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.
npx agentmods add instructions/colinds/forkable-mcp/claude-mdgit clone --depth 1 https://github.com/colinds/forkable-mcpWrote 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/colinds/forkable-mcp/claude-md)<a href="https://agentmods.dev/instructions/colinds/forkable-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/colinds/forkable-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.03215 | $0.03215 |
| Opus 5 | $0.01607 | $0.01607 |
| Sonnet 5 | $0.00643 | $0.00643 |
| Haiku 4.5 | $0.00321 | $0.00321 |
Grade A, and why
forkable-mcp 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 3d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.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.
src/
index.ts CLI entry point
server.ts stdio lifecycle and keepalive
tools.ts MCP tools and Forkable request construction
write-gate.ts preview, confirmation, and mutation recovery
net/ GraphQL transport and error mapping
auth/ login, browser-cookie ingest, and session storage
order/ domain types, selections, local guards, formatting, and status
tests/ Bun tests
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.
Authentication and session state
Forkable uses a Cookie header and CSRF token, not an API key. Sessions can come from email/password,
an imported browser cookie, FORKABLE_COOKIE, or an auth file/stdin. Browser import uses
@steipete/sweet-cookie on macOS, Linux, and Windows; Arc targeting is macOS-only, and Brave or
Chromium on Linux or Windows may require an explicit profile path. Password input must remain hidden
(--password-stdin or environment); never print credentials.
Session invariants:
- The store directory is mode
0700; the session file is atomically written with mode0600. - A usable session must contain a nonempty
_easyorder_sessioncookie. Set-Cookieresponse deltas are merged into the latest stored Cookie header. Do not persist a client's full stale jar over newer rotations.- In-process session writes are serialized. Cookie expiry and
Max-Ageare handled byauth/cookies.ts. - CSRF and cookie persistence failure is nonfatal after the in-memory client has accepted the response; emit a concise stderr warning and do not replay a mutation.
delegationSessionId: nullis meaningful and must clear delegation rather than preserve an older value.- Redacted logging may include lengths and metadata, never cookie, CSRF, password, or confirmation token contents.
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.
- 3d ago First seen · 275 lines · 3,215 tokens per session scan A 393908c3cc5f
forkable-mcp CLAUDE.md is an instructions file published in the GitHub repository colinds/forkable-mcp (2 stars, last pushed 9d ago), licensed MIT. It adds 3,215 tokens to every session, about $0.0161 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 2026-08-31.
Other instructions, from other repositories
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.