Borrowing it
Nothing to install: this file belongs to moonrunnerkc/swarm-orchestrator. 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/moonrunnerkc/swarm-orchestrator/v13-main/CLAUDE.mdgit clone --depth 1 https://github.com/moonrunnerkc/swarm-orchestratorWrote 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/moonrunnerkc/swarm-orchestrator/claude-md)<a href="https://agentmods.dev/instructions/moonrunnerkc/swarm-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/moonrunnerkc/swarm-orchestrator/claude-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/moonrunnerkc/swarm-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/moonrunnerkc/swarm-orchestrator/claude-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 | $0.03059 | $0.03059 |
| Opus 5.5 | $0.01224 | $0.01224 |
| Sonnet 5.5 | $0.00612 | $0.00612 |
| Haiku 4.5 | $0.00306 | $0.00306 |
Grade C, and why
swarm-orchestrator CLAUDE.md scanned grade C with 1 finding 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 14d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Generated from docs/engineering-policy.md by scripts/sync-agent-instructions.mjs. --> This is a copy
100% identical to swarm-orchestrator AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering policy
Swarm Orchestrator completes bounded engineering goals through one reusable worker loop, controlled integration and repair, and independent checks of the final tree. Every completion claim must resolve to harness-captured evidence. Local model selection is measured, never guessed.
This is the canonical policy. Run node scripts/sync-agent-instructions.mjs --write after editing
it; both agent filenames are generated and the drift check compares their entire contents.
Read docs/build-guide.md before structural work. Security and evidence changes must also consult
the corresponding detailed invariant and incident rationale preserved byte-for-byte through the offline archive documented in
docs/history/agent-policy-2026-09-13.md, plus the applicable regression tests. Those detailed
mechanics remain binding; this concise policy does not waive them. The deliberately approved
product revisions and their reasons are in docs/adr/0009-adaptive-goal-controller.md.
Commands and completion
npm run typecheck: strict TypeScript, no emit.npm run lint: Biome checks.npm run formatwrites formatting.npm test: the complete Vitest suite.npm run checks: corpus history, policy drift, documentation paths, weight and required headroom, packed derived evidence, cited bundles and CI verdicts.npm run gates: checks, typecheck, lint and the full test suite, in sequence. This defines green.npm run build,npm run check:packaged,npm run fuzz:build: release and CI checks.npm run dev: CLI from source in a scratch workspace.
Run npm run gates before claiming a task complete. Paste its real output, including failures
and skips. Bind evidence to the tested commit and diff. Do not combine separate runs into an
invented passing total. The corpus requires full history and v12-final; use the history check.
Declare intended files before edits. Record explicit amendments for additional files. Preserve unrelated work. Completion also requires meaningful tests for new behavior, no introduced placeholder markers, the smallest sufficient diff, and all applicable CI/package checks. State any unmet requirement precisely. Local commits, pushed code, passing CI and published packages are separate facts.
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.
- 14d ago Changed · +12 tokens per session 092588658ce1
- 21d ago Changed · +1 lines · +75 tokens per session 6932254bd8d0
- 1mo ago Changed · +8 tokens per session 50275732c4fc
- 1mo ago Changed · +2 lines · +35 tokens per session 0a534f897b20
- 1mo ago Changed · +28 lines · -2,377 tokens per session scan E → C 66c5445fe738
- 1mo ago Changed · +2 lines · +40 tokens per session 43bdb8bbf3b4
- 1mo ago Changed · +1 lines · +356 tokens per session 21000c6b3c9d
- 1mo ago Changed · +2 lines · +320 tokens per session 2da03f7b0d80
- 2mo ago First seen · 68 lines · 4,590 tokens per session scan E 9742d1c0cc28
swarm-orchestrator CLAUDE.md is an instructions file published in the GitHub repository moonrunnerkc/swarm-orchestrator (111 stars, last pushed today), licensed ISC. It adds 3,059 tokens to every session, about $0.0122 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). It is 100% identical to swarm-orchestrator AGENTS.md, differing in 0 lines, and is treated as a copy.
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.