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/yonatangross/orchestkit/agents-mdgit clone --depth 1 https://github.com/yonatangross/orchestkitWhat 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 | $0.00934 | $0.00934 |
| Opus 5 | $0.00467 | $0.00467 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
orchestkit 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 3d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in the OrchestKit repository. This is the
vendor-neutral companion to CLAUDE.md; where both exist, they say the same thing.
OrchestKit is a plugin for Claude Code (Anthropic's agentic CLI). It packages reusable
skills, specialist agents, and lifecycle hooks. It is source-built: you edit src/ and a
build step assembles the installable plugins/ tree. It is not a hosted service and has no
runtime backend.
The one rule that prevents most broken PRs
Edit src/ and manifests/. Never edit plugins/ by hand — it is generated.
src/ ← EDIT HERE
skills/<name>/SKILL.md # skills (YAML frontmatter + Markdown body, <500 lines)
agents/<name>.md # agents (frontmatter: name, description, model, tools, skills)
hooks/src/<category>/*.ts # TypeScript lifecycle hooks
manifests/ ← EDIT HERE (plugin definitions)
plugins/ ← GENERATED by `npm run build` — do not hand-edit
After any src/ change, run npm run build, then stage the resulting plugins/ diff
together with your src/ change in the same commit. A plugins/ diff after a build is
expected, not noise. If plugins/ comes out empty, the build was interrupted — run it again.
Build and verify
npm run build # assemble plugins/ from src/ — required after editing src/
npm test # full suite (lint + unit + security + integration + e2e)
npm test --quick # skip integration/e2e/performance
npm run test:skills # skill structure validation
npm run test:agents # agent frontmatter validation
npm run test:security # security tests — MUST pass, gates push
npm run typecheck # TypeScript check (run if hooks changed)
Before opening a PR: npm test and npm run test:security must pass, and git diff should
show real changes (not no-ops left over from a previous session).
Adding a component
- Skill — create
src/skills/<name>/SKILL.mdwith frontmatter (name,description,tags,user-invocable,complexity); body stays under 500 lines. Add it tomanifests/ork.json, thennpm run build. Seesrc/skills/CONTRIBUTING-SKILLS.md. - Agent — create
src/agents/<name>.mdwith the required frontmatter, add to the manifest, rebuild. - Hook — create
src/hooks/src/<category>/<name>.tsand register it in bothsrc/hooks/hooks.jsonand the entries mapsrc/hooks/src/entries/<event>.ts. One without the other is a silently-dead hook. Rebuild withcd src/hooks && npm run build.
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.
- 3d ago First seen · 74 lines · 934 tokens per session scan A 078615c33daa
orchestkit AGENTS.md is an instructions file published in the GitHub repository yonatangross/orchestkit (224 stars, last pushed 3d ago), licensed MIT. It adds 934 tokens to every session, about $0.0047 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
dawnai AGENTS.md
Instructions for cacheplane/dawnai, covering agents.md, what this is (and isn't), workspace map, definition of done and conventions.
eCan.ai CLAUDE.md
Instructions for scszcoder/eCan.ai, covering claude.md, 0. 废弃目录说明, 1. think before coding, 2. simplicity first and 3. surgical changes.
claude-code-sub-agent-collective CLAUDE.md
Instructions for vanzan01/claude-code-sub-agent-collective, covering claude.md, project overview, critical repository information, architecture and core system.
software-factory AGENTS.md
Instructions for Kripu77/software-factory, covering software factory, before you explore, skills, shipping and lanes.
browser-operator-core CLAUDE.md
Instructions for BrowserOperator/browser-operator-core, covering claude.md, project overview, build & development commands, initial setup and build.
AI-System-Design-Consultant CLAUDE.md
Instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.