agentmods.dev

FigCC AGENTS.md

A set of project instructions for FigCC, a Figma-connected application that links a Figma plugin with coding agents. It documents the system structure, compatibility requirements, security rules, and storage boundaries.

In plain words
What is it for?
Implementing or reviewing changes to FigCC's interface, Figma integration, bridge server, authentication, agent sessions, and tool routing.
Why use it?
It helps developers modify the project without breaking its connection between Figma, the bridge service, and the coding agents.

Instructions file for CodexOpenCode

22 26d ago A scan 1,670 tokens original MIT
View the source file madebypan/FigCC
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 instructions/madebypan/figcc/agents-md
Clone the repo
git clone --depth 1 https://github.com/madebypan/FigCC

Made for: Codex, OpenCode.

Per session 1,670 This file is loaded in full into every session.
When invoked 1,670 The same file — it is already loaded in full.
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 $0.01670 $0.01670
Opus 5 $0.00835 $0.00835
Sonnet 5 $0.00334 $0.00334
Haiku 4.5 $0.00167 $0.00167

Measured 2d ago against content hash f5dd12c92e37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FigCC 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 2d 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.

AGENTS.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file contains repository-wide instructions for coding agents working on FigCC.

Project identity

  • Product name: FigCC.
  • Compatibility package/service identifiers remain figcodex, FIGCODEX_*, and com.figcodex.bridge.
  • FigCC is a derivative of PavelLaptev/FigClaw, used under the MIT License.
  • Preserve LICENSE, NOTICE.md, the upstream copyright line, and the explicit FigClaw attribution in both READMEs.
  • This is an independent community project. Do not imply official affiliation with Figma, Anthropic, or OpenAI.

Runtime architecture

                                      ┌→ codex app-server
Figma iframe UI → authenticated bridge┤
       ↑ tool calls and results ↓      └→ Claude Code Agent SDK
Figma plugin sandbox → open Figma document
  • src/UI.svelte owns the iframe, WebSocket client, provider-scoped conversation state, streamed events, and tool-call routing.
  • src/code.ts owns Figma APIs, client storage, selection snapshots, downloads, and tool execution.
  • bridge/server.js owns pairing authentication, provider dispatch, Codex threads, Claude sessions, attachments, skills, and tool routing.
  • bridge/codex-app-server.js is the JSON-RPC stdio adapter.
  • bridge/claude-provider.js is the Claude Code Agent SDK adapter and in-process FigCC MCP server.
  • bridge/dynamic-tool-reviewer.js performs the independent fail-closed review for side-effecting FigCC tools.
  • bridge/skill-store.js owns canonical filesystem skill packages under skills/<name>/SKILL.md.
  • bridge/workspace-store.js owns the authenticated native folder selection and persisted project root; bridge/linked-skill-store.js overlays that project's live skills/ packages on the bundled set.
  • src/tools.ts is the dynamic-tool schema source of truth.
  • Do not replace the App Server flow with one codex exec subprocess per prompt; that breaks the in-turn client tool handshake and native thread resume.
  • A chat belongs to exactly one provider. Switching Codex/Claude starts a new empty chat; History restores the chat's recorded provider and only its native thread/session ID. Never import transcript text across providers.

Read the full file on GitHub · 115 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. 2d ago First seen · 115 lines · 1,670 tokens per session scan A f5dd12c92e37

Subscribe to this mod's changes

FigCC AGENTS.md is an instructions file published in the GitHub repository madebypan/FigCC (22 stars, last pushed 26d ago), licensed MIT. It adds 1,670 tokens to every session, about $0.0083 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 2026-08-30.

PlanningSecuritycodexcodex-clidesign-agentfigmafigma-plugin
Related

Other instructions, from other repositories

figwright AGENTS.md

Instructions for awdr74100/figwright, covering agents.md, architecture, layout, tech stack and commands.

awdr74100/figwright · 5,203 tokens

figwright CLAUDE.md

Instructions for awdr74100/figwright: Read AGENTS.md first — it's the single source of guidance for this repo: architecture, layout, tech stack, commands, conventions, release flow, and gotchas.

awdr74100/figwright · 720 tokens

figma-mcp-free copilot-instructions.md

Instructions for karthikyaddana/figma-mcp-free, covering figma mcp free rules, required flow (do not skip), implementation rules, tool usage guide and node id format.

karthikyaddana/figma-mcp-free · 887 tokens

MasterGo2Figma AGENTS.md

AGENTS.md instructions for AaronXu-Lab/MasterGo2Figma, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

AaronXu-Lab/MasterGo2Figma · 2,943 tokens

MasterGo2Figma CLAUDE.md

Claude Code instructions for AaronXu-Lab/MasterGo2Figma: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

AaronXu-Lab/MasterGo2Figma · 82 tokens

slide-mcp copilot-instructions.md

Copilot instructions for Rikuto-des/slide-mcp, covering slide-mcp — copilot instructions, generating a deck, layouts (slide.layout), design systems (theme.preset) and minimal example.

Rikuto-des/slide-mcp · 745 tokens