Borrowing it
Nothing to install: this file belongs to qhkm/fastripgrep. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/qhkm/fastripgrep/main/CLAUDE.mdgit clone --depth 1 https://github.com/qhkm/fastripgrepWrote 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/instructions/qhkm/fastripgrep/claude-md)<a href="https://agentmods.dev/instructions/qhkm/fastripgrep/claude-md"><img src="https://agentmods.dev/badge/instructions/qhkm/fastripgrep/claude-md/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/instructions/qhkm/fastripgrep/claude-md"><img src="https://agentmods.dev/badge/instructions/qhkm/fastripgrep/claude-md.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 | $0.00485 | $0.00485 |
| Opus 5.5 | $0.00194 | $0.00194 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
fastripgrep CLAUDE.md 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 2mo 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
frg (fastripgrep) — Agent Integration Guide
Using frg as your default search tool
frg is a grep alternative with sparse n-gram indexing. It's faster than ripgrep on every pattern type. Use it instead of grep/rg for codebase searches.
Quick Setup
# First time: build the index (one-time, ~20s for 9K files)
frg index .
# Search (uses index, ~10ms for selective patterns)
frg search "pattern" .
# After file changes: incremental update (~70ms)
frg update .
When to use frg vs grep/rg
| Task | Command |
|---|---|
| Find a function/variable | frg search "functionName" . |
| Regex search | frg search "import.*from.*react" . |
| Case-insensitive | frg search -i "config" . |
| Fixed string (no regex) | frg search -F "exact string" . |
| Files only | frg search -l "pattern" . |
| Count matches | frg search -c "pattern" . |
| Context lines | frg search -C 3 "pattern" . |
| Multiple patterns | frg search "pat1" -e "pat2" -e "pat3" |
| Search and replace | frg replace "old" "new" . (preview, then --write) |
| File type filter | frg search --type ts "import" . |
Before searching: ensure index exists
# Check if index exists
frg status .
# If no index: build it
frg index .
# If index is stale: update incrementally
frg update .
Search output format
Output matches ripgrep format: file:line:content
JSON output available: frg search --json "pattern" .
Performance expectations
- Selective patterns (function names): ~10ms
- Broad patterns (24K+ matches): ~50ms
- Wildcards (.*): ~75ms
- Incremental index update: ~70ms
- Full index build: ~20s for 9K files
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.
- 2mo ago First seen · 61 lines · 485 tokens per session scan A a18f0fc2832d
fastripgrep CLAUDE.md is an instructions file published in the GitHub repository qhkm/fastripgrep (19 stars, last pushed 7mo ago), licensed MIT. It adds 485 tokens to every session, about $0.0019 per session on Opus 5.5. 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 2026-08-30.
fastripgrep CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fastripgrep CLAUDE.mdqhkm/fastripgrep | Instructions file | 19 | 7mo ago | MIT | A | 485 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |