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/untrivial-ai/agent-orchestrator/agents-mdgit clone --depth 1 https://github.com/Untrivial-ai/agent-orchestratorWhat 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 | $0.02188 | $0.02188 |
| Opus 5 | $0.01094 | $0.01094 |
| Sonnet 5 | $0.00438 | $0.00438 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade A, and why
agent-orchestrator 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Operational guidance for coding agents working in this repository. Keep changes small, match the current rewrite architecture, and prefer the documented daemon/API boundaries over behavior from the old TypeScript implementation.
Repo layout
backend/— Go rewrite of Agent Orchestrator: CobraaoCLI, loopback HTTP daemon, services, SQLite storage, lifecycle/reaper, runtime/workspace/agent/tracker adapters, terminal mux, and tests.frontend/— Electron + React supervisor wired to the daemon via the generated typed client. Treat it as a thin supervisor/UI surface; do not move daemon logic into it.docs/— current architecture/status notes. Start here before changing lifecycle, CLI, agents, storage, or daemon behavior.test/— external smoke/e2e assets, including the CLI fresh-install container check..github/workflows/— CI definitions. Mirror these commands locally when possible.
Commands
From the repo root unless noted:
npm run lint # backend go test ./... + golangci-lint v2.12.2
npm run frontend:typecheck # frontend TypeScript check
npm run sqlc # regenerate backend/internal/storage/sqlite/gen from queries/schema
npm run api # regenerate OpenAPI spec + frontend TS types (see API contract changes below)
npx @redwoodjs/agent-ci run --all # local workflow validation; requires Docker socket
Backend-specific checks:
cd backend
go build ./...
go test ./...
go test -race ./...
go vet ./...
go run ./cmd/ao start
Frontend-specific checks:
cd frontend
npm run typecheck
npm run build
When showing or demoing frontend changes, run ao preview [url] from inside the session so the change renders in the desktop browser panel (the inspector rail's Browser tab); do not just describe it.
Where to look first
README.md— current run/config/test quickstart.docs/README.md— docs index.docs/architecture.md— backend mental model, package layout, lifecycle/session/service boundaries, and load-bearing rules.docs/STATUS.md— what is shipped onmaintoday and what is still in flight.docs/cli/README.md— intended CLI shape: thin Cobra client over daemon HTTP, never direct storage/runtime access.CLAUDE.md— compatibility pointer for Claude Code; it directs agents back toAGENTS.md.
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 · 138 lines · 2,188 tokens per session scan A 7d3488618c5a
agent-orchestrator AGENTS.md is an instructions file published in the GitHub repository Untrivial-ai/agent-orchestrator (10,763 stars, last pushed today), licensed Apache-2.0. It adds 2,188 tokens to every session, about $0.0109 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
bernstein AGENTS.md
AGENTS.md instructions for sipyourdrink-ltd/bernstein, covering bernstein - agents.md, module map, directory context files, build & test and setup.
bernstein copilot-instructions.md
Copilot instructions for sipyourdrink-ltd/bernstein, covering copilot instructions, architecture, key constraints, before committing and git rules.
cezar AGENTS.md
Instructions for open-mercato/cezar, covering agents.md — working in this repository, zero config, changing a mechanism that already works, the http api and repository layout.
crewplane AGENTS.md
Instructions for crewplaneai/crewplane, covering agents.md, repo facts, read first, repo map and project heuristics.
crewplane copilot-instructions.md
Instructions for crewplaneai/crewplane: Use AGENTS.md as the canonical repository instructions.
crewplane CLAUDE.md
Instructions for crewplaneai/crewplane, a project described as: Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.