Borrowing it
Nothing to install: this file belongs to GangGreenTemperTatum/fbdl-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GangGreenTemperTatum/fbdl-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/GangGreenTemperTatum/fbdl-mcpWrote 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/instructions/ganggreentempertatum/fbdl-mcp/agents-md)<a href="https://agentmods.dev/instructions/ganggreentempertatum/fbdl-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ganggreentempertatum/fbdl-mcp/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.
<a href="https://agentmods.dev/instructions/ganggreentempertatum/fbdl-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ganggreentempertatum/fbdl-mcp/agents-md.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 | $0.01473 | $0.01473 |
| Opus 5.5 | $0.00589 | $0.00589 |
| Sonnet 5.5 | $0.00295 | $0.00295 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
fbdl-mcp AGENTS.md 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 2mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FBDL MCP Server -- Agent Instructions
What is FBDL?
FBDL (Facebook Developer Language) is a domain-specific language used in Meta's MMBRC (bug bounty program). It creates reproducible test environments with whitehat test users, pages, groups, and other Facebook entities. Researchers use FBDL scripts to set up specific scenarios for security testing.
Scripts are executed inside Meta's bug bounty platform -- this MCP server generates and validates them locally. The server fetches the FBDL grammar from https://api.facebook.com/bug_bounty/fbdl_reference/ at startup so it stays current, which requires FBDL_API_TOKEN in the environment.
Available tools
| Tool | When to use |
|---|---|
validate_fbdl |
After generating or receiving any FBDL script. Always validate before presenting to user. |
list_entities |
To check what setup entities exist and their parameters. Filter by type (User, Page, Group, etc). |
list_actions |
To find available actions. Filter by name or category (post, group, page, business, event, app). |
explain_fbdl |
To describe what an existing FBDL script does in plain English. |
There is also a generate_fbdl prompt template that provides the full FBDL grammar for script generation.
Workflow
1. list_entities / list_actions --> discover what's available
2. write the FBDL script --> follow the grammar below
3. validate_fbdl --> catch errors before presenting
4. (optional) explain_fbdl --> verify it does what's intended
Never skip step 3. Always validate.
FBDL grammar
Setup block (single line)
[setup] Type Label [with {key: value}] [Type Label with {key: value}] ...
Everything in the setup block is on ONE line. Entities are declared sequentially.
Entity types:
- User -- No params needed. Just
User LabelName. - Page -- Requires
owner. Optional: admins, editors, moderators, is_parent_location. - Group -- Requires
owner,privacy(public|private|public_legacy). Optional: members, admins, visibility. - Album -- Requires
owner,type(user|shared|page|group),place. - Friendship -- Requires
sender,receivers(list). Has NO label. - Business -- Requires
owner. Optional: employees, admins, primary_page, quarantine. - App -- Requires
owner. Optional: live (true|false), type. - Event -- Requires
owner,place. Optional: privacy, is_past, post_permission, post_approval.
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.
- 2mo ago First seen · 131 lines · 1,473 tokens per session scan A cdd9994a43de
fbdl-mcp AGENTS.md is an instructions file published in the GitHub repository GangGreenTemperTatum/fbdl-mcp (8 stars, last pushed yesterday), licensed MIT. It adds 1,473 tokens to every session, about $0.0059 per session on Opus 5.5. 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.
fbdl-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fbdl-mcp AGENTS.mdGangGreenTemperTatum/fbdl-mcp | Instructions file | 8 | yesterday | MIT | A | 1,473 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |