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 instructions/qhkm/fastripgrep/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.svg" alt="Measured on agentmods" 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 | $0.00485 | $0.00485 |
| Opus 5 | $0.00243 | $0.00243 |
| Sonnet 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 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.
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.
- 5d 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 (15 stars, last pushed 5mo ago), licensed MIT. It adds 485 tokens to every session, about $0.0024 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 2026-08-30.
Other instructions, from other repositories
ck CLAUDE.md
Claude Code instructions for BeaconBay/ck, covering claude development guide, release process, version tagging convention, correct format (current standard since 0.3.8+) and old format (deprecated, do not use).
maroto AGENTS.md
Instructions for johnfercher/maroto, covering agent instructions, skills, definition of done, contributing commands and tool dependencies.
mcp-read-website-fast CLAUDE.md
Claude Code instructions for just-every/mcp-read-website-fast, covering claude.md, project overview, core modules & files, commands and development.
mcp-screenshot-website-fast CLAUDE.md
Claude Code instructions for just-every/mcp-screenshot-website-fast, covering claude.md, project overview, core modules & files, commands and development.
renux AGENTS.md
AGENTS.md instructions for andrianllmm/renux, covering agents.md, layout, testing and tags registry is the source of truth.
claude-grep CLAUDE.md
Instructions for evoleinik/claude-grep, covering claude-grep, quick reference, build, architecture and key design decisions.