What is figjam-mcp AGENTS.md?

Repository instructions for coding agents working on a TypeScript and Node.js server that turns FigJam boards into source-cited context for language models.

Use it when changing the FigJam MCP server, especially for running checks, adding tests, updating the changelog, and avoiding unsafe data sharing.

It tells an agent which files and public interfaces must remain compatible, which checks must pass, and what privacy and release rules apply.

How ecestnrkl/figjam-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ecestnrkl/figjam-mcp. 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/ecestnrkl/figjam-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ecestnrkl/figjam-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ecestnrkl/figjam-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ecestnrkl/figjam-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ecestnrkl/figjam-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ecestnrkl/figjam-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ecestnrkl/figjam-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ecestnrkl/figjam-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 588 This file is loaded in full into every session.

When invoked 588 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.

Model	Per session	Once invoked
Fable 5.1	$0.00588	$0.00588
Opus 5.5	$0.00235	$0.00235
Sonnet 5.5	$0.00118	$0.00118
Haiku 4.5	$0.00059	$0.00059

Measured 17d ago against content hash 1686ce9a483f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figjam-mcp 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 17d 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 · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for coding agents working on this repository. Humans: see CONTRIBUTING.md.

Context

figjam-context-mcp is a local stdio MCP server (TypeScript, Node.js 22.12+) that turns FigJam boards into source-cited context for LLMs. Five tools: ingest_board, get_board_context, answer_from_board, diff_board, diagnose_llm_config. Current plan: ROADMAP.md.

Working rules

Do the task, nothing more. Put other findings under "Follow-ups" in the PR description.
Compatibility: tool names, input schemas and required output fields are a public contract. Change them only when the task says so.
Done means: npm run check and npm run package:smoke pass, CI is green on all jobs, new behaviour has tests, user-visible changes have one line in CHANGELOG.md.
LLM answer quality is not a gate. Never block a change or a release on how a free model answers. No multi-round acceptance campaigns, request ledgers, checksum reports or per-request approval budgets. A live provider check is a smoke test: synthetic data, at most 10 requests, result summarized in the PR.
Privacy: never send content of a real board to an LLM provider unless the task explicitly allows it. Never commit .env, tokens, board data or .cache/, and never put real board names, URLs or content into commits, PRs or docs.
Docs: English and concise. Evidence belongs in the PR description, not in new files. Do not add review or report documents. Update README/docs only where behaviour changed.
Git: feature branch, Conventional Commits, one focused PR. Do not merge, tag, publish to npm or update registries (MCP Registry) unless the task says so.
Stop instead of looping: if something fails twice for reasons outside the code (provider outage, rate limit, missing credentials), stop and report what is needed.
Releases: a release bundles several PRs. Feature PRs keep the version and add their CHANGELOG line under ## <next version> — Unreleased; only the release PR sets the version (package.json, package-lock.json, both fields in server.json) and the date.

Read the full file on GitHub · 38 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.

17d ago Changed · +1 lines · +58 tokens per session 1686ce9a483f
19d ago First seen · 37 lines · 530 tokens per session scan A df2c41d8d4fe

Subscribe to this mod's changes

figjam-mcp AGENTS.md is an instructions file published in the GitHub repository ecestnrkl/figjam-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 588 tokens to every session, about $0.0024 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 2026-10-19.

Building agents LLM Project management ai-tools developer-tools figjam figma figma-api

figjam-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
figjam-mcp AGENTS.mdecestnrkl/figjam-mcp	Instructions file	1	yesterday	MIT	A	588	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

figjam-mcp: Instructions file for Codex