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/sonofmagic/skills/agents-mdgit clone --depth 1 https://github.com/sonofmagic/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 | $0.01041 | $0.01041 |
| Opus 5 | $0.00521 | $0.00521 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This pnpm + Turbo monorepo keeps template sources under templates/ (cli, client, server, vitepress, tsup, tsdown, unbuild, vue-lib) and reusable tooling under packages/ (e.g., monorepo, create-icebreaker). Shared TypeScript and build settings live in root configs such as turbo.json, tsconfig.json, and eslint.config.js. Tests sit alongside their targets in test/*.test.ts, and each app owns its public assets (public/, worker/) to keep deployments self-contained.
Build, Test, and Development Commands
pnpm install— set up workspaces; ensure Node 20+ as defined inpackage.json.pnpm dev— runturbo run dev --parallelfor all apps that expose adevscript.pnpm build— executeturbo run buildto build every workspace with caching.pnpm test/pnpm test:dev— run Vitest suites once or in watch mode across packages.pnpm lint— invoketurbo run lintto apply ESLint/Stylelint policies repo-wide.pnpm script:sync&pnpm script:clean— use the monorepo helper to align dependency versions or clear generated artifacts.
Coding Style & Naming Conventions
Follow the root .editorconfig: two-space indentation, LF line endings, UTF-8. Prefer TypeScript (.ts/.tsx) and Vue SFCs; name files with kebab-case (user-table.vue) and exported symbols with PascalCase for components or camelCase for utilities. ESLint (@icebreakers/eslint-config) and Stylelint enforce formatting; run pnpm lint before committing, and rely on Husky + lint-staged to auto-fix staged files. Any style-related code changes (CSS, SCSS, Less, Vue style blocks, and similar files) must pass Stylelint checks before commit. All changed code must pass ESLint checks before commit.
lint-staged.config.js must include Stylelint checks for staged style files so style validation also runs during pre-commit.
When a single code file exceeds 300 lines, treat it as a refactor signal and split it into smaller modules.
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 · 51 lines · 1,041 tokens per session scan A c228b7c4a15f
skills AGENTS.md is an instructions file published in the GitHub repository sonofmagic/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 1,041 tokens to every session, about $0.0052 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
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.