Borrowing it
Nothing to install: this file belongs to midego1/claude-orchestrate. 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/midego1/claude-orchestrate/main/CLAUDE.mdgit clone --depth 1 https://github.com/midego1/claude-orchestrateWrote 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/midego1/claude-orchestrate/claude-md)<a href="https://agentmods.dev/instructions/midego1/claude-orchestrate/claude-md"><img src="https://agentmods.dev/badge/instructions/midego1/claude-orchestrate/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/midego1/claude-orchestrate/claude-md"><img src="https://agentmods.dev/badge/instructions/midego1/claude-orchestrate/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 | $0.00918 | $0.00918 |
| Opus 5 | $0.00459 | $0.00459 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
claude-orchestrate 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 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-orchestrate: contributor rules
This repo is a Claude Code plugin: prose that agents follow (skills/orchestrate/, agents/, templates/), a CLI they call (bin/orchestrate), hooks (hooks/hooks.json, scripts/hooks/), and schemas. The prose is the protocol; the CLI is where the protocol is enforced.
Rules of the repo
- Enforce, do not exhort. A rule an agent keeps forgetting becomes a CLI command or a hook, not a louder sentence. Every "must" in SKILL.md should have a command that refuses when it is broken (cap, lease epoch, run artifact, stale checkpoint). Field evidence: prose-only rules get summarised away; CLI-enforced ones hold.
- Never weaken a rule. The maintenance note at the end of SKILL.md is binding. Anecdotes and rationale move to
skills/orchestrate/REFERENCE.md; thresholds, must/never statements and procedure steps stay in SKILL.md, DIRECT-MODE.md, foreman.md or the templates at their current strictness. A rewrite is checked rule by rule, not word by word. - Word guidance, soft targets with a hard ceiling. SKILL.md ≈ 4,500 words (ceiling 5,200),
agents/foreman.md≈ 3,000 (3,400), DIRECT-MODE.md ≈ 1,200 (1,400), verifiers ≈ 450. These files load into the most expensive context on every run. Above the ceiling, move content to REFERENCE.md or into the CLI; never trim wording to hit a number. - Harness claims need evidence. Any sentence about Claude Code behaviour (env vars, hook fields, fork mode, tool availability) needs a verbatim docs quote or a live probe in this session. Known trap:
CLAUDE_CODE_DISABLE_FORK_MODEdoes not exist; fork mode isCLAUDE_CODE_FORK_SUBAGENT=0, andCLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1is the deterministic foreground switch. Keeprun_in_background: falseon dispatches; the foreman's Agent probe decides the mode. - CLI constraints.
bin/orchestrateis bash 3.2 (macOS default) plus python3 stdlib; no jq, no flock (use themkdirlock), no bash 4 features. Every mutating subcommand runs under the archive lock and writes the checkpoint atomically after schema validation. Exit codes: 0 ok, 1 error, 2 refused by policy, 3 gate or merge failure. - Tests before commit.
ORCH_TEST_TMP=<tmp> bash tests/cli.shandHOME=<tmp> bash tests/hooks.shmust be green; a new subcommand or hook behaviour ships with checks.bash -nevery shell file,python3 -m json.toolevery JSON. - Placeholders are an interface.
templates/*.mdplaceholder names (<absolute worktree path>,<baselineSha>,<diffRange>, …) are filled byorchestrate contract new/contract verify; renaming one is a CLI change. - Plugin root convention. Agents locate the CLI with
ls -d ~/.claude/plugins/cache/claude-orchestrate/orchestrate/*/ | sort -V | tail -1(plugin install) or the repo checkout;${CLAUDE_PLUGIN_ROOT}is a hook placeholder only.
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 · 25 lines · 918 tokens per session scan A 2f24d31296af
claude-orchestrate CLAUDE.md is an instructions file published in the GitHub repository midego1/claude-orchestrate (7 stars, last pushed 2d ago), licensed MIT. It adds 918 tokens to every session, about $0.0046 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 2026-09-11.
Other instructions, from other repositories
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.
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.
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.
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).
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).