What is forkable-mcp AGENTS.md?

A project-specific instruction document for forkable-mcp, a Bun and TypeScript server that connects tools through the Model Context Protocol. It records the code layout, runtime rules, authentication state and safety requirements.

Use it when developing, testing or reviewing the forkable-mcp server, its React application, shared packages, build scripts and command-line behavior.

It gives coding agents the constraints they need to change the repository without breaking its structure, session handling or write-confirmation rules.

How colinds/forkable-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to colinds/forkable-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/colinds/forkable-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/colinds/forkable-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/colinds/forkable-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/colinds/forkable-mcp/agents-md)

Your own site

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

Per session 4,139 This file is loaded in full into every session.

When invoked 4,139 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	$0.04139	$0.04139
Opus 5.5	$0.01656	$0.01656
Sonnet 5.5	$0.00828	$0.00828
Haiku 4.5	$0.00414	$0.00414

Measured 17d ago against content hash cf6674a7b435, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

forkable-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 · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Development guidance for forkable-mcp. User setup belongs in README.md; this file records implementation contracts that coding agents must preserve.

Runtime and layout

This is a Bun + TypeScript MCP server. The MCP client spawns it over stdio and owns its lifecycle. There is no HTTP server.

apps/
  mcp/            The published forkable-mcp package
    src/
      index.ts    CLI entry point
      server/     Authentication, API access, tools, forms, and write gate
    tests/        Server and CLI tests
  app/
    src/          React components, hooks, pages, and host styling
    tests/        UI unit tests and browser fixtures
packages/shared/
  src/
    contracts/    Public MCP input/output schemas and inferred types
    dates.ts      Calendar helpers shared by app and server
    images.ts     Allowed meal-image origins and URL validation
tests/fixtures/   Fixtures shared by server and app tests
scripts/build.ts  bundles the server and self-contained UI
scripts/dev.ts    watches server code and rebuilds UI changes
scripts/smoke.ts  packed-install smoke test

The only durable runtime state is ~/.forkable-mcp/session.json (or FORKABLE_MCP_HOME/session.json). Pending confirmations are process-local and disappear on restart.

Keep one current MCP contract. Do not add legacy argument aliases, confirmation formats, session migrations, or response shims without a demonstrated need; agents can re-read tool schemas and adapt.

The root contains shared tooling; apps/mcp is the only published workspace. apps/app and packages/shared are private. Declare dependencies in the workspace that imports them, using the root catalog only for external versions shared across workspaces. React and TanStack belong to the app; the server uses lucide-static only at build time for native-form icons. Shared source is bundled into the published server; private workspace dependencies must never escape into its runtime.

Authentication and session state

Read the full file on GitHub · 345 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 · +15 tokens per session cf6674a7b435
18d ago First seen · 344 lines · 4,124 tokens per session scan A a323c7219c87

Subscribe to this mod's changes

forkable-mcp AGENTS.md is an instructions file published in the GitHub repository colinds/forkable-mcp (2 stars, last pushed 17d ago), licensed MIT. It adds 4,139 tokens to every session, about $0.0166 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 2026-10-20.

Building agents Writing and docs forkable mcp model-context-protocol

forkable-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
forkable-mcp AGENTS.mdcolinds/forkable-mcp	Instructions file	2	17d ago	MIT	A	4,139	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

forkable-mcp: Instructions file for Codex