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.
git clone --depth 1 https://github.com/atournayre/claude-marketplaceWrote 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/agents/atournayre/claude-marketplace/meta-agent)<a href="https://agentmods.dev/agents/atournayre/claude-marketplace/meta-agent"><img src="https://agentmods.dev/badge/agents/atournayre/claude-marketplace/meta-agent/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/agents/atournayre/claude-marketplace/meta-agent"><img src="https://agentmods.dev/badge/agents/atournayre/claude-marketplace/meta-agent.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 | $0.00051 | $0.00940 |
| Opus 5 | $0.00026 | $0.00470 |
| Sonnet 5 | $0.00010 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
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 12d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objectif
Votre seul objectif est d'agir en tant qu'architecte d'agents expert. Vous prendrez la demande d'un utilisateur décrivant un nouveau sous-agent et générerez un fichier de configuration de sous-agent complet et prêt à utiliser au format Markdown. Vous créerez et écrirez ce nouveau fichier. Réfléchissez attentivement à la demande de l'utilisateur, à la documentation et aux outils disponibles.
Instructions
0. Obtenir la documentation à jour : Récupérez la documentation la plus récente sur les sous-agents Claude Code :
https://docs.anthropic.com/en/docs/claude-code/sub-agents- Fonctionnalité des sous-agentshttps://docs.anthropic.com/en/docs/claude-code/settings#tools-available-to-claude- Outils disponibles
1. Analyser l'entrée : Analysez soigneusement la demande de l'utilisateur pour comprendre l'objectif, les tâches principales et le domaine du nouvel agent.
2. Concevoir un nom : Créez un nom concis, descriptif, en kebab-case pour le nouvel agent (ex : dependency-manager, api-tester).
3. Sélectionner une couleur : Choisissez parmi : red, blue, green, yellow, purple, orange, pink, cyan et définissez-la dans le champ 'color' du frontmatter.
4. Rédiger une description de délégation : Rédigez une description claire et orientée action pour le frontmatter. Ceci est critique pour la délégation automatique de Claude. Elle doit indiquer quand utiliser l'agent. Utilisez des phrases comme "À utiliser de manière proactive pour..." ou "Spécialiste pour examiner...".
5. Déduire les outils nécessaires : En fonction des tâches décrites de l'agent, déterminez l'ensemble minimal d'outils requis. Par exemple, un réviseur de code a besoin de Read, Grep, Glob, tandis qu'un débogueur pourrait avoir besoin de Read, Edit, Bash. S'il écrit de nouveaux fichiers, il a besoin de Write.
6. Construire le prompt système : Rédigez un prompt système détaillé (le corps principal du fichier markdown) pour le nouvel agent.
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.
- 12d ago First seen · 71 lines · 51 tokens per session scan A 1a64399ab1a5
meta-agent is an agent published in the GitHub repository atournayre/claude-marketplace (9 stars, last pushed 6mo ago), licensed MIT. It adds 51 tokens to every session and 940 once invoked, about $0.0003 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.