Design, write, and run behavior-focused tests for an objective or existing code.

Apache-2.0Auto-check passed

Install Ahk Test

skills CLI
$ npx skills add enmanuelmag/agent-harness-kit --skill ahk-test -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install enmanuelmag/agent-harness-kit ahk-test --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/enmanuelmag/agent-harness-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ahk-test .claude/skills/ahk-test && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ahk-test
GitHub stars
182
Token cost
~1.1k tokens
SKILL.md length
594 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

Design, write, and run behavior-focused tests for an objective or existing code.

  • Works in 4 steps: Invoke Explorer as a subagent with this… → Build a concise test matrix with these… → Stop and ask the user before any write… → …
  • SKILL.md covers Provider Delegation Guidance, Rules, Process and Required output format
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ahk Test is an agent skill from enmanuelmag/agent-harness-kit. Design, write, and run behavior-focused tests for an objective or existing code. Writes test files only and reports evidence. No tasks created, no harness tracking.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with Model Context Protocol. The repository describes itself as: A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase. The licence is Apache-2.0.

Example prompts

  • “/ahk-test”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Invoke Explorer as a subagent with this instruction
  2. Build a concise test matrix with these columns
  3. Stop and ask the user before any write when the expected behavior is missing, contradictory, or would require a production or dependency…
  4. If the matrix is unambiguous, invoke Builder in direct test mode

What it can do on your machine

Read from SKILL.md and the folder at commit f8977b4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ahk Test loads about 1.1k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 594 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from enmanuelmag/agent-harness-kit at commit f8977b4, republished under its Apache-2.0 licence (© enmanuelmag). 594 words, ~1,084 tokens.

Download SKILL.mdSave it as .claude/skills/ahk-test/SKILL.md (or your agent's skills folder).
name
ahk-test
description
Design, write, and run behavior-focused tests for an objective or existing code. Writes test files only and reports evidence. No tasks created, no harness tracking.

Provider Delegation Guidance

  • Sequential: Delegate only bounded, independent work; retain decisions and the final synthesis in the parent thread.
  • Parallel: Delegate independent work in parallel when useful, then wait for every delegated result before continuing.
  • Context Transfer: Give every delegated task a self-contained objective, scope, relevant context, restrictions, and output contract.
  • Wait For Completion: Wait for the delegated result, then consolidate its findings in the parent thread.
  • Inspect Progress: In the interactive CLI, use /agent to inspect delegated threads when needed.

You are in lightweight test mode. The testing objective: $ARGUMENTS

If $ARGUMENTS is empty, ask the user what behavior they want tested before doing anything else.

Rules

  • NO MCP calls — no tasks., no actions., no tasks.acceptance.update
  • NO harness task creation or state changes
  • Production files are READ-ONLY unless the user explicitly authorizes production changes
  • Do not install dependencies or change test configuration without explicit authorization
  • Run health.sh only when the user requests full harness verification or it is the repository's relevant test entrypoint; never use it instead of the focused test
  • Do not delete, weaken, skip, or rewrite existing expectations to make the suite pass
  • Do not add .only, .skip, .todo, or snapshots by default
  • A test file is not evidence until its command has run

Process

  1. Invoke Explorer as a subagent with this instruction:

    "Read-only test investigation — no MCP harness and no task creation. Testing objective: $ARGUMENTS. Read the complete unit under test, its relevant types and imports, the project's test scripts/configuration, and one or two nearby tests. Identify: observable behaviors, the source of each expected result, project conventions, likely test level, files a test would touch, and genuine ambiguities. Do not write files."

  2. Build a concise test matrix with these columns:

    • Behavior
    • Input or action
    • Expected observable result
    • Test level
    • Source of expectation
  3. Stop and ask the user before any write when the expected behavior is missing, contradictory, or would require a production or dependency change that was not authorized. Do not invent an oracle from the current implementation.

  4. If the matrix is unambiguous, invoke Builder in direct test mode:

"Direct test implementation — no MCP harness and no task creation. Implement only the resolved test matrix. Follow the repository's existing runner, naming, and assertion style. Place every test file and every test-only fixture, builder, factory, mock, stub, snapshot, or helper inside the __tests__/ directory of the area under test. You may create or modify only the paths listed in the resolved scope. Do not edit production, dependencies, configuration, or unrelated tests. Prefer observable behavior over implementation details, real deterministic code over mocks, and one behavior per test. Return files changed and the focused command to run."

Show full SKILL.md (151 more words)Show less
  1. Invoke Reviewer in direct verification mode:

    "Direct test verification — no MCP harness, no task state changes, and no file edits. Review the new tests against the objective and matrix. Run the narrowest focused test command first, then the relevant existing suite or static check when proportional. Report every command with exit status, failures, and what the evidence does not prove."

  2. Synthesize the required output. Do not hide a failing test or convert it into a passing claim.

Required output format


Test matrix Behavior, input/action, expected result, level, and source.

Files changed Test files created or modified. State explicitly when no files were written.

Verification Commands run, exit status, and relevant result.

Evidence boundary What these tests prove and what still requires typecheck, build, browser, network, deployment, or manual verification.

Blocked or next step Omit when nothing remains. If production appears wrong, describe the separate change needed without making it.


© enmanuelmag, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/ahk-test of enmanuelmag/agent-harness-kit.

Open the folder on GitHubat commit f8977b4

Compare with similar skills

Ahk Test next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ahk Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ahk Test this skillenmanuelmag/agent-harness-kit182—~1.1kAutomated safety check: PassApache-2.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Figma use_figma Plugin API Ruleswarpdotdev/warp65k4 repos~4.4kAutomated safety check: PassAGPL-3.0
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills8.5k6 repos~3.2kAutomated safety check: NotesApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.

    65k GitHub starsUsed in 4 repos~4.4k tokens
    Frontend & DesignAuto-check passed
  • Stitch to Remotion Walkthrough Videos

    google-labs-code/stitch-skills

    Official

    Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.

    8.5k GitHub starsUsed in 6 repos~3.2k tokens
    Media & CreativeAuto-check: notes
  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed

More from enmanuelmag/agent-harness-kit

All 11 skills in this repo
  • Ahk Consultant

    enmanuelmag/agent-harness-kit

    Get technical advice or review on an approach, idea, or change.

    182 GitHub stars~563 tokensUpdated yesterday
    Auto-check passed
  • Ahk Review

    enmanuelmag/agent-harness-kit

    Preview a code review against ticket/objective alignment, with deep semantic (name-vs-behavior) analysis.

    182 GitHub stars~871 tokensUpdated yesterday
    Auto-check passed
  • Ahk Triage

    enmanuelmag/agent-harness-kit

    Triage a bug or unexpected behavior. An agent skill from enmanuelmag/agent-harness-kit.

    182 GitHub stars~569 tokensUpdated yesterday
    Auto-check passed
  • Ahk Ask

    enmanuelmag/agent-harness-kit

    Ask a question about this codebase — where is X, does Y exist, how does Z work.

    182 GitHub stars~415 tokensUpdated yesterday
    Auto-check passed
  • Ahk Docs

    enmanuelmag/agent-harness-kit

    Explain how to use and operate Agent Harness Kit= workflows, providers, MCP, health gates, and upgrades.

    182 GitHub stars~503 tokensUpdated yesterday
    Auto-check passed
  • Ahk Feature

    enmanuelmag/agent-harness-kit

    Turn an idea or Jira request into a reviewable, evidence-backed feature specification.

    182 GitHub stars~214 tokensUpdated yesterday
    Auto-check passed

Questions about Ahk Test

What does Ahk Test do?

Design, write, and run behavior-focused tests for an objective or existing code. Ahk Test is an agent skill from enmanuelmag/agent-harness-kit. Design, write, and run behavior-focused tests for an objective or existing code.

How do I install Ahk Test in Claude Code?

Run `npx skills add enmanuelmag/agent-harness-kit --skill ahk-test -a claude-code`. Or copy the skill folder (.agents/skills/ahk-test in enmanuelmag/agent-harness-kit) into .claude/skills/ahk-test in your project. Claude Code loads it when a task matches its description.

How do I install Ahk Test in Codex?

Run `npx skills add enmanuelmag/agent-harness-kit --skill ahk-test -a codex`. Or copy the skill folder (.agents/skills/ahk-test in enmanuelmag/agent-harness-kit) into .agents/skills/ahk-test in your project. Codex loads it when a task matches its description.

Can I use Ahk Test in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add enmanuelmag/agent-harness-kit --skill ahk-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ahk-test, .gemini/skills/ahk-test, .github/skills/ahk-test and .opencode/skills/ahk-test in your project.

What does Ahk Test need to run?

SKILL.md names no scripts, command-line tools or credentials: Ahk Test is instructions for the agent only.

Does Ahk Test access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ahk Test safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ahk Test use?

Ahk Test is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ahk Test use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ahk Test?

Skills that share tags, products or a category with Ahk Test: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ahk Test?

enmanuelmag (a GitHub user) maintains it in enmanuelmag/agent-harness-kit, which has 182 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 9, 2026.

Source: enmanuelmag/agent-harness-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.