How do I install the Ax Grep CLI skill?

Run npx skillmds@latest add hmmhmmhm/ax-grep-cli in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ax Grep CLI safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ax Grep CLI?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ax Grep CLI free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ax Grep CLI?

hmmhmmhm (@hmmhmmhm) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ax Grep CLI by hmmhmmhm — Agent Skill

Name: Ax Grep CLI
Author: hmmhmmhm

Ax Grep CLI

Use ax-grep as a CLI-first page search and page-check tool before opening a browser. Best for agents that need compact semantic trees, source links, hidden app signals, forms, tables, citations, and browser handoff guidance.

hmmhmmhm 575fefb 2.5 KB Updated Sep 17, 2026

File contents

ax-grep CLI

Use ax-grep before browser automation when a subagent needs to inspect a search result, URL, HTML file, or captured page.

First Command

ax-grep "https://example.com" --agent

If ax-grep is not on PATH, use the npm executable:

npx --yes ax-grep@latest "https://example.com" --agent

For smaller context:

ax-grep "https://example.com" --agent-brief

Search

ax-grep --search "official docs pricing" --agent

Use the returned agent.*CommandArgs fields when continuing. They are JSON argv arrays in execution order. Use agent.*Command when you need a shell string.

Agent Policy

Prefer --agent or --agent-brief over raw text output for subagents.
Read agent.executor, agent.handoff, agent.next, agent.readTargets, and any returned agent.sourceChoices or agent.resultChoices before deciding.
If agent.executor.decision is return, answer from the referenced readFrom payload instead of opening a browser.
If a URL follow-up is needed, run the provided commandArgs one command at a time.
Escalate to browser automation only when needsBrowserHtml, needsBrowserInteraction, or the executor/handoff fields say it is needed.
Do not run multiple browser-backed checks in parallel.

Useful Patterns

Inspect a result and open the best match in one step:

ax-grep --search "site:example.com api reference" --open-result best --agent

If an engine rejects best, open the top ranked result directly:

ax-grep --search "site:example.com api reference" --open-result 1 --agent

Check a page for specific terms:

ax-grep "https://example.com/docs" --find "rate limit" --find "authentication" --agent

Read static HTML from another tool:

curl -fsSL "https://example.com" | ax-grep --stdin --agent

What ax-grep Sees

ax-grep --agent can expose:

semantic headings, landmarks, links, buttons, forms, tables, and lists
source-like links and ranked search choices
JSON-LD schema facts, metadata, policies, topics, provenance, and citations
hydration URLs, API endpoints, runtime hints, app config, and mobile hints
recommended next commands and browser handoff reasons

Treat the full JSON payload as source of truth; top-level shortcuts are for fast routing.

---name: ax-grep-clidescription: Use ax-grep as a CLI-first page search and page-check tool before opening a browser. Best for agents that need compact semantic trees, source links, hidden app signals, forms, tables, citations, and browser handoff guidance.---# ax-grep CLIUse `ax-grep` before browser automation when a subagent needs to inspect asearch result, URL, HTML file, or captured page.## First Command```shax-grep "https://example.com" --agent```If `ax-grep` is not on `PATH`, use the npm executable:```shnpx --yes ax-grep@latest "https://example.com" --agent```For smaller context:```shax-grep "https://example.com" --agent-brief```## Search```shax-grep --search "official docs pricing" --agent```Use the returned `agent.*CommandArgs` fields when continuing. They are JSON argvarrays in execution order. Use `agent.*Command` when you need a shell string.## Agent Policy- Prefer `--agent` or `--agent-brief` over raw text output for subagents.- Read `agent.executor`, `agent.handoff`, `agent.next`, `agent.readTargets`, and any returned `agent.sourceChoices` or `agent.resultChoices` before deciding.- If `agent.executor.decision` is `return`, answer from the referenced `readFrom` payload instead of opening a browser.- If a URL follow-up is needed, run the provided `commandArgs` one command at a time.- Escalate to browser automation only when `needsBrowserHtml`, `needsBrowserInteraction`, or the executor/handoff fields say it is needed.- Do not run multiple browser-backed checks in parallel.## Useful PatternsInspect a result and open the best match in one step:```shax-grep --search "site:example.com api reference" --open-result best --agent```If an engine rejects `best`, open the top ranked result directly:```shax-grep --search "site:example.com api reference" --open-result 1 --agent```Check a page for specific terms:```shax-grep "https://example.com/docs" --find "rate limit" --find "authentication" --agent```Read static HTML from another tool:```shcurl -fsSL "https://example.com" | ax-grep --stdin --agent```## What ax-grep Sees`ax-grep --agent` can expose:- semantic headings, landmarks, links, buttons, forms, tables, and lists- source-like links and ranked search choices- JSON-LD schema facts, metadata, policies, topics, provenance, and citations- hydration URLs, API endpoints, runtime hints, app config, and mobile hints- recommended next commands and browser handoff reasonsTreat the full JSON payload as source of truth; top-level shortcuts are forfast routing.

Frequently asked questions