agentic-tools: Instructions file for Codex

AGENTS.md

agentic-tools AGENTS.md is an instructions file for Codex, OpenCode from facebook/agentic-tools. It costs 2,062 tokens per session, scanned B, original, MIT.

Repository guidance for AI coding agents working on a collection of workflow skills for Meta's developer platform. It explains the repository layout, its plugin marketplaces, and the Developer Tools MCP server.

In plain words
What is it for?
Use it when developing skills or plugins for Meta developer tools, including app management, webhooks, compliance checks, app review, API monitoring, and documentation search.
Why use it?
It helps an agent find the right plugin files and follow the repository's organization when changing or adding skills.

Instructions file for CodexOpenCode ✓ vendor

Written for Codex and OpenCode: uses $skill-installer, but also the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is facebook/agentic-tools's own configuration. It tells Codex and OpenCode how to work on agentic-tools 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 agentic-tools configures →

About the project

Agentic Tools is a marketplace of plugins and skills for managing Meta Social Technologies applications, including settings, webhooks, compliance, app review, and API health. Developers use it with coding agents such as Claude Code, Cursor, and Codex through Meta's remote MCP server. The catalogue contains the project's agent add-ons.

facebook/agentic-tools · 15 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to facebook/agentic-tools. 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/facebook/agentic-tools/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/facebook/agentic-tools

Made for: Codex, OpenCode.

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 agentic-tools AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/facebook/agentic-tools/agents-md/github.svg)](https://agentmods.dev/instructions/facebook/agentic-tools/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/facebook/agentic-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/facebook/agentic-tools/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.

agentmods 80×15 button for agentic-tools AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/facebook/agentic-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/facebook/agentic-tools/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,062 This file is loaded in full into every session.
When invoked 2,062 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.02062 $0.02062
Opus 5.5 $0.00825 $0.00825
Sonnet 5.5 $0.00412 $0.00412
Haiku 4.5 $0.00206 $0.00206

Measured 6d ago against content hash 009cc47d00a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

agentic-tools AGENTS.md scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Codex**: install via `$skill-installer`, and add the MCP to `~/.codex/config.toml` (see README).
AGENTS.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide — Agentic Tools

This file helps AI agents navigate and use this repository effectively.

What this repo is

A skills repository for AI coding agents that provides workflow-oriented guidance for the Meta Social Technologies Developer Platform. Skills wrap the Meta Social Technologies MCP server tools into higher-level workflows for app management, webhook configuration, compliance auditing, app review preparation, API health monitoring, and documentation search.

Naming

These names are user-facing and easy to conflate. Use them exactly as written; do not invent variants.

Thing Canonical name Notes
This repo / marketplace Meta Agentic Tools displayName in both marketplace manifests. Docs headings use the shorter "Agentic Tools", since the facebook/agentic-tools repo path already supplies the "Meta".
The plugin (devtools) Meta Social Technologies Developer Never append "plugin" to the name itself; write "the Meta Social Technologies Developer plugin".
The platform Meta Social Technologies Developer Platform developers.facebook.com. Also known as "Meta for Developers: Social Technologies". Note the plugin name is a prefix of this one, so avoid using both in the same sentence.
The MCP server Meta Social Technologies MCP Formerly "Meta Developer Tools MCP". Server id is still devtools; tools are still prefixed devtools_.
The skills kebab-case ids app-health-check, webhook-setup, etc. No branding in skill names.

The plugin description is a single shared string, byte-identical across all five manifests. Change it in one place and propagate it to the other four.

devtools is a frozen identifier, not a name. It is the plugin id, the MCP server key in every mcp.json, the mcp__devtools__devtools_* tool namespace in all nine skills' allowed-tools, the plugins/devtools/ path, and the devtools@facebook install target. It is pinned to the MCP endpoint https://mcp.facebook.com/devtools, so it does not follow display-name changes. Renaming it breaks existing installs.

Read the full file on GitHub · 114 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 Changed · +4 lines · +55 tokens per session 009cc47d00a5
  2. 1mo ago Changed · +16 lines · +423 tokens per session 3f20f45bc257
  3. 1mo ago First seen · 94 lines · 1,584 tokens per session scan B 2ce37fb90f2d

Subscribe to this mod's changes

agentic-tools AGENTS.md is an instructions file published in the GitHub repository facebook/agentic-tools (15 stars, last pushed 6d ago), licensed MIT. It adds 2,062 tokens to every session, about $0.0082 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

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 · 9,649 tokens

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 · 7,257 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 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 · 4,159 tokens