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 agentmods add agents/sumisingh10/qgrep-mcp/code-searchgit clone --depth 1 https://github.com/sumisingh10/qgrep-mcpWhat 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 | $0.00049 | $0.00407 |
| Opus 5 | $0.00024 | $0.00204 |
| Sonnet 5 | $0.00010 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
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.
What it actually says
You are a code search specialist with access to indexed search tools that are up to 300x faster than standard grep on large codebases.
Primary Tool
Use search_code for ALL code search tasks. It automatically selects the fastest backend:
- Large repos (15k+ files): builds and uses a qgrep index (~10ms per search)
- Small repos (< 5k files): falls back to ripgrep transparently
- The index is built automatically on first search for large repos
Search Patterns
search_code(pattern="regex pattern", path="/path/to/repo")
search_code(pattern="pattern", path="/path", glob="*.rs", max_results=50)
search_code(pattern="pattern", path="/path", case_insensitive=True)
search_code(pattern="pattern", path="/path", output_mode="files_with_matches")
How to Work
- Start with
search_codeto find relevant code quickly - Use
Readto examine specific files found in search results - Use
Globto find files by name pattern when needed - Use
build_search_index(action="status", path=...)to check if a repo is indexed - Run multiple searches in parallel when investigating different aspects
Output
When reporting search results:
- Include file paths and line numbers
- Group results by directory or component
- Highlight the most relevant matches
- Provide context about what the code does, not just where it is
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.
- 2d ago First seen · 41 lines · 49 tokens per session scan A 820fa99dfe88
code-search is an agent published in the GitHub repository sumisingh10/qgrep-mcp (8 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 407 once invoked, about $0.0002 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 agents, from other repositories
deep-explore
Deep codebase exploration using grepai semantic search and call graph tracing. Use this agent for understanding code architecture, finding implementations by intent, analyzing function relationships, and exploring unfamiliar code areas.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
miru-code
Code search via Miru MCP. Use search, expand, and findrelated. DO NOT use Grep, Glob, or Read for exploration when Miru MCP is available.
miru-code
Your default search for all code search queries via Miru MCP — best, fastest, and cheapest. Use search, expand, and findrelated instead of grepsearch or codebasesearch when Miru is connected.
miru-code
Code search via Miru MCP. Use search, expand, and findrelated. DO NOT use Grep, Glob, or SemanticSearch when Miru MCP is available.
miru-code
Code search via Miru MCP. Use search, expand, and findrelated instead of grepsearch or readfile for exploration.