agentmods.dev

figbridge AGENTS.md

figbridge AGENTS.md is an instructions file for Codex, OpenCode from rudraptpsingh/figbridge. It costs 1,695 tokens per session, scanned A, original, MIT.

Project instructions for Figbridge, a repository containing a Figma plugin, an MCP server, tests, release scripts, and documentation. They describe the project layout and the required release process.

In plain words
What is it for?
Use them when working on Figbridge code, tests, documentation, or releases, including version bumps, tagging, and pushing changes.
Why use it?
They give coding agents the repository-specific rules needed to edit the right files and avoid breaking the release workflow or runtime constraints.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

not rated 12 +1 2mo ago A scan 1,695 tokens original MIT
View the source file rudraptpsingh/figbridge rudraptpsingh.github.io
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/rudraptpsingh/figbridge/agents-md
Clone the repo
git clone --depth 1 https://github.com/rudraptpsingh/figbridge

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 figbridge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rudraptpsingh/figbridge/agents-md.svg)](https://agentmods.dev/instructions/rudraptpsingh/figbridge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rudraptpsingh/figbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/rudraptpsingh/figbridge/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,695 This file is loaded in full into every session.
When invoked 1,695 The same file — it is already loaded in full.
Security scan A 1 finding. 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 5.1 $0.01695 $0.01695
Opus 5 $0.00847 $0.00847
Sonnet 5 $0.00339 $0.00339
Haiku 4.5 $0.00169 $0.00169

Measured 6d ago against content hash 66df188d8a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

figbridge AGENTS.md scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Verify a listing: `curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.rudraptpsingh/figbridge"`.
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figbridge — agent memory

Context for future Codex sessions working in this repo. Keep short and current.

Repo shape

  • plugin/code.js — Figma plugin main thread. ES2017-safe (no spread / ?? / ?.), runs in QuickJS. The user-facing bug source.
  • plugin/ui.html — iframe UI. Cream/ink/rust theme. Sends pluginMessage events; receives window.onmessage.
  • mcp/ — npm package figbridge-mcp. Stdio MCP server + HTTP+SSE bridge on :7331.
  • test/ — integration tests.
  • test-agent/ — unit tests for the render pipeline, with a Figma-sandbox shim.
  • scripts/release.mjs — one-shot release cutter (below).
  • docs/ — GitHub Pages landing page + Figma Community listing assets.

Release flow — do not deviate

Cut a release:

node scripts/release.mjs patch          # 0.1.n → 0.1.(n+1)
node scripts/release.mjs minor          # 0.1.n → 0.2.0
node scripts/release.mjs X.Y.Z          # explicit
node scripts/release.mjs patch --dry    # preview, no mutation

The script refuses to run on dirty trees / off main / when local is behind origin. It bumps mcp/package.json, commits chore(release): vX.Y.Z, tags, pushes main + tag. Don't manually git tag unless the script itself is broken.

On tag push, .github/workflows/publish.yml runs:

  1. Verify tag matches mcp/package.json version.
  2. Smoke + full pipeline + tool-surface tests.
  3. npm publish --provenance.
  4. Poll npm until the version resolves.
  5. Sync server.json version to the tag (release script already did this, but CI re-runs to be safe).
  6. Install mcp-publisher from modelcontextprotocol/registry GH releases, login via github-oidc (no secrets), publish.
  7. Create GitHub Release — notes grouped by conventional-commit prefix (feat / fix / docs / ci|chore / other), appends install + update footer. Idempotent on re-run (gh release edit).

Checkout uses fetch-depth: 0 + fetch-tags: true so git describe --tags "$TAG^" can resolve the previous tag for the notes range. id-token: write permission covers both npm provenance and MCP registry OIDC.

Read the full file on GitHub · 103 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 First seen · 103 lines · 1,695 tokens per session scan A 66df188d8a11

Subscribe to this mod's changes

figbridge AGENTS.md is an instructions file published in the GitHub repository rudraptpsingh/figbridge (12 stars, last pushed 2mo ago), licensed MIT. It adds 1,695 tokens to every session, about $0.0085 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-agentsanthropicclaudecursordesign-to-codedesign-tokens
Related

Other instructions, from other repositories

design-md-extractor CLAUDE.md

Instructions for jpoindexter/design-md-extractor, covering claude.md, commands, run a single test file, cli usage (after build) and architecture.

jpoindexter/design-md-extractor · 1,039 tokens

figma-ios-codegen AGENTS.md

Instructions for mythkiven/figma-ios-codegen, covering project agent rules, 必读规则文件, 何时启用本流程, 铁律（最高优先级） and 架构（1 → 2 → 4；阶段 3 仓外）.

mythkiven/figma-ios-codegen · 1,739 tokens

figma-ios-codegen CLAUDE.md

Instructions for mythkiven/figma-ios-codegen, covering claude.md and how to run here (claude code).

mythkiven/figma-ios-codegen · 226 tokens

figma-unified-mcp CLAUDE.md

Instructions for sso-ss/figma-unified-mcp, covering agent instructions — figma-unified-mcp, critical: always check available tools & agent skills first, available tools (106), connection (3) and utility (3).

sso-ss/figma-unified-mcp · 2,662 tokens

awesome-copilot-id AGENTS.md

AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 8,242 tokens

llm-safe-haven CLAUDE.md

Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.

pleasedodisturb/llm-safe-haven · 1,322 tokens