3198/copilot-governance/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,614 This file is loaded in full into every session.
When invoked 3,614 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
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 5.1 $0.03614 $0.03614
Opus 5.5 $0.01446 $0.01446
Sonnet 5.5 $0.00723 $0.00723
Haiku 4.5 $0.00361 $0.00361

Measured 2mo ago against content hash b927b4736747, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

copilot-governance copilot-instructions.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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| **Claude Code** | `~/.claude/` | `~/.claude/skills/` (also reads `.agents/skills/`) | `~/.claude/CLAUDE.md`, `~/.claude/rules/` | `~/.claude/settings.json` → `hooks` key |
.github/copilot-instructions.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions — copilot-governance

Purpose and Core Problem

This repo solves cross-platform, cross-machine AI governance: ensuring that any AI coding platform on any machine receives the same global instructions, skills, agents, and lifecycle hooks — without duplication or manual per-machine setup.

The strategic challenge: Different AI IDE platforms have different global-config formats and install paths. This repo packages global-items so they are easily installed once and auto-updating on every new machine, for any number of platforms and users.

Currently wired: VS Code Copilot, Claude Code, and Google Antigravity. The architecture accommodates any additional platform that supports file-based rules and a skills directory — adding one means writing a template rules file and one install.sh stanza. No skill files change.

Platform Landscape (April 2026)

The following platforms are currently wired. This list is not exhaustive — any platform that reads a markdown rules file and loads skills from a directory can be added.

Platform Global Config Root Skills Path Rules/Instructions Hooks
VS Code Copilot ~/.copilot/ (via settings) ~/.copilot/skills/ ~/.copilot/instructions/ ~/.copilot/hooks/global-standards.json
Claude Code ~/.claude/ ~/.claude/skills/ (also reads .agents/skills/) ~/.claude/CLAUDE.md, ~/.claude/rules/ ~/.claude/settings.json → hooks key
Google Antigravity ~/.gemini/ ~/.gemini/antigravity/skills/ ~/.gemini/GEMINI.md, .agents/rules/ Not yet documented
Any platform ~/.yourplatform/ symlink → skills/ template rules file via envsubst platform-specific

Key insight: Any platform that implements the agentskills.io open standard consumes the same SKILL.md format. Skills in skills/*/SKILL.md require zero per-platform variants — the install path is the only variable.

Read the full file on GitHub · 279 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. 2mo ago First seen · 279 lines · 3,614 tokens per session scan F b927b4736747

Subscribe to this mod's changes

copilot-governance copilot-instructions.md is an instructions file published in the GitHub repository chf3198/copilot-governance (2 stars, last pushed 3mo ago), licensed MIT. It adds 3,614 tokens to every session, about $0.0145 per session on Opus 5.5. 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.

Building agents
Related

copilot-governance copilot-instructions.md compared with instructions from other repositories

copilot-governance copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
copilot-governance copilot-instructions.mdchf3198/copilot-governanceInstructions file23mo agoMITB3,614Claude Code, GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode