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/nordicnode/skillpack/claude-mdgit clone --depth 1 https://github.com/nordicnode/skillpackWhat 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 | $0.00803 | $0.00803 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
skillpack 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 yesterday.
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.
This is a copy
100% identical to skillpack copilot-instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skillpack
Generate and verify the agent-distribution layer for any OSS project
When to use
Invoke this tool when the user's task matches any of these triggers:
- generate a claude code skill pack
- verify agent-discoverability of a CLI or library
- scaffold claude plugin distribution files
When NOT to use
- Do not use this tool if the user only wants to read or inspect skillpack without performing an action — prefer reading docs directly.
- Do not use this tool for tasks outside the Rust tooling it was built for.
Installation
Ensure skillpack is installed and available on PATH before invoking the examples below.
Invocation
The exact command an agent should run to use this tool:
skillpack init
Run skillpack --help to discover the available flags. Documented flags (verified by skillpack verify):
--non-interactive--verbose--debug--log-level--log-format-h--help-V--version
Subcommands
This CLI uses subcommands. Each one has its own flags (verified by skillpack verify):
init— flags:--root,--non-interactive,--author,--invocation,--import,--accept-warnings,--auto,--license,--trigger,--description,--verbose,--debug,--log-level,--target,--force,--dry-run,--log-format,--template-dir,--formatverify— flags:--root,--format,--fix,--min-score,--watch,--template-dir,--verbose,--debug,--log-level,--log-formatdoctor— flags:--root,--format,--verbose,--debug,--log-level,--log-formatupdate— flags:--root,--target,--force,--template-dir,--format,--verbose,--debug,--log-level,--log-formatdiff— flags:--root,--target,--force,--template-dir,--format,--verbose,--debug,--log-level,--log-formatadd— flags:--non-interactive,--root,--description,--trigger,--author,--invocation,--import,--license,--target,--force,--verbose,--debug,--log-level,--template-dir,--format,--log-formatremove— flags:--root,--target,--force,--template-dir,--format,--verbose,--debug,--log-level,--log-formatcompletions— flags:--verbose,--debug,--log-level,--log-formatconfig— flags:--root,--validate,--verbose,--debug,--log-level,--log-format
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.
- yesterday First seen · 66 lines · 803 tokens per session scan A c43a67e5addb
skillpack CLAUDE.md is an instructions file published in the GitHub repository nordicnode/skillpack (2 stars, last pushed 4d ago), licensed MIT. It adds 803 tokens to every session, about $0.0040 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to skillpack copilot-instructions.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
mirage CLAUDE.md
Instructions for strukto-ai/mirage, covering claude.md, repo layout, typescript packages, python/typescript parity and module layout.
mcp-steroid CLAUDE.md
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.
TakoVM CLAUDE.md
Instructions for Tako-Research/TakoVM, covering tako vm, why gvisor?, architecture, key concepts and build & test.
kinocut copilot-instructions.md
Copilot instructions for KyaniteLabs/kinocut: Read the nearest AGENTS.md for repository rules. For Kinocut workflows, load skills/kinocut/SKILL.md; it is the canonical public skill. Keep this adapter limited to host-specific discovery and do not duplicate policy here.
akm AGENTS.md
Instructions for itlackey/akm, covering akm repo notes, workflow, architecture, tests and test-isolation harness.
trustabl GEMINI.md
Instructions for trustabl/trustabl, a project described as: Fix agent reliability issues across Claude, OpenAI, Google ADK, MCP, LangChain, CrewAI, AutoGen, Pydantic AI, and Vercel AI.