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/nornscode/norns/agents-mdgit clone --depth 1 https://github.com/nornscode/nornsWhat 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 | $0.01274 | $0.01274 |
| Opus 5 | $0.00637 | $0.00637 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
norns 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- norns CLAUDE.md — 100% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Norns
Project Overview
Open-source (MIT) durable agent runtime on BEAM. The orchestrator is a pure state machine — it dispatches tasks to workers and persists events, but never executes LLM calls or tools directly.
Tech Stack
- Language: Elixir on BEAM/OTP
- Web Framework: Phoenix (REST + Channels + LiveView)
- Database: PostgreSQL via Ecto
- Background Jobs: Oban
- Dev Environment: Docker Compose (all mix commands run in containers)
- License: MIT
Running Commands
docker compose run --rm -e POSTGRES_HOST=db app mix test
docker compose run --rm -e POSTGRES_HOST=db app mix ecto.migrate
docker compose run --rm -e MIX_ENV=test -e POSTGRES_HOST=db app mix test
Project Structure
lib/norns/
tenants/ — Tenant schema + context (multi-tenancy)
agents/ — Agent, AgentDef, Process (state machine), Registry
conversations/ — Conversation schema + context (persistent chat history)
runs/ — Run + RunEvent schemas, Runs context (event log)
runtime/ — Event contracts, error taxonomy, retry policy
gards/ — Gard + GardPort schemas; Gards context (worker affinity)
hooks/ — Hook schema, Signature verification; Hooks context (webhook ingress)
triggers/ — Trigger schema + context (cron schedules that start runs)
workers/ — WorkerRegistry, TaskQueue, ResumeAgents, TriggerScheduler
llm.ex — LLM dispatcher (used by workers via Fake in tests)
llm/ — Behaviour, Anthropic adapter, Format (neutral ↔ Anthropic), Fake
tools/ — Behaviour, Tool struct, Executor, Registry, Idempotency
lib/norns_web/
endpoint.ex — Phoenix endpoint (REST + WebSocket + LiveView)
router.ex — API routes + LiveView routes
plugs/ — Auth (API bearer token), SessionAuth (browser cookies)
controllers/ — AgentController, RunController, ConversationController
channels/ — AgentSocket/Channel (streaming), WorkerSocket/Channel (task dispatch)
live/ — AgentsLive, AgentLive, RunLive, ToolsLive, SetupLive
components/ — Layouts (root + app)
json.ex — Serialization helpers
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 · 102 lines · 1,274 tokens per session scan A 633dea283237
norns AGENTS.md is an instructions file published in the GitHub repository nornscode/norns (11 stars, last pushed 16d ago), licensed MIT. It adds 1,274 tokens to every session, about $0.0064 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
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).
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.
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.