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/chronoaiproject/ornn/claude-mdgit clone --depth 1 https://github.com/ChronoAIProject/OrnnWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/chronoaiproject/ornn/claude-md)<a href="https://agentmods.dev/instructions/chronoaiproject/ornn/claude-md"><img src="https://agentmods.dev/badge/instructions/chronoaiproject/ornn/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.06198 | $0.06198 |
| Opus 5 | $0.03099 | $0.03099 |
| Sonnet 5 | $0.01240 | $0.01240 |
| Haiku 4.5 | $0.00620 | $0.00620 |
Grade A, and why
Ornn 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 5d 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 — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — chrono-ornn
Product Positioning
Ornn is an agent-facing skill-lifecycle API, not a human marketplace.
The primary customer is the AI agent developer / agentic-system builder. Agents call Ornn directly — over HTTP or MCP — to manage their own skill lifecycle: search → pull → install → execute → build → upload → share. Closest analog: npm registry + npm CLI fused, model-agnostic (works for Claude / GPT / Gemini / custom — not locked to one model runtime).
Implications when proposing or building features:
- Lead with the agent-API contract (REST / MCP ergonomics, stable schemas, model-agnostic guarantees) before any human-UX angle.
ornn-webis a secondary surface for skill owners and platform admins — it is not the primary product. UI features that don't translate into agent-API value are deprioritized.- Avoid feature framing that drifts toward "another skill marketplace" (social ranking, browse-style discovery, recommendation feeds, leaderboards) unless we deliberately decide to. When a feature looks marketplace-shaped, surface that tension before building.
Tech Stack
TypeScript, Bun workspace monorepo
- Runtime: Bun (backend + tests), Vite (frontend dev/build)
- Backend: Hono
- Frontend: React 19, Zustand, TanStack Query, Tailwind CSS 4, Framer Motion, React Router 7
- Database: MongoDB 7
- Validation: Zod
- Logging: Pino
- Testing: Bun test (backend); Vitest + Testing Library + jsdom (frontend + TS SDK); pytest + respx (Python SDK). All run in CI — bun packages via
bun run test, Python via a dedicatedpython-sdk-testjob.
Packages:
| Package | Path | Description |
|---|---|---|
ornn-api |
ornn-api/ |
Backend API (Bun + Hono + MongoDB) |
ornn-web |
ornn-web/ |
React SPA (Vite + React 19 + Zustand + TanStack Query) |
@chronoai/ornn-sdk |
sdk/typescript/ |
TypeScript client for /api/v1/* |
ornn-sdk (Python) |
sdk/python/ |
Python client for /api/v1/* (httpx) — separate release cadence |
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.
- 5d ago First seen · 423 lines · 6,198 tokens per session scan A ae0a1a45d4a2
Ornn CLAUDE.md is an instructions file published in the GitHub repository ChronoAIProject/Ornn (20 stars, last pushed 5d ago), licensed Apache-2.0. It adds 6,198 tokens to every session, about $0.0310 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
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
nutrition-mcp CLAUDE.md
Claude Code instructions for akutishevsky/nutrition-mcp, covering claude.md, project overview, deploying, publishing to the registry and commands.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
get-fable AGENTS.md
AGENTS.md instructions for imMamdouhaboammar/get-fable, covering get-fable repository instructions, purpose, working contract, canonical lifecycle packs and runtime semantics.
agenttool CLAUDE.md
Claude Code instructions for cambridgetcg/agenttool, covering agenttool, where things are, the five load-bearing flows, custody axis (the most-confused concept) and kingdom engine.
zangia-mcp-ai CLAUDE.md
Instructions for enkhbold470/zangia-mcp-ai, covering claude.md — zangia ai & mcp server (typescript), quick commands, mcp stdio (claude code / codex / cursor / any mcp host), local clone and landing page + api (proxy: vite :3000 → hono :4000 /api).