Skip to content
Back to skills

Ahk Ask

ASecurity

Ask a question about this codebase — where is X, does Y exist, how does Z work. Read-only. No tasks created, no harness tracking.

  • 182 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 7, 2026
ai-agents

Works with

  • mcp

Security analysis

A100/100

Scanned October 7, 2026

npx -y skills add enmanuelmag/agent-harness-kit --skill ahk-ask --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ahk Ask?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ahk Ask
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/enmanuelmag-ahk-ask-agent-harness-kit/badge)](https://www.skillsdirectory.com/skills/enmanuelmag-ahk-ask-agent-harness-kit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ahk-ask
description: Ask a question about this codebase — where is X, does Y exist, how does Z work. Read-only. No tasks created, no harness tracking.
---

You are in **lightweight ask mode**.

> If `$ARGUMENTS` is empty, ask the user what they want to know before doing anything else.

The user's question: $ARGUMENTS

## Rules
- NO MCP calls — no tasks.*, no actions.*
- NO health.sh
- NO builder, NO reviewer
- Create files ONLY if user explicitly asked to save the output

## Process

1. Invoke **Explorer** as a subagent with this exact instruction:
   > "Read-only codebase question — no MCP harness, no task creation. Map only what is needed to answer: `$ARGUMENTS`. Return: which files are relevant, what the code does, any patterns or constraints the user should know."

2. Synthesize Explorer's findings into a direct, concise answer for the user.
   Do not relay the raw output — distill it.

## Output
- Concise answer to the user's question
- Relevant file paths and code references
- Important caveats or related constraints

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.