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/sbroenne/skillpm/copilot-instructionsgit clone --depth 1 https://github.com/sbroenne/skillpmWhat 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 | $0.01296 | $0.01296 |
| Opus 5 | $0.00648 | $0.00648 |
| Sonnet 5 | $0.00259 | $0.00259 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
skillpm 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 2d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions for skillpm
What is skillpm?
skillpm is npm for Agent Skills. It builds on top of npm to add skill-awareness: resolving skill dependency trees, scanning for installed skills, and wiring them into agent directories.
Design principle: stay as close to npm as possible. skillpm should feel like npm. Same package.json, same node_modules, same package-lock.json, same registry. skillpm only adds what npm cannot do by itself: discovering installed skills and linking them into agent directories.
skillpm only manages npm-hosted skills. For broader project-level agent packaging or non-npm sources, point users to APM or to the underlying host-specific tools.
The project is developed in TypeScript.
Key dependencies (don't reimplement — use these)
| Package | Type | What it does | How skillpm uses it |
|---|---|---|---|
| npm | CLI (shell out) | Package management, dependency resolution, registry, lockfiles, caching | All package operations — skillpm install calls npm install under the hood |
skills |
CLI (shell out) | Links skills into agent directories | npx skills add <path> — wires npm-installed skills into agent dirs |
skills-ref |
CLI (shell out) | Validates SKILL.md against the Agent Skills spec | npx skills-ref validate <path> during skillpm publish |
Before writing any new code, check whether one of these tools already does it.
What are Agent Skills?
Agent Skills are modular, reusable packages of instructions, scripts, and resources that AI agents can dynamically load to extend their capabilities. They follow an open standard adopted by Claude, Codex, Cursor, Gemini CLI, Augment, and others.
Skill package structure
A skill is a standard npm package with the skill content in a skills/<name>/ subdirectory:
my-skill/
├── package.json # npm metadata, deps, keywords: ["agent-skill"]
├── README.md
├── LICENSE
└── skills/
└── my-skill/
├── SKILL.md
├── scripts/
├── references/
└── assets/
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.
- 2d ago First seen · 139 lines · 1,296 tokens per session scan A 5504a731a7af
skillpm copilot-instructions.md is an instructions file published in the GitHub repository sbroenne/skillpm (14 stars, last pushed 2d ago), licensed MIT. It adds 1,296 tokens to every session, about $0.0065 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
huly-mcp CLAUDE.md
Instructions for dearlordylord/huly-mcp, covering project instructions, design principle: llm-first api, project harness (copy to new projects), package manager and verification.
lola CLAUDE.md
Instructions for LobsterTrap/lola, covering active technologies and recent changes.
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
entroly CLAUDE.md
Instructions for juyterman1000/entroly, covering claude.md, gstack operating protocol, default workflow, entroly trust invariants and review checklist.
autonomous-os AGENTS.md
Instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
spellbook AGENTS.md
Instructions for majiayu000/spellbook, covering spellbook agent contract, routing, scope rules, threads long-run guardrails and validation.