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/docfork/docfork/claude-mdgit clone --depth 1 https://github.com/docfork/docforkWhat 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 | $0.00711 | $0.00711 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
docfork 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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
Root (monorepo)
pnpm build # Build all packages (turbo)
pnpm dev # Start all dev servers
pnpm lint # Lint all packages
pnpm lint:check # Check linting (CI)
pnpm format # Format all code
pnpm format:check # Check formatting (CI)
pnpm typecheck # Type-check all packages
pnpm test # Run all tests
pnpm clean # Clean all dist/node_modules
Package-scoped
pnpm --filter dgrep build
pnpm --filter dgrep typecheck
pnpm --filter dgrep test
pnpm --filter docfork build # MCP server package
pnpm --filter docfork typecheck
Before committing
pnpm lint:check && pnpm typecheck
Architecture
Monorepo structure
docfork/
├── packages/
│ ├── mcp/ # MCP server (npm: docfork, v2.1.0)
│ └── dgrep/ # Documentation grounding CLI (npm: dgrep, v0.1.0-alpha)
└── plugins/ # IDE plugins
Package manager: pnpm v9.0.0+ with workspaces Build orchestration: Turborepo TypeScript: Strict mode, ES2022 target, Node16 module resolution
MCP server (packages/mcp/)
Docfork MCP server supporting stdio and HTTP transports. Published to npm as docfork. Has its own API client in src/api/ — intentionally isolated from dgrep.
dgrep CLI (packages/dgrep/)
Documentation context CLI. Alpha stage. Uses obuild for single-file bundling (zero runtime node_modules). Has its own standalone API client — will migrate to ConnectRPC when api-v2 is ready.
Code Style
Formatting (Prettier)
Print width: 100, tab width: 2, semicolons: true, double quotes, trailing commas: all.
TypeScript
- Strict mode. Prefer
unknownoverany. - ESM only (
"type": "module"in all packages).
Naming
- Files: kebab-case. Types/Interfaces: PascalCase. Variables/functions: camelCase.
- Constants:
SCREAMING_SNAKE_CASE.
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.
- 2d ago First seen · 97 lines · 711 tokens per session scan A 0f643a237e31
docfork CLAUDE.md is an instructions file published in the GitHub repository docfork/docfork (488 stars, last pushed 2mo ago), licensed MIT. It adds 711 tokens to every session, about $0.0036 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 2026-08-30.
Other instructions, from other repositories
mcp-toolbox GEMINI.md
Gemini CLI instructions for googleapis/mcp-toolbox, covering mcp toolbox context & style guide, project overview, tech stack, key directories and development workflow.
open-agents AGENTS.md
AGENTS.md instructions for vercel-labs/open-agents, covering agents.md, quick links, authentication, database & migrations and environment isolation.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
ping-island AGENTS.md
Instructions for erha19/ping-island, covering agents.md, mission, start here, repo map and change routing.
axonhub AGENTS.md
AGENTS.md instructions for looplj/axonhub, covering agents.md, global rules, configuration, project overview and technology stack.