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.
curl -O https://raw.githubusercontent.com/dannykeane/figmanage/main/AGENTS.mdgit clone --depth 1 https://github.com/dannykeane/figmanageWrote 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.
[](https://agentmods.dev/instructions/dannykeane/figmanage/agents-md)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Define its input shape and discovery metadata in
src/schemas.ts. UsefigmaIdfor every ID parameter. - Implement it in
src/operations/: callvalidateInputfirst, return plain data, throw errors with useful context. No MCP or CLI concerns. - Add the MCP wrapper with
defineTool(mark mutations;destructive: truewhere it deletes or removes access) and return throughtoolResult,toolSummaryortoolError. - Add the CLI subcommand. Route data through
output/outputEmpty, declaring the list field for wrapped lists (collection: 'files') so--jsonlworks. - Test observable behavior, including failed and partial responses for writes.
- Update docs/reference.md and the changelog. Keep the README to getting started.
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.
- 1mo ago First seen · 59 lines · 769 tokens per session scan A 828ba367bbeb
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.
figmanage AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| figmanage AGENTS.mddannykeane/figmanage | Instructions file | 9 | 25d ago | MIT | A | 769 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |