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 skills add toaruR/mcp-server-bm25-code-search --skill bm25-searchgit clone --depth 1 https://github.com/toaruR/mcp-server-bm25-code-searchWrote 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/skills/toarur/mcp-server-bm25-code-search/bm25-search)<a href="https://agentmods.dev/skills/toarur/mcp-server-bm25-code-search/bm25-search"><img src="https://agentmods.dev/badge/skills/toarur/mcp-server-bm25-code-search/bm25-search/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/toarur/mcp-server-bm25-code-search/bm25-search"><img src="https://agentmods.dev/badge/skills/toarur/mcp-server-bm25-code-search/bm25-search.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00027 | $0.01074 |
| Opus 5 | $0.00014 | $0.00537 |
| Sonnet 5 | $0.00005 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
bm25-search 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 9d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BM25 Code Search Guidelines
When exploring the codebase, finding function implementations, or investigating features, use the search (BM25 Code Search) MCP tool.
Agent-Specific Execution (Claude Code)
Claude Code treats MCP tools as deferred tools. If the schema is not yet loaded in the current session:
- Load schema: Run
ToolSearchwith queryselect:mcp__bm25-code-search__search. - Execute search: Call
mcp__bm25-code-search__searchwith natural language keywords.
(Other agents like Cursor, Codex, and Antigravity can call the tool directly without ToolSearch).
When to Use BM25 Search
- Feature exploration: Searching for where a specific feature, API, or logic is implemented (e.g., "user authentication", "webhook retry handling").
- Symbol & identifier lookup: Searching for camelCase (
getUserProfile), PascalCase (UserAuthManager), or snake_case (session_token) names. - Multilingual documents: Searching Japanese or CJK technical comments and documentation.
Search Strategy
- Search first: Prioritize the
searchtool over brute-forcegreporglobto retrieve the most relevant code chunks within strict token limits. - Path boosting: File path matches are boosted 3.0x over body content, making it fast to locate files by name or directory structure.
- Query formulation: Pass descriptive keywords (e.g.,
"user profile authentication"or"process_payment error") rather than complex regex. - Fallback: See the Re-Search Loop section below for the full retry/fallback sequence, or when exact substring/regex matches across all lines are strictly required, fall back to
grep_searchorglobimmediately.
Multi-Query Fan-Out (queries)
When a single query risks missing relevant chunks due to vocabulary mismatch (e.g. the code may say "auth" while you searched "login"), pass paraphrased alternatives in the optional queries array (up to 5) alongside query. The server searches every variant, merges them into one ranked list via Reciprocal Rank Fusion (RRF), and returns a single response — this avoids spending a full extra round trip per rephrasing.
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.
- 9d ago First seen · 63 lines · 27 tokens per session scan A a7b7f65c986a
bm25-search is a skill published in the GitHub repository toaruR/mcp-server-bm25-code-search (0 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 1,074 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…