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/halaprix/bd-explore/claude-mdgit clone --depth 1 https://github.com/halaprix/bd-exploreWhat 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 | $0.00863 | $0.00863 |
| Opus 5 | $0.00432 | $0.00432 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
bd-explore CLAUDE.md scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Zero Runtime Dependencies**: The core package, CLI, and MCP server must rely exclusively on Python 3.10+ standard library modules (`sqlite3`, `argparse`, `json`, `pathlib`, `re`, `subprocess`, `urllib`, `dataclasses` How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Development & Repository Guide for bd-explore
Overview
bd-explore is a zero-dependency Python tool and MCP server that enables AI agents and developers to query a beads issue store codegraph-style. One query returns verbatim issue content (descriptions, notes, comments, close reasons, memories) along with relationship graphs (blocks, blocked-by, parent-child, mentions, GitHub refs) under a strict token/character budget.
Repository Architecture
src/bd_explore/
├── __init__.py # Package root
├── __main__.py # python -m bd_explore entrypoint
├── constants.py # Shared constants, defaults (budget, limits, dependency kinds)
├── explorer.py # Deep explore module: explore()/blast() own the whole pipeline (store discovery, index freshness, connection lifetime, defaults, error text)
├── index.py # SQLite FTS5 indexing, mention mining, store discovery, caching
├── search.py # BM25 search, query parsing, neighborhood graph, blast radius, formatting
├── mcp.py # Pure Python stdio JSON-RPC 2.0 MCP server
├── cli.py # CLI parsing, subcommand dispatch (serve, install, uninstall, print-config)
└── installer/ # Multi-target agent platform installer & memory injector
├── instructions.py # Marker-fenced instruction template management
├── memory.py # Beads persistent memory integration (`bd remember` / `bd forget`)
├── shared.py # Atomic file operations, JSON/TOML merging helpers
└── targets/ # Platform adapters (claude, gemini, antigravity, codex, cursor, agents_md)
Running Tests
All tests use Python's built-in unittest module. No external test runners or packages are required.
# Run the entire test suite
PYTHONPATH=src python3 -m unittest discover tests
# Run specific test modules
PYTHONPATH=src python3 -m unittest tests.test_index
PYTHONPATH=src python3 -m unittest tests.test_search
PYTHONPATH=src python3 -m unittest tests.test_mcp
PYTHONPATH=src python3 -m unittest tests.test_installer
PYTHONPATH=src python3 -m unittest tests.test_cli
# Run a single test case
PYTHONPATH=src python3 -m unittest tests.test_search.TestSearchEngine.test_bm25_search_scoring
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 · 69 lines · 863 tokens per session scan A 0dfaf670229a
bd-explore CLAUDE.md is an instructions file published in the GitHub repository halaprix/bd-explore (0 stars, last pushed 14d ago), licensed MIT. It adds 863 tokens to every session, about $0.0043 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
markdown-vault-mcp AGENTS.md
Instructions for pvliesdonk/markdown-vault-mcp, covering markdown vault mcp, design, project structure, conventions and skills.
claude-mem-lite CLAUDE.md
Instructions for sdsrss/claude-mem-lite, covering claude-mem-lite, quick reference, health stack, architecture and where new code goes (audit 2026-08-22 p2-7).
AllBeads CLAUDE.md
Instructions for thrashr888/AllBeads, covering claude.md, project overview, what allbeads does, current state (v0.2.0) and rust development commands.
markdown-vault-mcp CLAUDE.md
Instructions for pvliesdonk/markdown-vault-mcp, a project described as: Generic markdown collection MCP server with FTS5 + semantic search, frontmatter-aware indexing, and incremental reindexing.
flow AGENTS.md
Instructions for cofin/flow: Flow is a toolkit for context-driven development. It has no flow executable; invoke the Flow skill or a /flow: command.
flow CLAUDE.md
Instructions for cofin/flow: Flow is a skill, not a CLI. In repositories with .agents/, invoke the Flow skill or a /flow: command.