agentmods.dev

shaft-skills

shaft-skills is a plugin for Claude Code from ShaftHQ/SHAFT_ENGINE. Its manifest loads nothing; the 30 skills it bundles cost 987 tokens per session together, scanned A, original, MIT.

A collection of SHAFT skills for planning, writing, running, and investigating automated tests across web, mobile, API, and database systems.

In plain words
What is it for?
Use it for test planning and authoring, accessibility checks, API and mobile testing, failure analysis, reporting, and change verification.
Why use it?
It brings common testing methods into one workflow, helping teams choose suitable locators, understand failures, and verify changes consistently.

Plugin for Claude Code

not rated 407 2d ago A scan tokens not measured original MIT
View the source file ShaftHQ/SHAFT_ENGINE shafthq.github.io
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.

Claude Code
/plugin marketplace add ShaftHQ/SHAFT_ENGINE
agentmods
npx agentmods add plugins/shafthq/shaft_engine/shaft-skills
Clone the repo
git clone --depth 1 https://github.com/ShaftHQ/SHAFT_ENGINE

Made for: Claude Code.

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.

agentmods badge for shaft-skills

README.md
[![agentmods](https://agentmods.dev/badge/plugins/shafthq/shaft_engine/shaft-skills.svg)](https://agentmods.dev/plugins/shafthq/shaft_engine/shaft-skills)
Your own site
<a href="https://agentmods.dev/plugins/shafthq/shaft_engine/shaft-skills"><img src="https://agentmods.dev/badge/plugins/shafthq/shaft_engine/shaft-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 30 skills cost 987 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

shaft-skills 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 2d 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.

.claude-plugin/marketplace.json#shaft-skills · 55 lines

What it actually says

{
  "author": {
    "name": "ShaftHQ"
  },
  "category": "testing",
  "description": "Official SHAFT agent skills: methodology router, locator strategy, test planning and authoring, MCP-driven recording, failure analysis, and change verification.",
  "homepage": "https://shafthq.github.io/docs/start/overview",
  "keywords": [
    "shaft",
    "test-automation",
    "selenium",
    "appium",
    "rest-assured",
    "java",
    "testng",
    "junit"
  ],
  "license": "MIT",
  "name": "shaft-skills",
  "repository": "https://github.com/ShaftHQ/SHAFT_ENGINE",
  "skills": [
    "./shaft-accessibility-testing",
    "./shaft-api-testing",
    "./shaft-assertions",
    "./shaft-automated-test-authoring",
    "./shaft-change-verification",
    "./shaft-cli",
    "./shaft-database-testing",
    "./shaft-defect-reporting",
    "./shaft-developer",
    "./shaft-execution-reporting",
    "./shaft-failure-analysis",
    "./shaft-flaky-test-analysis",
    "./shaft-fluent-api",
    "./shaft-guide-search",
    "./shaft-locator-design",
    "./shaft-mcp",
    "./shaft-mobile-actions",
    "./shaft-nonfunctional-test-design",
    "./shaft-page-objects",
    "./shaft-recording-codegen",
    "./shaft-requirements-analysis",
    "./shaft-stakeholder-reporting",
    "./shaft-test-case-design",
    "./shaft-test-data-design",
    "./shaft-test-environment",
    "./shaft-test-execution",
    "./shaft-test-monitoring",
    "./shaft-test-planning",
    "./shaft-test-recording",
    "./shaft-web-actions"
  ],
  "source": "./shaft-skills",
  "strict": false
}
Contents

What it installs

The manifest is a name and a version. 30 skills travel with it, and installing the plugin installs all of them — 987 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#shaft-skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 55 lines scan A f4b068582d30

Subscribe to this mod's changes

shaft-skills is a plugin published in the GitHub repository ShaftHQ/SHAFT_ENGINE (407 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.

DebuggingTestingautomationautomation-engineend-to-end-testingmcp-server
Related

Other plugins, from other repositories

secedgar-mcp-server

Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.

cyanheads/secedgar-mcp-server · not measured

safe-android-reverser

Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.

salingnh/android-reverse-engineering-mcp · not measured

claude-webcache

Cross-session WebFetch cache for Claude Code. WebFetches disappear after 15 minutes — claude-webcache makes them persist.

theYahia/claude-webcache · not measured

wikimoth

Deterministic, token-minimal memory for Claude Code: capture each session as a [[wikilink]] note (edges computed by code, not a model) and recall connected notes at boot.

juliangeymonat-jpg/wikimoth · not measured

youtube-outlier-research

YouTube outlier finder and competitor research. Ranks a channel's recent uploads and Shorts by how far each beat that channel's own baseline views, compares channels, and sweeps a niche for video ideas that already worked. Runs on your own free YouTube Data API key, unmetered.

AdesiaHQ/bangermap-integrations · not measured

linkedctl

LinkedIn API toolkit — MCP server and workflow guidance for Claude Code.

alexey-pelykh/linkedctl · not measured