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/raultov/knot/agents-mdgit clone --depth 1 https://github.com/raultov/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/raultov/knot/agents-md)<a href="https://agentmods.dev/instructions/raultov/knot/agents-md"><img src="https://agentmods.dev/badge/instructions/raultov/knot/agents-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 | $0.05196 | $0.05196 |
| Opus 5 | $0.02598 | $0.02598 |
| Sonnet 5 | $0.01039 | $0.01039 |
| Haiku 4.5 | $0.00520 | $0.00520 |
Grade C, and why
knot AGENTS.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Delete `.knot/` and rebuild: `rm -rf .knot/ && ./target/release/knot-indexer` How it starts
The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Knot Development Guidance
knot is a dual-database codebase indexer (Rust 2024 edition) that powers semantic code search via MCP. This file captures repo-specific guidance that would trip up an unfamiliar agent.
Quick Commands
Build everything:
cargo build --release
Run unit tests only:
cargo test
Run all E2E tests (requires Docker + databases):
./tests/run_all_e2e_fast.sh
Run a single E2E language suite:
./tests/run_typescript_e2e.sh # TypeScript
./tests/run_java_e2e.sh # Java
./tests/run_javascript_e2e.sh # JavaScript
./tests/run_web_e2e.sh # HTML + JSX + CSS + SCSS + hybrid
./tests/run_kotlin_e2e.sh # Kotlin
./tests/run_rust_e2e.sh # Rust
./tests/run_python_e2e.sh # Python
./tests/run_build_systems_e2e.sh # Maven/Gradle/Jenkins/Cargo.toml
./tests/run_groovy_e2e.sh # Groovy
./tests/run_cpp_e2e.sh # C/C++
./tests/run_csharp_e2e.sh # C#
./tests/run_cross_lang_ref_e2e.sh # Cross-language validation
./tests/run_config_e2e.sh # YAML/JSON/.properties config
./tests/run_k8s_helm_e2e.sh # Kubernetes + Helm
./tests/run_cross_repo_dep_e2e.sh # Cross-repo dependency linking
Code quality:
cargo clippy --all-targets -- -D warnings # Must pass
cargo fmt -- --check # Must pass before commit
cargo fmt # Auto-fix formatting
Architecture Overview
Three Binaries
| Binary | Purpose | Feature Flag |
|---|---|---|
knot-indexer |
Parses code, builds indexes (Qdrant + Neo4j) | indexer (default) |
knot |
CLI tool for search/explore/callers | always built |
knot-mcp |
MCP server for LLM integration | always built |
Entrypoints
src/bin/knot-indexer.rs— Main indexing pipelinesrc/bin/knot.rs— CLI tool (search/explore/callers/deps commands)src/bin/knot-mcp.rs— MCP server (exposes tools to LLMs)src/lib.rs— Shared library (modules:pipeline,db,mcp_tools,cli_tools, etc.)
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 · 455 lines · 5,196 tokens per session scan C 10d24833adc5
knot AGENTS.md is an instructions file published in the GitHub repository raultov/knot (5 stars, last pushed 4d ago), licensed MIT. It adds 5,196 tokens to every session, about $0.0260 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
codedb copilot-instructions.md
Copilot instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
codedb CLAUDE.md
Claude Code instructions for justrach/codedb, covering codedb — agent instructions, project, rules, filing issues and test style.
rust-code CLAUDE.md
Instructions for fortunto2/rust-code, covering claude.md — rust-code, stack, architecture, crate dependency graph and sgr-agent framework.
goodboy AGENTS.md
AGENTS.md instructions for akhayam99/goodboy, covering agents.md, where new code goes, naming, components and exports and store selectors and memoization.
goodboy CLAUDE.md
Claude Code instructions for akhayam99/goodboy, covering goodboy (claude-specific notes), stack quick-reference and claude-specific notes.