figmanage: Instructions file for Codex

AGENTS.md

figmanage AGENTS.md is an instructions file for Codex, OpenCode from dannykeane/figmanage. It costs 769 tokens per session, scanned A, original, MIT.

Repository-specific instructions for AI coding agents working on figmanage, a command-line tool and MCP server for administering Figma workspaces. They describe the project layout, development commands, testing setup, and rules for adding operations.

In plain words
What is it for?
Use them when building, checking, testing, or extending figmanage, including its command-line and MCP interfaces.
Why use it?
They give an agent the local conventions and safety rules needed to change this repository without guessing.

Instructions file for CodexOpenCode

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

This is dannykeane/figmanage's own configuration. It tells Codex and OpenCode how to work on figmanage 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 figmanage configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dannykeane/figmanage. 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/dannykeane/figmanage/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dannykeane/figmanage

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 figmanage AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dannykeane/figmanage/agents-md/github.svg)](https://agentmods.dev/instructions/dannykeane/figmanage/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dannykeane/figmanage/agents-md"><img src="https://agentmods.dev/badge/instructions/dannykeane/figmanage/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.

agentmods 80×15 button for figmanage AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dannykeane/figmanage/agents-md"><img src="https://agentmods.dev/badge/instructions/dannykeane/figmanage/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 769 This file is loaded in full into every session.
When invoked 769 The same file — it is already loaded in full.
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 $0.00769 $0.00769
Opus 5.5 $0.00308 $0.00308
Sonnet 5.5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 1mo ago against content hash 828ba367bbeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figmanage 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 1mo 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents working in this repository. Human contributors: see CONTRIBUTING.md, which this file follows.

figmanage is a CLI and MCP server for Figma workspace admin: seats, permissions, billing, files, components. It ships to npm as figmanage.

Commands

Use Node 22 or newer to develop. The published package supports Node 18 and newer.

npm ci --ignore-scripts
npm run build    # compile to dist/
npm run lint     # tsc --noEmit
npm test         # vitest run

Build before testing: integration tests launch the compiled CLI and MCP server from dist/ against a local fake API. Tests never need Figma credentials. Never use a real account in a test.

Layout

src/
  operations/   business logic, one module per area; pure functions that return data and throw on error
  tools/        MCP wrappers; defineTool() in tools/register.ts
  cli/          CLI wrappers (noun-verb subcommands); output helpers in cli/format.ts
  schemas.ts    input schemas and discovery metadata, shared by CLI and MCP
  validation.ts validateInput()
  mcp.ts        toolsets and presets
  types/        shared types, including the Toolset union
test/           one test file per module; shared mocks in test/helpers.ts

Operations hold all logic. Tools and CLI commands are thin wrappers that call an operation and format the result for their surface.

Adding an operation

  1. Define its input shape and discovery metadata in src/schemas.ts. Use figmaId for every ID parameter.
  2. Implement it in src/operations/: call validateInput first, return plain data, throw errors with useful context. No MCP or CLI concerns.
  3. Add the MCP wrapper with defineTool (mark mutations; destructive: true where it deletes or removes access) and return through toolResult, toolSummary or toolError.
  4. Add the CLI subcommand. Route data through output/outputEmpty, declaring the list field for wrapped lists (collection: 'files') so --jsonl works.
  5. Test observable behavior, including failed and partial responses for writes.
  6. Update docs/reference.md and the changelog. Keep the README to getting started.

Read the full file on GitHub · 59 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. 1mo ago First seen · 59 lines · 769 tokens per session scan A 828ba367bbeb

Subscribe to this mod's changes

figmanage AGENTS.md is an instructions file published in the GitHub repository dannykeane/figmanage (9 stars, last pushed 25d ago), licensed MIT. It adds 769 tokens to every session, about $0.0031 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 2026-10-08.

Related

figmanage AGENTS.md compared with instructions from other repositories

figmanage AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
figmanage AGENTS.mddannykeane/figmanageInstructions file925d agoMITA769Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode