fbdl-mcp: Skill for Codex

.codex/skills/validate-fbdl/SKILL.md

validate-fbdl is a skill for Codex from GangGreenTemperTatum/fbdl-mcp. It costs 24 tokens per session (480 once invoked), scanned A, original, MIT.

A validation skill for FBDL scripts that checks them against the current block grammar, required entities, and action and reference rules. The input does not explain what FBDL means.

In plain words
What is it for?
Use it to check FBDL scripts for valid structure, required entities, and permitted actions or references.
Why use it?
It can identify scripts that do not follow the current FBDL rules, but the available description does not explain the wider system.

Skill for Codex

Written for Codex: installed under .codex/.

This is GangGreenTemperTatum/fbdl-mcp's own configuration. It tells Codex how to work on fbdl-mcp 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 fbdl-mcp configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/GangGreenTemperTatum/fbdl-mcp/main/.codex/skills/validate-fbdl/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GangGreenTemperTatum/fbdl-mcp

Made for: 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 validate-fbdl

README.md
[![agentmods](https://agentmods.dev/badge/skills/ganggreentempertatum/fbdl-mcp/validate-fbdl/github.svg)](https://agentmods.dev/skills/ganggreentempertatum/fbdl-mcp/validate-fbdl)
Your own site
<a href="https://agentmods.dev/skills/ganggreentempertatum/fbdl-mcp/validate-fbdl"><img src="https://agentmods.dev/badge/skills/ganggreentempertatum/fbdl-mcp/validate-fbdl/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 validate-fbdl

Your own site · 80×15
<a href="https://agentmods.dev/skills/ganggreentempertatum/fbdl-mcp/validate-fbdl"><img src="https://agentmods.dev/badge/skills/ganggreentempertatum/fbdl-mcp/validate-fbdl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00024 $0.00480
Opus 5.5 $0.00010 $0.00192
Sonnet 5.5 $0.00005 $0.00096
Haiku 4.5 $0.00002 $0.00048

Measured 2mo ago against content hash d6b92b60119c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validate-fbdl 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.

.codex/skills/validate-fbdl/SKILL.md · 74 lines

What it actually says

Validate FBDL

Validate an FBDL script and report any errors clearly.

Instructions

  1. If the validate_fbdl MCP tool is available, use it.
  2. Otherwise validate manually with the checklist below.
  3. Report errors with line numbers and specific explanations.
  4. If the script is valid, confirm that and briefly explain what it does.
  5. If the script is invalid, provide a corrected version.

Validation checklist

Structure

  • Script starts with [setup]
  • [setup] is on its own line
  • [action], if present, is on its own line
  • One entity declaration per line under [setup]
  • One action per line under [action]
  • Setup-only scripts are valid
  • Lines beginning with # are comments

Setup entities

  • Entity type is known: User, Page, Group, Album, Friendship, Business, App, Event
  • Every labeled entity has a label
  • Friendship has no label
  • Required params are present:
    • Page: owner
    • Group: owner, privacy
    • Album: owner, type, place
    • Friendship: sender, receivers
    • Business: owner
    • App: owner
    • Event: owner, place

References and syntax

  • Action name is known
  • Subject exists
  • Required keyword params are present
  • Voice switcher is only used on actions that support it
  • Referenced labels were defined earlier
  • Keyword blocks use {key: value}
  • Lists use [item1, item2]
  • String values use single quotes
  • Labels are unique and PascalCase

Output

If valid:

Script is valid. It creates [brief setup summary] and performs [brief action summary].

If invalid:

Found N error(s):

  • Line X: [specific error]
  • Line Y: [specific error]

Corrected script:

[corrected script]
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. 2mo ago First seen · 74 lines · 24 tokens per session scan A d6b92b60119c

Subscribe to this mod's changes

validate-fbdl is a skill published in the GitHub repository GangGreenTemperTatum/fbdl-mcp (8 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 480 once invoked, about $0.0001 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.

Related

validate-fbdl compared with skills from other repositories

validate-fbdl next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
validate-fbdlGangGreenTemperTatum/fbdl-mcpSkill8yesterdayMITA24Codex
opik-diagnosecomet-ml/opik-mcpSkill2259d agoApache-2.0A187Claude Code
ue-mcp-epic-routingdb-lyon/ue-mcpSkill476yesterdayMITA81Claude Code, Codex
qa-knowledgegriddynamics/rosettaSkill370yesterdayApache-2.0A32Claude Code, Codex
apitapn1byn1kt/apitapSkill13117d agoApache-2.0A0Claude Code, Codex
frontmcp-setupagentfront/frontmcpSkill148yesterdayApache-2.0A176Claude Code, Codex
x-use-reviewihuzaifashoukat/x-useSkill1814d agoMITA56Claude Code