miru-code-search

A rule that makes Miru MCP the default tool for exploring how code works. Miru searches a codebase and returns small relevant code sections.

In plain words
What is it for?
Use it to answer conceptual questions about a codebase, expand truncated search results, and find similar code elsewhere.
Why use it?
It reduces broad file reads and keeps code exploration focused on the most relevant matches.

Cursor rule for Cursor

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 rules/takara-ai/miru-code/miru-code-search
Clone the repo
git clone --depth 1 https://github.com/takara-ai/miru-code

Made for: Cursor.

Per session 196 This file is loaded in full into every session.
When invoked 196 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 $0.00196 $0.00196
Opus 5 $0.00098 $0.00098
Sonnet 5 $0.00039 $0.00039
Haiku 4.5 $0.00020 $0.00020

Measured 2d ago against content hash d16c6188b48e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

miru-code-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 2d 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.

.cursor/rules/miru-code-search.mdc · 21 lines

What it actually says

DO NOT use Grep, Glob, SemanticSearch, or broad file reads to explore how code works when Miru MCP is available.

Search returns compact snippets (~±15 lines around the best match). When a hit has truncated: true, call expand with file_path and anchor_line (or start_line) instead of rereading the whole file.

Use Miru MCP tools:

  • search — one call per question; pass project root as repo
  • expand — more context in the same file when truncated: true
  • find_related — similar code in other files

Allowed native-tool exceptions:

  • exact literal lookups such as env vars or quoted strings
  • reading a file Miru already identified so it can be edited
  • searching outside the indexed repo
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. 2d ago First seen · 21 lines · 196 tokens per session scan A d16c6188b48e

Subscribe to this mod's changes

miru-code-search is a cursor rule published in the GitHub repository takara-ai/miru-code (10 stars, last pushed 11d ago), licensed MIT. It adds 196 tokens to every session, about $0.0010 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.