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/yurakawa/mskills/copilot-instructionsgit clone --depth 1 https://github.com/yurakawa/mskillsWrote 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/yurakawa/mskills/copilot-instructions)<a href="https://agentmods.dev/instructions/yurakawa/mskills/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/yurakawa/mskills/copilot-instructions.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 | $0.01324 | $0.01324 |
| Opus 5 | $0.00662 | $0.00662 |
| Sonnet 5 | $0.00265 | $0.00265 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
mskills 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 4d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mskills - Copilot Instructions
Project Overview
mskills is a CLI tool designed to manage "Agent Skills" for various AI agents (Claude, Codex, Gemini, Copilot, Cursor) in a centralized way. It allows users to register skills, enable agents, and apply skills across different agent configurations through symbolic links or file copies.
Tech Stack
- Language: TypeScript (strict mode enabled)
- Runtime: Node.js (ES2022, ESM modules with
.jsextension imports) - Package Manager: npm
- Testing: Vitest
- CLI Framework: Commander.js
- UI/Styling: chalk (terminal colors), ora (spinners)
- Validation: Zod for runtime type checking
Architecture
Directory Structure
src/- Source code in TypeScriptagents/- Agent definitions and management (base.ts, manager.ts)commands/- CLI command implementations (add, remove, list, apply, agents)config/- Configuration file management (~/.mskills.json)skills/- Skill management logicindex.ts- Main CLI entry point
dist/- Compiled JavaScript output (not committed)demo-skill/- Example skill for demonstrations
Key Concepts
- Skills: Directories containing agent instructions, registered with a name and path
- Agents: Supported AI agents with their configuration directories (~/.claude/skills, ~/.copilot/skills, etc.)
- Config: JSON file stored at
~/.mskills.jsoncontaining registered skills and enabled agents - Apply: Creates symbolic links (or copies) from skill directories to agent skill directories
Coding Standards
TypeScript Guidelines
- Use strict mode - Already enabled in tsconfig.json
- Avoid
anytype - Use proper typing orunknownwith type guards - ESM imports - Always use
.jsextensions for local module imports (e.g.,'./config/index.js') - Use modern Node.js APIs - Prefer
node:fs/promises,node:path,node:osimports - Commander types - Import types with
import type { Command } from 'commander' - Error handling - Catch errors and display user-friendly messages with chalk.red()
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.
- 4d ago First seen · 153 lines · 1,324 tokens per session scan A c71bd92db4ab
mskills copilot-instructions.md is an instructions file published in the GitHub repository yurakawa/mskills (3 stars, last pushed 4mo ago), licensed MIT. It adds 1,324 tokens to every session, about $0.0066 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 2026-08-31.
Other instructions, from other repositories
mcp-steroid CLAUDE.md
Claude Code instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.
nopua AGENTS.md
Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.
skills CLAUDE.md
Instructions for mixedbread-ai/skills, covering mixedbread skills, repository structure, conventions, adding a new skill and testing a skill.
video-podcast-maker AGENTS.md
AGENTS.md instructions for Agents365-ai/video-podcast-maker, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
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.
coach CLAUDE.md
Instructions for Andamio-Platform/coach, covering claude.md and claude code-specific notes.