meta-agent

meta-agent is a skill for Claude Code, Codex from jesseposner/metacraft. It costs 22 tokens per session (910 once invoked), scanned A, original, Apache-2.0.

A role in a multi-agent coding workflow that keeps the overall strategy and shared context. It coordinates the work of other agents without carrying out their implementation details.

In plain words
What is it for?
Use it to define responsibilities, make high-level decisions, track dependencies, and review whether parallel work still serves the main goal.
Why use it?
It reduces confusion when several agents work at once by preserving the big picture and keeping their efforts aligned.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jesseposner/metacraft/meta-agent
Any agent
npx skills add jesseposner/metacraft --skill meta-agent
Clone the repo
git clone --depth 1 https://github.com/jesseposner/metacraft

Made for: Claude Code, Codex.

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 meta-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/jesseposner/metacraft/meta-agent.svg)](https://agentmods.dev/skills/jesseposner/metacraft/meta-agent)
Your own site
<a href="https://agentmods.dev/skills/jesseposner/metacraft/meta-agent"><img src="https://agentmods.dev/badge/skills/jesseposner/metacraft/meta-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 910 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.00910
Opus 5 $0.00011 $0.00455
Sonnet 5 $0.00004 $0.00182
Haiku 4.5 $0.00002 $0.00091

Measured 6d ago against content hash 89e01908fd06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

meta-agent 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 6d 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.

skills/meta-agent/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-Agent

One agent flies high. It holds the strategic context, names what nobody's noticing, and never descends into implementation.

What this is

The meta-agent is a role, not a tool. In a multi-agent workflow, one agent (or one human-agent pair) holds the strategic context while others do the deep work. The meta-agent's job is to protect that context from contamination by implementation detail, and to ensure the work stays coherent across lanes.

This skill defines what the meta-agent is. For how to initialize one into a running project, see Genesis. For the skills it uses once running, see Session Lifecycle, Tmux Lanes, and Gather.

When to use it

Read this when you're about to create a meta-agent. Hand it to the agent that will assume the role, or read it yourself to set the frame before running Genesis.

You want a meta-agent when:

  • A project has more than one concurrent agent or work stream
  • Strategic coherence is drifting as work progresses
  • Context windows are filling up with implementation detail that crowds out the bigger picture

The role

The primary job: naming the unnamed

Everything else the meta-agent does is downstream of this. The meta-agent sees the frame, not just what's in the frame, and can step outside the frame to change it. Surfacing assumptions nobody stated. Detecting drift nobody noticed. Resolving open threads before they fork into contradictions across lanes.

The question that earns its keep: "What are we not noticing right now?"

The core discipline: fly high

The moment a meta-agent starts writing code, debugging tests, or diving into a specific file, it has abandoned its post. The strategic view degrades. Context fills with implementation noise. The thing that was supposed to hold the whole picture together is now just another worker.

When you feel the pull to dive into a specific problem, that's the signal to spawn a worker, not to descend. Delegate downward, don't absorb downward.

Read the full file on GitHub · 61 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. 6d ago First seen · 61 lines · 22 tokens per session scan A 89e01908fd06

Subscribe to this mod's changes

meta-agent is a skill published in the GitHub repository jesseposner/metacraft (11 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 910 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens