search-code

A command for searching text, patterns, symbols, or ideas across a codebase through an MCP code index. A codebase is the complete collection of files in a software project.

In plain words
What is it for?
Use it to find functions, classes, imports, regular-expression matches, or code related to a broader concept, with optional result limits.
Why use it?
It helps locate relevant code without opening files one by one, while explaining when indexed results are unavailable and native search should be used.

Command for Claude Code

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 commands/consiliency/code-index-mcp/search-code
Clone the repo
git clone --depth 1 https://github.com/Consiliency/Code-Index-MCP

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 278 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00278
Opus 5 $0.00000 $0.00139
Sonnet 5 $0.00000 $0.00056
Haiku 4.5 $0.00000 $0.00028

Measured 2d ago against content hash 9e0f93cdff28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

search-code 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.

.claude/commands/search-code.md · 34 lines

What it actually says

Search Code Patterns

Search for code patterns, text, or concepts across the entire codebase using the MCP index. Use indexed results as authoritative only when repository readiness is ready. If search_code returns index_unavailable with safe_fallback: "native_search", use native rg/file search and follow the readiness remediation, such as reindex.

Usage

/search-code <pattern> [options]

Examples

  • /search-code "def process_.*" - Find all process functions
  • /search-code "class.*Plugin" - Find all plugin classes
  • /search-code "error handling" semantic - Semantic search for error handling patterns
  • /search-code "import torch" - Find all files importing torch

Options

  • semantic - Enable semantic search for concept queries
  • limit=N - Limit results (default: 10)

Implementation

This command uses mcp__code-index-mcp__search_code with these features:

  • Regular expression support
  • Semantic search with Voyage AI embeddings
  • Context snippets with highlighting
  • <500ms response time

Ready indexes return ordinary results: [] for no matches. Non-ready indexes return index_unavailable, where native_search is expected until remediation is complete.

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 · 34 lines · 0 tokens per session scan A 9e0f93cdff28

Subscribe to this mod's changes

search-code is a command published in the GitHub repository Consiliency/Code-Index-MCP (57 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 278 tokens. 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.