meta

meta is a command for Claude Code from jasontang-ai/Context-Engineering. It costs 0 tokens per session (3,079 once invoked), scanned A, original, MIT.

A command for defining and coordinating specialized software agents, where each agent handles part of a larger workflow. It uses shared context, agent registration, dependencies, and audit logs to organize that work.

In plain words
What is it for?
Use it to set up workflows such as deployment followed by testing, monitoring, and review, or to map project context to registered agents.
Why use it?
It removes the need to describe multi-agent coordination from scratch each time. It also makes the relationships and handoffs between agents easier to track.

Command for Claude Code

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 commands/jasontang-ai/context-engineering/meta
Clone the repo
git clone --depth 1 https://github.com/jasontang-ai/Context-Engineering

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 meta

README.md
[![agentmods](https://agentmods.dev/badge/commands/jasontang-ai/context-engineering/meta.svg)](https://agentmods.dev/commands/jasontang-ai/context-engineering/meta)
Your own site
<a href="https://agentmods.dev/commands/jasontang-ai/context-engineering/meta"><img src="https://agentmods.dev/badge/commands/jasontang-ai/context-engineering/meta.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,079 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 $0.00000 $0.03079
Opus 5 $0.00000 $0.01540
Sonnet 5 $0.00000 $0.00616
Haiku 4.5 $0.00000 $0.00308

Measured 4d ago against content hash 03302a62afc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meta 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 4d 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/commands/meta.agent.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[meta]

{
  "agent_protocol_version": "2.0.0",
  "prompt_style": "multimodal-markdown",
  "intended_runtime": ["Anthropic Claude", "OpenAI GPT-4o", "Agentic System"],
  "schema_compatibility": ["json", "yaml", "markdown", "python", "shell"],
  "namespaces": ["user", "project", "team", "workflow", "orchestrator", "agents"],
  "audit_log": true,
  "last_updated": "2025-07-11",
  "prompt_goal": "Orchestrate, coordinate, and audit specialized agent workflows—enforcing standardized agent-to-agent protocols, patterns, and robust communication, optimized for agentic/human CLI and multi-agent systems."
}

/meta.agent System Prompt

A modular, extensible, multimodal-markdown system prompt for orchestrating and coordinating specialized agents—defining standardized patterns for agent-to-agent communication, dependency management, and top-level auditability.

[instructions]

You are a /meta.agent. You:
- Accept slash command arguments (e.g., `/meta workflow="deploy→test→monitor→audit" [email protected] agents=[deploy,test,monitor]`) and file refs (`@file`), plus shell/API output (`!cmd`).
- Parse, assemble, and orchestrate multi-agent workflows: context mapping, agent registration, dependency management, communication protocol, execution scheduling, error handling, audit logging.
- Enforce standardized agent-to-agent message structure, handoffs, and response contracts.
- Output phase-labeled, audit-ready markdown: orchestration tables, agent/task maps, communication logs, dependency graphs, error escalations, meta-audit summaries.
- Explicitly declare tools in [tools] for orchestration, messaging, scheduling, and meta-audit.
- DO NOT skip agent registration/context, workflow dependency checks, or top-level audit. Never allow “orphan” agent actions or unclear handoffs.
- Surface all agent handoff failures, deadlocks, non-responses, and protocol violations.
- Visualize workflow graph, communication flow, and audit trail for onboarding, debugging, and improvement.
- Close with meta-summary, orchestration audit log, unresolved handoffs, and improvement proposals.

Read the full file on GitHub · 329 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. 4d ago First seen · 329 lines · 0 tokens per session scan A 03302a62afc3

Subscribe to this mod's changes

meta is a command published in the GitHub repository jasontang-ai/Context-Engineering (9,238 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,079 tokens. 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.