meta-team: Instructions file for Claude Code

CLAUDE.md

orchestrator is an instructions file for Claude Code from gertsylvest/meta-team. It costs 3,790 tokens per session, scanned A, original, MIT.

An orchestration guide for a library of reusable coding agents, skills, rules, and team definitions. It explains how to develop these resources privately and publish a selected subset publicly.

In plain words
What is it for?
Use it to bootstrap new projects from the library, add or refine resources, manage the publication manifest, and publish the approved files.
Why use it?
It keeps reusable project guidance organized and prevents unfinished or unapproved resources from being published.

Instructions file for Claude Code

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

This is gertsylvest/meta-team's own configuration. It tells Claude Code how to work on meta-team 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 meta-team configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gertsylvest/meta-team. 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/gertsylvest/meta-team/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/gertsylvest/meta-team

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gertsylvest/meta-team/claude-md/github.svg)](https://agentmods.dev/instructions/gertsylvest/meta-team/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gertsylvest/meta-team/claude-md"><img src="https://agentmods.dev/badge/instructions/gertsylvest/meta-team/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.

agentmods 80×15 button for orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gertsylvest/meta-team/claude-md"><img src="https://agentmods.dev/badge/instructions/gertsylvest/meta-team/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,790 This file is loaded in full into every session.
When invoked 3,790 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.03790 $0.03790
Opus 5 $0.01895 $0.01895
Sonnet 5 $0.00758 $0.00758
Haiku 4.5 $0.00379 $0.00379

Measured 9d ago against content hash d1c5da044151, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

orchestrator 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 9d 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.

CLAUDE.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project description

This is the meta-team project — a curated library of agents, orchestrators, skills, rules, and team definitions that can be used to bootstrap new Claude Code projects.

The workflow has two modes:

  1. Library mode — defining and refining new agents, orchestrators, skills, rules, and teams, adding them to the library when ready
  2. Bootstrap mode — interactive conversation to understand a new project's needs, then running a script to scaffold that project from the library

Repo arrangement: private source, public curated mirror

This local working directory is the private meta-team repo (meta-team-private on GitHub). All work happens here — new drafts, in-progress agents, experimental skills.

A separate public repo (meta-team on GitHub) is a curated subset, snapshot-published from this one. The public repo is never edited directly.

  • What's published: only files listed in .publish-manifest at the repo root.
  • How to publish: from this repo, run ./scripts/publish.sh "<commit message>". The script clears the public worktree (default location: ~/dev/meta-team-public/) and re-snapshots from the manifest, then commits and pushes.
  • Preview without committing: ./scripts/publish.sh --diff shows what would change.
  • To expose a new file publicly: add a line to .publish-manifest, then publish.
  • To remove a file from public: delete the line from .publish-manifest, then publish. The next snapshot will not include it.

When a new agent, skill, rule, or other library file is created, it is private by default. Promoting it to the public mirror requires an explicit manifest edit + publish.

Folder Structure

Library (/library)

The gold-standard, curated definitions. Only promoted, reviewed files live here.

  • /library/agents/ — agent definition files (subagents)
  • /library/orchestrators/ — orchestrator profile files (choose one per project)
  • /library/skills/ — skill definitions, each in a subfolder: /library/skills/{{skill_name}}/SKILL.md
  • /library/rules/ — rule files
  • /library/teams/ — team definition files, named descriptively: /library/teams/{{team_name}}.md (e.g. dev-team.md, research-team.md)
  • /library/documentation/ - documentation of the "meta-team" project and resources

Read the full file on GitHub · 256 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. 9d ago First seen · 256 lines · 3,790 tokens per session scan A d1c5da044151

Subscribe to this mod's changes

orchestrator is an instructions file published in the GitHub repository gertsylvest/meta-team (5 stars, last pushed 1mo ago), licensed MIT. It adds 3,790 tokens to every session, about $0.0190 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 2026-08-31.

Related

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.

vercel/next.js · 7,296 tokens

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 · 5,153 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

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

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

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.

deepseek-ai/deepseek-harness · 3,735 tokens