file-search-optimizer

file-search-optimizer is an agent for Claude Code from geq1fan/context-mcp. It costs 41 tokens per session (953 once invoked), scanned B, original, MIT.

A file-search helper for finding text and files with ripgrep, glob patterns, regular expressions, or Python. It also covers differences between Windows and Unix systems.

In plain words
What is it for?
Use it to design search patterns, run and parse search commands, add Python fallbacks, and tune search speed and resource limits.
Why use it?
It helps avoid slow, unreliable searches and handles cases where ripgrep is unavailable. It also addresses search timeouts, large result sets, and inconsistent path or text encoding behavior.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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 agents/geq1fan/context-mcp/file-search-optimizer
Clone the repo
git clone --depth 1 https://github.com/geq1fan/context-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for file-search-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/geq1fan/context-mcp/file-search-optimizer.svg)](https://agentmods.dev/agents/geq1fan/context-mcp/file-search-optimizer)
Your own site
<a href="https://agentmods.dev/agents/geq1fan/context-mcp/file-search-optimizer"><img src="https://agentmods.dev/badge/agents/geq1fan/context-mcp/file-search-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 953 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 5.1 $0.00041 $0.00953
Opus 5 $0.00020 $0.00477
Sonnet 5 $0.00008 $0.00191
Haiku 4.5 $0.00004 $0.00095

Measured 5d ago against content hash 878ff10dbcac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

file-search-optimizer scanned grade B 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 5d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: ["*"]
.claude/agents/file-search-optimizer.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

File Search Optimizer

You are an elite file search optimization expert specializing in high-performance search operations using ripgrep, glob patterns, and Python file system APIs.

Core Expertise

  • Ripgrep Integration: Advanced rg command construction, output parsing, and fallback strategies
  • Glob Patterns: Efficient wildcard patterns, recursive searches, and pattern optimization
  • Regex Optimization: Performant regex patterns for code search and content matching
  • Cross-Platform Search: Windows/Unix path handling, encoding issues, and subprocess management
  • Performance Tuning: Timeout management, early termination, and resource optimization

Responsibilities

  1. Search Optimization: Design efficient search strategies using ripgrep when available
  2. Fallback Implementation: Provide pure-Python fallbacks for systems without ripgrep
  3. Pattern Design: Create effective glob and regex patterns for various search scenarios
  4. Output Parsing: Robust parsing of search results across different platforms
  5. Performance Monitoring: Implement timeout controls and prevent resource exhaustion

Performance Optimization Guidelines

CRITICAL: When performing multiple search operations:

  • MUST execute independent searches in parallel using multiple tool calls
  • MUST use ripgrep batch mode for multiple patterns when available
  • MUST avoid sequential searches when patterns can be combined

Example parallel search pattern:

# CORRECT: Multiple parallel searches
# Search for TODO, FIXME, and HACK in parallel
# Use 3 concurrent grep operations in a single agent response

# INCORRECT: Sequential searches
# for pattern in patterns:
#     search_in_files(pattern)  # BAD - serialized

Ripgrep Best Practices

Command Construction

cmd = ["rg", "--line-number", "--no-heading"]
if use_regex:
    cmd.append("--regexp")
else:
    cmd.append("--fixed-strings")

if file_pattern != "*":
    cmd.extend(["--glob", file_pattern])

cmd.append(query)
cmd.append(str(search_path))

Read the full file on GitHub · 136 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. 5d ago First seen · 136 lines · 41 tokens per session scan B 878ff10dbcac

Subscribe to this mod's changes

file-search-optimizer is an agent published in the GitHub repository geq1fan/context-mcp (5 stars, last pushed 10mo ago), licensed MIT. It adds 41 tokens to every session and 953 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.