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/supabase/agent-skills/agents-mdgit clone --depth 1 https://github.com/supabase/agent-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 | $0.01630 | $0.01630 |
| Opus 5 | $0.00815 | $0.00815 |
| Sonnet 5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
agent-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 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.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working with this repository.
Note:
CLAUDE.mdis a symlink to this file.
Prerequisites
This project uses pnpm for dependency management and task execution. Use the
Node.js version declared in .node-version,
then install dependencies with pnpm install.
Repository Structure
skills/
{skill-name}/
SKILL.md
references/ (optional)
Commands
Run tasks with pnpm.
pnpm install # Install dependencies
pnpm test # Run tests
Before completing any task, run pnpm test to ensure CI passes.
Releases
This repository uses Release Please on main.
- Merge conventional commits using
feat:andfix:prefixes so Release Please can open or update the release PR. - Release Please opens one combined release PR that bumps the root version and the version of any skill whose files were touched. Unrelated skills are not bumped. Do not bump skill versions manually.
- When the PR is merged, GitHub Actions creates one GitHub release (tag
v{version}) with all skill tarballs andindex.json. Per-skill packages useskip-github-release: true— no separate GitHub release is created for them, but theirmetadata.versioninSKILL.mdand theirCHANGELOG.mdare committed as part of the release PR.
If you change shipped skill contents under skills/, make sure the change is represented with an appropriate conventional commit so it is included in the next release.
Creating a New Skill
Skills follow the Agent Skills Open Standard.
- Create directory:
mkdir -p skills/{skill-name}/references - Create
SKILL.mdfollowing the format below - Add
references/_sections.mddefining sections - Add reference files:
{prefix}-{reference-name}.md - Register the skill in
release-please-config.jsonas a new package and seed its version in.release-please-manifest.json:// release-please-config.json — add under "packages": "skills/{skill-name}": { "release-type": "simple", "skip-github-release": true, "changelog-path": "skills/{skill-name}/CHANGELOG.md", "extra-files": [ { "type": "generic", "path": "skills/{skill-name}/SKILL.md", "expressions": ["version: \"([0-9]+\\.[0-9]+\\.[0-9]+)\""] } ] }// .release-please-manifest.json — add: "skills/{skill-name}": "0.0.0" - Run
pnpm test - Commit the new skill with a
feat:prefix so Release Please bumps it from0.0.0to0.1.0on first release. Usingfix:would produce0.0.1instead.
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 · 228 lines · 1,630 tokens per session scan A b2810943ae05
agent-skills AGENTS.md is an instructions file published in the GitHub repository supabase/agent-skills (2,562 stars, last pushed 20d ago), licensed MIT. It adds 1,630 tokens to every session, about $0.0081 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
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
Instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
people-memory-mcp AGENTS.md
AGENTS.md instructions for michelgrolet/people-memory-mcp, a project described as: A private people graph that gives your AI agent durable memory.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.