figwright CLAUDE.md

figwright CLAUDE.md is an instructions file for coding agents from awdr74100/figwright. It costs 720 tokens per session, scanned A, original, MIT.

Project instructions for Figwright, a server that connects Figma to coding tools. They describe its structure, commands, coding rules, and release checks.

In plain words
What is it for?
Working on the Figma connection, building and testing its packages, and following the repository's development and release process.
Why use it?
They tell the agent which guidance to read, how to rebuild the server after changes, and which checks must pass before pushing code.

Instructions file

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/awdr74100/figwright/claude-md
Clone the repo
git clone --depth 1 https://github.com/awdr74100/figwright

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 figwright CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/awdr74100/figwright/claude-md.svg)](https://agentmods.dev/instructions/awdr74100/figwright/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/awdr74100/figwright/claude-md"><img src="https://agentmods.dev/badge/instructions/awdr74100/figwright/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 720 This file is loaded in full into every session.
When invoked 720 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 $0.00720 $0.00720
Opus 5 $0.00360 $0.00360
Sonnet 5 $0.00144 $0.00144
Haiku 4.5 $0.00072 $0.00072

Measured 4d ago against content hash 3dd3f81a1a19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

figwright CLAUDE.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 4d 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.

CLAUDE.md · 14 lines

What it actually says

CLAUDE.md

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

Claude Code specifics:

  • This repo is a Figma MCP server. The project-scoped .mcp.json launches the local build (packages/mcp/dist/index.mjs), so after changing packages/mcp or packages/shared you must pnpm build and restart the MCP connection before the figwright tools reflect your change.
  • There are no git hooks; CI is the gate. When you edit through Claude Code, the PostToolUse hook (.claude/hooks/format-on-edit.mjs) auto-formats and lints the file — don't hand-format.
  • The canonical checks before pushing are pnpm typecheck && pnpm lint && pnpm format:check && pnpm knip && pnpm build && pnpm test (the same gates CI runs).
  • The MCP SDK is v2@modelcontextprotocol/server (plus its transitive @modelcontextprotocol/core), not the v1 @modelcontextprotocol/sdk. src/index.ts builds the server in a factory and hands it to serveStdio, which owns the transport and the protocol-era decision.
  • The SDK is a runtime dependency — it generates every tool's JSON Schema and negotiates the protocol version — so a release can move what clients see while tsc stays green. packages/mcp/test/e2e/mcp-wire.test.ts is the gate for exactly that: it spawns the built dist over real stdio, speaks raw JSON-RPC (never the SDK's own Client, which would move in lockstep and hide the regression), and asserts the advertised tool set, each schema against an SDK-independent derivation, the dialect, annotations, prompts, a live tools/call, that a 2024-11-05 client is still served, that a 2026-07-28 client gets the modern era and is refused the ping that revision deleted, and that the process still exits cleanly when the client goes away mid-session. It runs in pnpm test but needs pnpm build first, and skips when dist is missing.
  • The mcp-sdk-audit skill (.claude/skills/) owns SDK upgrades. The gate answers did anything break; the skill's probe.mjs answers what moved, by snapshotting the live wire contract before and after a bump and diffing. Reach for it on any @modelcontextprotocol/* bump.
  • The figma-typings-audit skill (.claude/skills/) owns @figma/plugin-typings upgrades end to end: it diffs the .d.ts between the installed and target version (that package ships no changelog), maps the result onto the sandbox handlers, the hand-written Zod mirrors in shared, and the tool registry, then bumps and implements what's worth having. It diffs before upgrading — the installed version is the baseline. Reach for it on a Renovate bump PR for that package: a green pipeline does not mean the update was absorbed, since shared mirrors Figma's shapes with no compile-time coupling to the typings.
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. 4d ago First seen · 14 lines · 720 tokens per session scan A 3dd3f81a1a19

Subscribe to this mod's changes

figwright CLAUDE.md is an instructions file published in the GitHub repository awdr74100/figwright (667 stars, last pushed today), licensed MIT. It adds 720 tokens to every session, about $0.0036 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.