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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/del-taiseiozaki/claude-code-orchestra/agents-md"><img src="https://agentmods.dev/badge/instructions/del-taiseiozaki/claude-code-orchestra/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/del-taiseiozaki/claude-code-orchestra/agents-md"><img src="https://agentmods.dev/badge/instructions/del-taiseiozaki/claude-code-orchestra/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 | $0.04654 | $0.04654 |
| Opus 5.5 | $0.01862 | $0.01862 |
| Sonnet 5.5 | $0.00931 | $0.00931 |
| Haiku 4.5 | $0.00465 | $0.00465 |
Grade A, and why
claude-code-orchestra 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Orchestra — Root Agent Contract
Every CLI agent loads this file automatically from the repository root, and
Claude Code reads it directly because no CLAUDE.md sits beside it. It is
the single root contract for both roles. The main-agent sections come first --
mission, routing policy, skill catalog, quality gates -- followed by the
contract for CLI executors such as Codex, Antigravity, Grok, and opencode:
response structure, handoff rules, how to call another CLI as a subagent, and
the completion-verification guardrails. Those cross-CLI invocation rules and
completion guardrails bind the main agent as a caller too. Follow it as
written -- nothing here depends on opening another file first.
Do not add a CLAUDE.md, a .claude/CLAUDE.md, or a CLAUDE.local.md at or
above the repository root. Claude Code reads the first one it finds instead of
this file and silently stops loading AGENTS.md -- no warning, no error, just a
main agent operating without its contract.
Where to go next, only as the task needs it:
| You are | Read |
|---|---|
| Any agent needing tier details | .claude/rules/tiers.md |
| Any agent needing shared standards | .claude/rules/ -- coding, testing, security, delegation |
| Codex | .codex/AGENTS.md -- model, sandbox, enabled skills |
| Antigravity | .agents/AGENTS.md -- headless behaviour and limits |
.claude/ contains the canonical detailed rules and capabilities. Claude Code
is the default main agent; the active main is recorded in
.claude/STATE.md.
.claude/docs/INDEX.md is the full registry, and
.claude/docs/change_main.md changes the main
agent -- read it only when the user asks to change it.
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.
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 · +154 lines · +1,854 tokens per session d9b2b225ab8c
- 2mo ago Changed · +83 lines · +1,228 tokens per session c4ec9068135d
- 2mo ago First seen · 140 lines · 1,572 tokens per session scan A eacef046a85a
claude-code-orchestra AGENTS.md is an instructions file published in the GitHub repository DeL-TaiseiOzaki/claude-code-orchestra (198 stars, last pushed 5d ago), licensed MIT. It adds 4,654 tokens to every session, about $0.0186 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 2026-08-30.
claude-code-orchestra AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-code-orchestra AGENTS.mdDeL-TaiseiOzaki/claude-code-orchestra | Instructions file | 198 | 5d ago | MIT | A | 4,654 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |