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/n-n-code/n-n-code-skills/agents-mdgit clone --depth 1 https://github.com/n-n-code/n-n-code-skillsWhat 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 | $0.00757 | $0.00757 |
| Opus 5 | $0.00378 | $0.00378 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
n-n-code-skills AGENTS.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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repo Purpose
This repository stores reusable agent skills. Most work should be limited to
root documentation, .agents/skills/, and the validation scripts
under scripts/.
Structure
- Skills live in
.agents/skills/<skill-name>/ - Each skill must include
SKILL.md SKILL.mdfrontmatter must contain exactlynameanddescription; the declared name must match the skill folder- Supporting files such as
references/,scripts/, andassets/are allowed when they directly serve the skill README.mdis the published skill inventory and routing guide; keep it aligned whenever a skill is added, removed, or retitled
Skill Taxonomy
README.md is the source of truth for the current skill inventory, family
routing, and composition examples. Do not duplicate that catalog here.
- Start with one principle skill for language- or discipline-specific work, add matching domain or project overlays, and add an orthogonal workflow skill only when the task needs that mode
- A baseline overlay is the routine default; a canonical overlay is the stronger option for harder work in the same domain and should preserve the baseline's core expectations
- A companion overlay adds an optional workflow without replacing its baseline
- A process overlay governs workflow or enforcement; a template overlay is a pattern for repo-local adaptation
- A system skill builds or installs a repo-owned system instead of guiding ordinary execution
- Keep these relationships explicit when adding or revising skills so adjacent skills do not drift into overlapping jobs
Working Rules
- Preserve the existing folder-based layout unless the task explicitly requires a structural change
- Keep instructions concise, specific, and grounded in files that actually exist
- Use the repo's role vocabulary consistently when naming or describing skills
- Update only the skill folder and root docs relevant to the task
- When adding or changing a skill, keep its trigger boundaries distinct from
neighboring skills and update the relevant
README.mdfamily and defaults - Treat
README.mdandAGENTS.mdas durable repo docs; do not add process or automation claims that the repository does not implement - Prefer small, targeted edits over broad repo rewrites
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 · 94 lines · 757 tokens per session scan A 0591e7d5b540
n-n-code-skills AGENTS.md is an instructions file published in the GitHub repository n-n-code/n-n-code-skills (4 stars, last pushed 4d ago), licensed MIT. It adds 757 tokens to every session, about $0.0038 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
claude-code-karma CLAUDE.md
Instructions for JayantDevkar/claude-code-karma, covering claude.md, project overview, quick start, clone (no submodule init needed — this is a monorepo) and start api (terminal 1).
gangsta GEMINI.md
Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.
GenerateAgents.md AGENTS.md
Instructions for originalankur/GenerateAgents.md, covering agents.md — autogenerateagentsmd.md, project overview, tech stack, architecture and code style.
bundl-cli CLAUDE.md
Instructions for Bundl-AI/bundl-cli, covering agent operating instructions, role, hard constraints and corpus info.
teamclaw AGENTS.md
Instructions for teamclawai/teamclaw, covering teamclaw - agent development guidelines, project overview, quick start for contributors, prerequisites and setup.
symbi-gemini-cli GEMINI.md
Instructions for ThirdKeyAI/symbi-gemini-cli, covering symbiont governance context, key concepts, available mcp tools (via symbi server), file conventions and dual-mode operation.