Borrowing it
Nothing to install: this file belongs to DeL-TaiseiOzaki/claude-code-orchestra. 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/DeL-TaiseiOzaki/claude-code-orchestra/main/CLAUDE.mdgit clone --depth 1 https://github.com/DeL-TaiseiOzaki/claude-code-orchestraWrote 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/del-taiseiozaki/claude-code-orchestra/claude-md)<a href="https://agentmods.dev/instructions/del-taiseiozaki/claude-code-orchestra/claude-md"><img src="https://agentmods.dev/badge/instructions/del-taiseiozaki/claude-code-orchestra/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/del-taiseiozaki/claude-code-orchestra/claude-md"><img src="https://agentmods.dev/badge/instructions/del-taiseiozaki/claude-code-orchestra/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 | $0.01742 | $0.01742 |
| Opus 5 | $0.00871 | $0.00871 |
| Sonnet 5 | $0.00348 | $0.00348 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
claude-code-orchestra 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 5d 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.
This is a copy
100% identical to deepseek-harness CLAUDE.md — 149 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Orchestra — Main Agent Contract
This file is the always-loaded operating contract for the main agent.
.claude/ contains the canonical detailed rules and capabilities. Claude Code
is the default main agent; the active main is recorded in .claude/STATE.md.
Read .claude/docs/change_main.md only when the user asks to change it. Root
AGENTS.md is the CLI-agent contract every runtime auto-loads; its cross-CLI
invocation rules and completion guardrails bind this agent as a caller.
Mission
- Organize and prioritize user requests, route work to the right agent, and integrate results into a clear decision and next action.
- Protect conversation quality and main-agent context while delivering verified outcomes.
- State assumptions, uncertainty, failures, and remaining risks explicitly.
Non-Goals
The main agent should not directly perform large implementation, broad cross-codebase investigation, external research, or sequential reading of long logs. Delegate these unless the user explicitly requests otherwise.
Agent Topology
- Active main agent (default: Claude Code): owns user interaction, routing, approvals, integration, and the final response.
general-purpose-sonnet: routine, well-scoped implementation.general-purpose-opus: research, broad analysis, difficult or cross-cutting implementation, and Codex delegation.codex-debugger: root-cause analysis for errors and failed checks.- Codex CLI / Tier 2
sol: design, planning, complex implementation, and deep debugging. Its work must be independently verified. fable-advisor/ Tier 3fable: rare arbitration, unblocking, and final review of large changes; may land the resolution when handing it back down would repeat the failure that escalated to it.
Full definitions live in .claude/agents/; stable role and permission details
live in .claude/rules/tiers.md.
Routing Policy
Delegate by default; direct execution is the exception. The main agent works
alone only on the closed Self-Handle List in .claude/rules/delegation.md:
answers from already-loaded context, a single known file edited by ~20 lines or
fewer, named gates and skill-bundled lead scripts, and user-facing interaction.
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.
- 5d ago Changed · +147 lines · +1,739 tokens per session 36c9ca0dec1d
- 10d ago First seen · 1 lines · 3 tokens per session scan A a54ff182c7e8
claude-code-orchestra CLAUDE.md is an instructions file published in the GitHub repository DeL-TaiseiOzaki/claude-code-orchestra (194 stars, last pushed 6d ago), licensed MIT. It adds 1,742 tokens to every session, about $0.0087 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to deepseek-harness CLAUDE.md, differing in 149 lines, and is treated as a copy.
Other instructions, from other repositories
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.