rg · Andrew Gallant

ripgrep for AI Agents

Search source trees quickly with stable JSON, glob, type, and context controls.

Official toolOperational risk: R0–R0verified

Install for an Agent Report broken data

Agent readiness

83/100

Evidence confidence

verified

Documentation checked

2026-07-10

Independently tested version

15.1.0

Install for an Agent

Choose an official installation path that matches the runtime. Pin a version for team or CI use, then record the version before the first task.

HomebrewRecommended

macos · linux

$ shell

brew install ripgrep

winget

windows

$ shell

winget install BurntSushi.ripgrep.MSVC

Authentication and Minimum Permissions

Grant only the permissions the task needs. Pass credentials through environment variables or a platform secret store, never through prompts, repositories, or logs.

No authentication requiredHeadless authentication supported

No service credential is required; restrict filesystem and network access to the task.

Methods: none
Secret environment variables: None
Credential storage: No service credential is stored for this CLI.

Agent and Environment Compatibility

Confirm shell access first, then check the platform, network boundary, and credential path.

claude-codecodexgemini-clicopilot-cli

Environments: local, ci, container, headless, remote
Platforms: macos, linux, windows

Structured Output for Reliable Automation

Prefer a machine-readable format. Treat stdout as the result channel and stderr as diagnostics so the agent can parse failures separately.

json · text · null-delimited paths

Use --json or --null where supported and keep diagnostic logs on stderr.

--json--null

Independently captured output sample

15.1.0 · macOS 26.5.1 (arm64), local non-interactive shell

Executed command

rg --json '"name"' package.json | jq -c 'select(.type == "match")'

Captured stdout · ndjson match event

{"type":"match","data":{"path":{"text":"package.json"},"lines":{"text":"  \"name\": \"clifinder-net\",\n"},"line_number":2,"absolute_offset":2,"submatches":[{"match":{"text":"\"name\""},"start":2,"end":8}]}}

Sample JSON Schema

{
  "type": "object",
  "required": [
    "type",
    "data"
  ],
  "properties": {
    "type": {
      "const": "match"
    },
    "data": {
      "type": "object",
      "required": [
        "path",
        "lines",
        "line_number",
        "submatches"
      ],
      "properties": {
        "path": {
          "type": "object"
        },
        "lines": {
          "type": "object"
        },
        "line_number": {
          "type": "integer"
        },
        "absolute_offset": {
          "type": "integer"
        },
        "submatches": {
          "type": "array"
        }
      }
    }
  }
}

R0–R3 Command Risk Guide

Risk is assigned per command. R0 is local or remote read-only, R1 is reversible local write, R2 changes remote state, and R3 can be irreversible or production-impacting.

Read-only does not mean public

R0 only means the command does not change local or remote state. A read-only command may still return secrets, identity data, configuration, or production data. Expose only the minimum needed for the task, and never place it in logs, prompts, or commits.

R0Search with JSON events

Searches a bounded directory and emits one JSON event per line.

$ shell

rg --json --glob "*.ts" "pattern" src

IdempotentSensitive output

R0List searchable files

Lists files while respecting ignore rules.

$ shell

rg --files --null src

Idempotent

How the Agent Readiness Score Is Built

Readiness describes how reliably an agent can operate the tool. It does not make every command safe and it does not replace an independent execution test.

Documentation indicates an agent-readiness score of 83/100. A bounded local smoke test is recorded for 15.1.0; review its limitations before relying on untested commands.

Structured output

Use --json or --null where supported and keep diagnostic logs on stderr.

18/20

Headless operation

Official documentation describes a non-interactive authentication or execution path.

14/15

Safety controls

CLI Finder separates read commands from commands that require confirmation.

8/15

Determinism

Commands use explicit arguments and documented output controls where available.

8/10

Authentication

No service credential is required; restrict filesystem and network access to the task.

10/10

Documentation

This entry cites official documentation checked on 2026-07-10.

9/10

Installation

Official installation paths cover macOS, Linux, and Windows.

8/8

Maintenance

An official source repository is linked for release and maintenance review.

6/7

Agent artifacts

CLI Finder can generate registry-derived skills and policies; the tool itself was not credited with shipping them.

