orchestrator: Instructions file for Claude Code

CLAUDE.md

orchestrator CLAUDE.md is an instructions file for Claude Code from c9r-io/orchestrator. It costs 690 tokens per session, scanned C, original, MIT.

Project instructions for the Orchestrator codebase covering forbidden operations, safe database handling, and how to start and stop its background service.

In plain words
What is it for?
Use it when working on the Orchestrator daemon, runtime database, test probes, service lifecycle, or QA procedures.
Why use it?
It prevents agents from deleting runtime data or using unsafe service-control scripts when testing or changing the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is c9r-io/orchestrator's own configuration. It tells Claude Code how to work on orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to c9r-io/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.

Copy the file
curl -O https://raw.githubusercontent.com/c9r-io/orchestrator/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/c9r-io/orchestrator

Made for: Claude Code.

Wrote 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.

agentmods badge for orchestrator CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/c9r-io/orchestrator/claude-md.svg)](https://agentmods.dev/instructions/c9r-io/orchestrator/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/c9r-io/orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/c9r-io/orchestrator/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 690 This file is loaded in full into every session.
When invoked 690 The same file — it is already loaded in full.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00690 $0.00690
Opus 5 $0.00345 $0.00345
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 7d ago against content hash 0836ba32f433, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

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 7d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

`rm -rf` proceeds to delete the data directory out from under a live writer. Measured on
CLAUDE.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Forbidden Operations

Never delete the runtime database

Do NOT run rm -f ~/.orchestratord/agent_orchestrator.db or any command that deletes or truncates the runtime database (default location: ~/.orchestratord/agent_orchestrator.db, overridable via ORCHESTRATORD_DATA_DIR).

If you encounter a scenario that seems to require deleting the database, it indicates a bug — the system should provide proper isolation (e.g., project-scoped operations) without destructive resets.

  • During QA testing: Create a ticket under docs/ticket/ documenting the scenario and the missing isolation mechanism. Adjust the QA doc to work without database deletion, noting the known issue.
  • During interactive work: Inform the user that the operation would require deleting the database, explain why this suggests a bug, and let the user decide.

Starting a daemon

Never hand-roll the daemon lifecycle, including in throwaway scripts

If a script you write starts orchestratord, it must take its start and stop from scripts/lib/gate_daemon.sh. That applies especially to one-off probes — a script under /tmp, under ~/.claude/jobs/, or anywhere else outside this repository. Those are the scripts that leak, because they are the ones nobody reviews and no gate can see.

. /Users/…/orchestrator/scripts/lib/gate_daemon.sh   # sourceable by absolute path,
                                                     # installs no traps
gate_daemon_wait_ready "$ORCH"          # ready means "can serve", not "answers"
gate_daemon_stop "$DAEMON_PID"          # SIGTERM → 10s → named SIGKILL → 5s → named failure

Do not write ( cd "$X" && "$ORCHD" … & echo $! > pidfile ). Under bash the & backgrounds the whole cd && … list and the final command is not exec'd, so $! is the wrapper shell, not the daemon. pkill -F then kills the wrapper and exits 0 — reporting success — while the daemon is reparented to init and survives; a cleanup's rm -rf proceeds to delete the data directory out from under a live writer. Measured on 2026-08-12: two daemons leaked this way ran for 22 hours holding unlinked inodes, and the run that started them reported all checks passed. FR-160 removed this shape from 25 gates and scripts/qa/test-qa-gate-surface.sh check 16 keeps it out of scripts/** — but that gate cannot see a file outside the repository, which is why this rule is here and not only there. See DD-174.

Read the full file on GitHub · 45 lines

Changes

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.

  1. 7d ago First seen · 45 lines · 690 tokens per session scan C 0836ba32f433

Subscribe to this mod's changes

orchestrator CLAUDE.md is an instructions file published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 5d ago), licensed MIT. It adds 690 tokens to every session, about $0.0034 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens