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/projanvil/knot/claude-mdgit clone --depth 1 https://github.com/ProjAnvil/KnotWrote 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/projanvil/knot/claude-md)<a href="https://agentmods.dev/instructions/projanvil/knot/claude-md"><img src="https://agentmods.dev/badge/instructions/projanvil/knot/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 | $0.01921 | $0.01921 |
| Opus 5 | $0.00960 | $0.00960 |
| Sonnet 5 | $0.00384 | $0.00384 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
Knot 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 — 228 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.
Project Overview
Knot is an API documentation management system with Model Context Protocol (MCP) support. It features a Svelte 5 frontend and Go backend, supports multiple databases (SQLite, PostgreSQL, MySQL), and includes standalone CLI tools for both backend and MCP server management.
The project is structured as three independent components:
- frontend/: Svelte 5 application (manages its own dependencies with bun/npm)
- backend/: Go backend server
- mcp-server/: Go MCP server for AI integration
Essential Commands
Frontend Development (Svelte 5 + Vite)
cd frontend
bun install # Install dependencies
bun dev # Start dev server on port 5173 with hot reload
bun run build # Build for production to dist/
Backend Development (Go + Chi + GORM)
cd backend
go mod download # Download Go dependencies
make build # Build binary to bin/knot-server
./bin/knot-server # Run server on port 3000
# Development with auto-reload (using air)
air
# Build for all platforms
make build-all # Outputs to dist/
make package-all # Create distribution packages
MCP Server Development (Go)
cd mcp-server
go mod download # Download Go dependencies
make build # Build binary to bin/knot-mcp
./bin/knot-mcp # Run MCP server
# Build for all platforms
make build-all # Outputs to dist/
CLI Tool (knot)
The backend includes a CLI tool for server management:
cd backend
./bin/knot setup # Initialize config at ~/.knot/config.json
./bin/knot start # Start server in background
./bin/knot stop # Stop running server
./bin/knot status # Check server status and PID
Architecture
Database Layer
- ORM: GORM (Go ORM) with multi-database support
- Schema: Defined in
backend/internal/models/Group: API groupingsAPI: API endpoints (references groups)Parameter: Request/response parameters with nested support (self-referencing for object/array types)
- Migrations: Auto-migration via GORM's
AutoMigrateon startup - Database Support: SQLite, PostgreSQL, MySQL with runtime switching
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 · 228 lines · 1,921 tokens per session scan A 29a52d276db8
Knot CLAUDE.md is an instructions file published in the GitHub repository ProjAnvil/Knot (2 stars, last pushed 14d ago), licensed MIT. It adds 1,921 tokens to every session, about $0.0096 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
keryx CLAUDE.md
Instructions for actionhero/keryx, covering claude.md, project overview, monorepo structure, development environment and environment setup.
stitchkit AGENTS.md
Instructions for max-listov/stitchkit, covering stitchkit — agent guide, two roads — pick yours, rules, stack and commands.
stitchkit CLAUDE.md
Instructions for max-listov/stitchkit: This project's agent guide is AGENTS.md — the tool-agnostic standard also read by Cursor, Codex and other tools. It is imported below so Claude Code picks it up too.
pddikti CLAUDE.md
Claude Code instructions for andikadevs/pddikti, covering claude.md — pddikti api (bun + hono), what this is, data flow, project layout and web client (root /).
OmniBrain-AI-Proxy-Smart CLAUDE.md
Use Bun instead of Node.js, npm, pnpm, or vite.
APIMesh CLAUDE.md
Claude Code instructions for mbeato/APIMesh, covering apis, testing and frontend.