2/5

Generate a Skill or Agent Policy

Choose an agent and safety mode to generate a copyable artifact with installation, allowed commands, approval boundaries, and the evidence limitation.

Artifact typeTarget agentSafety mode

Generated artifact preview

SKILL.md

---
name: ripgrep-agent-workflow
description: Use ripgrep for source search, pattern discovery, file type filtering with explicit command risk and evidence boundaries.
---

# ripgrep agent workflow

Use this skill when the task needs source search, pattern discovery, file type filtering, machine-readable matches.

## Evidence boundary

- Registry confidence: `verified`
- Documentation checked: `2026-07-10`
- Locally tested version: `15.1.0`
- Treat only the recorded executed checks as independently verified; every unlisted command remains documentation-only.

## Executed smoke checks

- `rg --version` — passed; exit 0. The recorded smoke check completed successfully.
- `rg --json --glob '*.ts' 'createFileRoute' src/routes` — passed; exit 0. The recorded smoke check completed successfully.
- `rg --json '"name"' package.json | jq -c 'select(.type == "match")'` — passed; exit 0. The NDJSON stream was reduced to the recorded match event without changing its payload.
- `rg --json 'definitely-no-clifinder-match' package.json` — expected-failure; exit 1. ripgrep returned its documented no-match exit status without writing diagnostics to stderr.

## Installation

- Homebrew (macos, linux): `brew install ripgrep`
- winget (windows): `winget install BurntSushi.ripgrep.MSVC`

## Authentication

- Methods: none
- Secret environment variables: none
- Minimum permissions: No service credential is required; restrict filesystem and network access to the task.
- Credential storage: No service credential is stored for this CLI.
- Never print, persist, or commit credential values.

## Allowed commands (read-only)

- `rg --json --glob "*.ts" "pattern" src` — R0: Searches a bounded directory and emits one JSON event per line.
- `rg --files --null src` — R0: Lists files while respecting ignore rules.

## Commands requiring explicit approval (read-only)

- None recorded.

## Forbidden commands (read-only)

- None recorded.

## Execution rules

1. Mode boundary: R0 exact commands may be used; R1, R2, and R3 commands are forbidden.
2. Confirm the selected account, project, context, database, namespace, or environment before any command.
3. Prefer structured output using `--json`, `--null`.
4. Capture the exact command, exit code, stdout, and stderr separately.
5. A generated prefix policy must prompt unless that exact prefix is explicitly marked suffix-safe; do not infer safety from the executable name.
6. Never broaden credentials or disable safety controls to make a command succeed.

## Official sources

- [ripgrep guide](https://github.com/BurntSushi/ripgrep/blob/master/GUIDE.md)
- [ripgrep guide source repository](https://github.com/BurntSushi/ripgrep)

CLI vs MCP vs API for This Task

CLI

Use the CLI on a developer machine, in CI, or in a container when the task should reuse existing shell state, credentials, and scripts and remain directly observable.

MCP

Consider MCP when the agent benefits from controlled tool definitions, delegated identity, or centrally governed server-side access.

API

Use the direct API for persistent application integrations, high-volume requests, or event-driven work where starting a process adds unnecessary overhead.

Read the full CLI vs MCP guide

Verification History and Official Evidence

CLI Finder records documentation review separately from real execution. Installation, help, exit codes, and output cannot be called Verified until they were run.

Current evidence boundary

Version output, repository search, NDJSON event output, one extracted match event, and the no-match exit path were executed locally. Installation paths, other platforms, binary files, encoding edge cases, and out-of-scope directories were not tested.

Evidence confidence: verified
Independently tested version: 15.1.0 · 2026-07-10
Test environment: macOS 26.5.1 (arm64), local non-interactive shell

Executed checks

PassedExit code: 0
rg --version
The recorded smoke check completed successfully.
stdout excerpt
ripgrep 15.1.0
PassedExit code: 0
rg --json --glob '*.ts' 'createFileRoute' src/routes
The recorded smoke check completed successfully.
PassedExit code: 0
rg --json '"name"' package.json | jq -c 'select(.type == "match")'
The NDJSON stream was reduced to the recorded match event without changing its payload.
Expected failure pathExit code: 1
rg --json 'definitely-no-clifinder-match' package.json
ripgrep returned its documented no-match exit status without writing diagnostics to stderr.