A code-search tool that builds an index of a project so text searches can return quickly. An index is a prepared lookup structure that avoids scanning every file from scratch.

For finding text across source files, limiting searches by file type, counting matches, viewing surrounding lines, and returning machine-readable search results.

It can make repeated searches faster in large codebases and can update its index as files change. It also offers filters, counts, context, and JSON output for agent use.

frg-search — Skill for Claude Code by qhkm

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.

Any agent

npx skills add qhkm/fastripgrep --skill frg-search

Clone the repo

git clone --depth 1 https://github.com/qhkm/fastripgrep

Made for: Claude Code.

Or install frg, the plugin that ships this one along with the rest of its 2 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/qhkm/fastripgrep/frg-search/github.svg)](https://agentmods.dev/skills/qhkm/fastripgrep/frg-search)

Your own site

<a href="https://agentmods.dev/skills/qhkm/fastripgrep/frg-search"><img src="https://agentmods.dev/badge/skills/qhkm/fastripgrep/frg-search/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/qhkm/fastripgrep/frg-search"><img src="https://agentmods.dev/badge/skills/qhkm/fastripgrep/frg-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 359 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.00359
Opus 5	$0.00008	$0.00179
Sonnet 5	$0.00003	$0.00072
Haiku 4.5	$0.00002	$0.00036

Measured 10d ago against content hash 596446c871a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

frg-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 10d 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.

skills/frg-search/SKILL.md · 42 lines

What it actually says

Use frg for code search. It indexes your codebase with sparse n-grams and searches in ~10ms instead of scanning every file.

Setup

If frg is not installed: cargo install fastripgrep

For agent mode (auto-index, JSON output, no noise): export FRG_AGENT=1

Commands

frg "pattern"                    # search current directory
frg "pattern" path               # search specific path
frg "pattern" . -i               # case-insensitive
frg "pattern" . -F               # fixed string (no regex)
frg "pattern" . -l               # files only
frg "pattern" . -c               # count per file
frg "pattern" . -C 3             # context lines
frg "pat1" . -e "pat2" -e "pat3" # multiple patterns (OR)
frg "pattern" . --type ts        # filter by file type
frg "pattern" . --json           # JSON output

Index Management

frg index .      # build index (one-time, ~20s)
frg update .     # incremental update (~70ms)
frg status .     # check index stats
frg watch .      # auto-update on file changes

When to Use

Use frg for all codebase searches when a .frg/ index exists
Use grep/rg for one-off searches on unfamiliar codebases
frg auto-indexes in agent mode (FRG_AGENT=1)

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.

10d ago First seen · 42 lines · 15 tokens per session scan A 596446c871a9

Subscribe to this mod's changes

frg-search is a skill published in the GitHub repository qhkm/fastripgrep (15 stars, last pushed 5mo ago), licensed MIT. It adds 15 tokens to every session and 359 once invoked, about $0.0001 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.

Productivity cli fast grep index ngram regex

frg-search

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Setup

Commands

Index Management

When to Use

What this file has done since we first saw it

Other skills, from other repositories

install

colgrep

gws-calendar

gws-gmail-reply

gws-gmail-send

gws-calendar-insert