agentmods.dev

bd-explore AGENTS.md

A project guide for AI agents working on bd-explore, a command-line tool and MCP server for searching Beads issue stores.

In plain words
What is it for?
Understanding the repository, finding relevant code, and running its Python unit tests.
Why use it?
It gives agents the project rules, architecture, test commands, and code locations they need before making changes.

Instructions file for CodexOpenCode

0 14d ago A scan 520 tokens original MIT
View the source file halaprix/bd-explore
Install

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.

agentmods
npx agentmods add instructions/halaprix/bd-explore/agents-md
Clone the repo
git clone --depth 1 https://github.com/halaprix/bd-explore

Made for: Codex, OpenCode.

Per session 520 This file is loaded in full into every session.
When invoked 520 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00520 $0.00520
Opus 5 $0.00260 $0.00260
Sonnet 5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured yesterday against content hash 1537e02bca71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bd-explore AGENTS.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.

AGENTS.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Agent Guide for bd-explore

Project Overview

bd-explore is a zero-dependency CLI tool and MCP server that provides fast, deep full-text and relational search across beads issue stores. It surfaces complete issue prose (descriptions, designs, notes, comments, close reasons, memories) and relational graphs (blocks, parent-child, mentions, GitHub issues).

Agent Guidelines & Rules

Testing Commands

All unit tests run via Python stdlib unittest:

# Run all tests
PYTHONPATH=src python3 -m unittest discover tests -v

# Run individual test files
PYTHONPATH=src python3 -m unittest tests/test_index.py
PYTHONPATH=src python3 -m unittest tests/test_search.py
PYTHONPATH=src python3 -m unittest tests/test_mcp.py
PYTHONPATH=src python3 -m unittest tests/test_installer.py
PYTHONPATH=src python3 -m unittest tests/test_cli.py

Architecture & Code Map

  • src/bd_explore/constants.py: Constants (VERSION, DEFAULT_BUDGET_CHARS, DEFAULT_SEEDS, DEP_KINDS, FILTER_KEYS).
  • src/bd_explore/index.py: Store resolution, SQLite FTS5 database management, mention mining, GitHub #NNN ref extraction, bd memories indexing, cache invalidation.
  • src/bd_explore/search.py: Query parser (filters + free text), BM25 ranking, 1-hop relationship neighborhoods, transitive blast radius calculations, character budget formatting.
  • src/bd_explore/mcp.py: Stdio JSON-RPC 2.0 MCP server exposing bd_explore.
  • src/bd_explore/cli.py: CLI dispatcher for search, serve, install, uninstall, print-config.
  • src/bd_explore/installer/: Multi-target platform configuration engine (Claude Code, Gemini CLI, Antigravity IDE, Codex, Cursor, AGENTS.md) and beads persistent memory injection.

Code Style Requirements

  • Zero runtime dependencies outside Python 3.10+ standard library.
  • Type annotations across all public functions and methods.
  • Atomic file writes for all configuration files.
  • Fenced marker tags (<!-- BD_EXPLORE_START --> / <!-- BD_EXPLORE_END -->) for agent rule injections.

Read the full file on GitHub · 40 lines

Changes

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.

  1. yesterday First seen · 40 lines · 520 tokens per session scan A 1537e02bca71

Subscribe to this mod's changes

bd-explore AGENTS.md is an instructions file published in the GitHub repository halaprix/bd-explore (0 stars, last pushed 14d ago), licensed MIT. It adds 520 tokens to every session, about $0.0026 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.

LanguagesResearchTestingai-agentsbeadsclifts5mcpmcp-server
Related

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.

pvliesdonk/markdown-vault-mcp · 7,054 tokens

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).

sdsrss/claude-mem-lite · 9,614 tokens

AllBeads CLAUDE.md

Instructions for thrashr888/AllBeads, covering claude.md, project overview, what allbeads does, current state (v0.2.0) and rust development commands.

thrashr888/AllBeads · 4,866 tokens

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.

pvliesdonk/markdown-vault-mcp · 43 tokens

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.

cofin/flow · 202 tokens

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.

cofin/flow · 131 tokens