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/codebendkit/codeseek/claude-mdgit clone --depth 1 https://github.com/CodeBendKit/codeseekWhat 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 | $0.01559 | $0.01559 |
| Opus 5 | $0.00779 | $0.00779 |
| Sonnet 5 | $0.00312 | $0.00312 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
codeseek 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 yesterday.
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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Build & Test
# Enter Rust project directory
cd rust-core
# Build
cargo build
# Run tests
cargo test
# Run specific test
cargo test test_build_graph_functionality
# Run with output
cargo test -- --nocapture
# Start server (single repo per process, required)
cargo run -- server --repo-path /path/to/repo
# Start server with custom address
cargo run -- server --repo-path /path/to/repo --address 0.0.0.0:8080
# CLI vectorize mode
cargo run -- vectorize --path /path/to/code --collection my-collection --db-uri data/lancedb
Architecture
src/
├── main.rs # CLI entry: server and vectorize subcommands
├── lib.rs # Top-level module re-exports
├── config.rs # Config loading from ~/.codeseek/config/config.toml
├── cli/ # CLI args (clap), runner, analyze, vectorize commands
├── codegraph/ # AST parsing + graph data structures
│ ├── graph.rs # Flat CodeGraph (HashMap-based)
│ ├── types.rs # PetCodeGraph, EntityGraph, FileIndex, SnippetIndex
│ ├── parser.rs # CodeParser: tree-sitter parsing with FileIndex/SnippetIndex
│ └── treesitter/ # Language parsers (Rust/Python/JS/TS/Java/C++/Go)
├── services/ # High-level analysis services
│ ├── analyzer.rs # CodeAnalyzer: call chains, cycles, complexity, reports
│ ├── embedding_service.rs # LanceDB vector embeddings + SQLite cache + semantic search
│ └── snippet_service.rs # Code snippet extraction + caching
├── storage/ # Graph persistence and file watching
│ ├── persistence.rs # Save/load graphs (JSON + binary), project registry
│ ├── petgraph_storage.rs # PetCodeGraph serde (JSON, bincode, GraphML, GEXF)
│ ├── incremental.rs # MD5-based incremental file change detection
│ └── mod.rs # StorageManager: central hub (graph, watchers, tasks, config, current_repo)
├── http/ # Axum HTTP server
│ ├── server.rs # CodeSeekServer: startup init + router
│ ├── handlers/ # Request handlers (query, search, investigate, embed)
│ └── models/ # Request/response types + ApiResponse<T>
└── config/ # Config file template
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.
- yesterday First seen · 125 lines · 1,559 tokens per session scan A b9b1fb60c993
codeseek CLAUDE.md is an instructions file published in the GitHub repository CodeBendKit/codeseek (765 stars, last pushed 1mo ago), licensed MIT. It adds 1,559 tokens to every session, about $0.0078 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
bonsai-ninja AGENTS.md
Instructions for gromhacks/bonsai-ninja, covering bonsai-ninja, map a codebase, optional explicit semantic sidecar prewarm, explicit spelling for default syntax/construct indexing and optional during active editing.
codeweave-mcp CLAUDE.md
Instructions for semihkayan/codeweave-mcp, covering claude.md, what this project is, build & run, architecture and layers.
codexray CLAUDE.md
Instructions for NeuralRays/codexray, covering codexray — ai agent instructions, workflow and key principle.
roam-code AGENTS.md
Instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).
ScalaSemantic AGENTS.md
Instructions for MercurieVV/ScalaSemantic, covering agents.md instructions and quick start.
aptu-coder AGENTS.md
AGENTS.md instructions for clouatre-labs/aptu-coder, covering agents.md, project structure, ci runners, commands and observability.