Borrowing it
Nothing to install: this file belongs to crossben/orchestra-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/crossben/orchestra-code/main/AGENTS.mdgit clone --depth 1 https://github.com/crossben/orchestra-codeWrote 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/crossben/orchestra-code/agents-md)<a href="https://agentmods.dev/instructions/crossben/orchestra-code/agents-md"><img src="https://agentmods.dev/badge/instructions/crossben/orchestra-code/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/crossben/orchestra-code/agents-md"><img src="https://agentmods.dev/badge/instructions/crossben/orchestra-code/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02236 | $0.02236 |
| Opus 5.5 | $0.00894 | $0.00894 |
| Sonnet 5.5 | $0.00447 | $0.00447 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
orchestra-code 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 1mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
What this repo is
Go CLI (cmd/orchestra) that orchestrates multiple AI coding agents (Claude Code, OpenCode, Mimo, etc.) through a single supervised interface. Agents run headless; human approves via diff review.
Build & verify (run these in order before pushing)
go build ./... # compile
go vet ./... # static analysis
go test ./... # all tests
gofmt -w . # format (CI enforces this)
No shortcuts. CI runs exactly these four steps against Go 1.22.
Single-focus commands
go test ./internal/scheduler/... # test one package
go vet ./internal/engine/... # vet one package
gofmt -l . # list unformatted files
Build the binary
go build -o bin/orchestra ./cmd/orchestra
./bin/orchestra --help
Binary is at bin/orchestra (gitignored).
Project structure
cmd/orchestra/— Cobra CLI (main.go + one file per subcommand: run, do, plan, dashboard, agents, etc.)internal/engine/— the core supervised loop (dispatch → validate → retry → review). Every front door (run, shell,do) drives this.internal/agent/— Agent interface + registry. This is the extension point for adding new agents.internal/router/— AI routing: classifies intent → picks agent. CLI classifier by default; optional direct-API classifier (router.classifier); history-aware agent resolution via theHistoryinterface.internal/planner/— decomposes requests into ordered steps withdepends_onfor parallelism.internal/scheduler/— bounded-concurrency DAG runner for parallel isolated tasks.internal/parallel/— shared plan → waves → isolated task logic (Graph,BaseGuard,RunStep) used bydo --paralleland the dashboard's/parallel.internal/worktree/— task isolation behind theIsolatorinterface:worktree.New(dir)picks git worktrees in a repository (branch per task, merge + conflict detection) or aCopyIsolatorin plain folders (temp copy per task, all-or-nothing merge, conflict if a touched file changed in the source).internal/validate/— build → lint → test pipeline, auto-detects toolchain, stops on first failure.internal/config/— YAML config + built-in agent defaults + toolchain auto-detection.internal/memory/— SQLite history at~/.orchestra/orchestra.db(never in the repo tree): runs, diffs, benchmarks, tokens/cost, and the per-directory agent scores the router uses.internal/update/— self-updater: checks GitHub Releases (throttled to once per 24h), verifieschecksums.txt, swaps the binary in place. Relies on the GoReleaser archive name template — see docs/RELEASING.md.internal/tui/— Bubble Tea dashboard: Chat (live run panel + file-by-file review), Changes, History, Agents, Benchmarks, Logs. One file per concern (chat, live, review, views, chrome, theme, table).internal/ui/— terminal styling (gradients, spinners, diffs). TTY-aware.internal/shell/— interactive chat REPL.internal/review/— diff display + accept/reject prompt.internal/runner/— generic process exec (stream/capture/timeout). The engine's engine.internal/gitutil/— git helpers (is-repo, is-clean, diff, restore, commit).internal/fsdiff/— git-free supervision for plain folders: directory snapshots, a Myers line-diff emitting git-style unified output, and snapshot restore. Used by the engine whenever--diris not a git repository.internal/llm/— HTTP LLM providers (Providerinterface; openai-compatible + anthropic). No new deps: stdlib net/http.internal/patch/— extracts unified diffs / whole-file blocks from model output and applies them (git apply --check dry-run first; traversal-guarded writes).
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.
- 1mo ago Changed · +5 lines · +262 tokens per session a981ed84134e
- 1mo ago First seen · 140 lines · 1,974 tokens per session scan A 212470d7a1bb
orchestra-code AGENTS.md is an instructions file published in the GitHub repository crossben/orchestra-code (4 stars, last pushed 1mo ago), licensed MIT. It adds 2,236 tokens to every session, about $0.0089 per session on Opus 5.5. 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 2026-09-26.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.