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.
npx agentmods add skills/kint4/autoframe/setupnpx skills add kint4/autoframe --skill setupgit clone --depth 1 https://github.com/kint4/autoframeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00055 | $0.00663 |
| Opus 5 | $0.00028 | $0.00331 |
| Sonnet 5 | $0.00011 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
setup 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup — Bootstrap the Autoframe Project
Type: Setup Description: Bootstraps the entire Autoframe framework for a specific product. Asks for the app URL, auth type, stack details, and CI platform, then produces a fully wired, ready-to-run Playwright project. Includes a simple mode for non-technical users.
Input Format
The user runs /setup. Gather the following before generating anything:
- App URL — the base URL of the product under test (
BASE_URL) - API URL — base URL for API tests, if any (
API_URL) - Auth type — none / form login / token / SSO
- First feature to cover — e.g.
auth,checkout - CI platform — defaults to GitHub Actions
If the user signals they are non-technical (Persona 1 or 4), switch to simple mode: ask only for the app URL and what they want to test first, and explain each step in plain language.
Output Format
A fully scaffolded project that matches the folder structure in CLAUDE.md, with:
playwright.config.ts,tsconfig.json,package.json.env.examplepopulated with the discovered variables.gitignore- The three GitHub Actions workflows (
e2e.yml,api.yml,load.yml) - One starter Page Object, spec, and fixture for the first feature
- A short summary of what was created and how to run it
Step-by-Step Instructions
- Read
CLAUDE.mdandAUTOFRAME.mdcompletely. - Detect the persona from the user's language (see CLAUDE.md). Adjust tone and depth.
- Ask the clarifying questions above (max 3 at a time). In simple mode, ask the minimum.
- Verify the folder structure exists; create any missing directories exactly as defined in CLAUDE.md.
- Generate or confirm the baseline config files. Never substitute the stack.
- Write
.env.examplewith every required variable (BASE_URL,API_URL,API_TOKEN,TEST_USER_EMAIL,TEST_USER_PASSWORD). Never write a real.env. - Generate a starter Page Object + spec + fixture for the first feature, following the POM and spec conventions exactly.
- Confirm the three CI workflows exist.
- Summarize what was created and give the exact commands to install and run (
npm install,npx playwright install,npm test). - Suggest the next skill to run (usually
/new-pageor/tc-to-spec).
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.
- yesterday First seen · 53 lines · 0 tokens per session scan A a46702eef43d
setup is a skill published in the GitHub repository kint4/autoframe (6 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 663 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
tokenless
Use when a task can be delegated through the globally installed Tokenless CLI without directly writing to the workspace; route it to a visible AI provider website to save agent tokens.
tokenless-install
Install, upgrade, repair, and verify Tokenless, its agent skills, and local Playwright runtime. Use only when the user explicitly asks for installation, upgrade, repair, browser sign-in handoff, a failed doctor check, or an installation integrity check.
agent-qa-authoring
Use when creating, editing, validating, or running agent-qa tests, suites, or hooks. Prefer agent-qa MCP tools, enforce canonical agent-qa IDs, and use the bundled schema reference to avoid hallucinated config keys or YAML fields.
agent-qa-debug-fix
Use after an agent-qa run has failed and you need to debug, patch, and verify the issue using MCP evidence, logs, artifacts, and local code changes instead of generated fix suggestions.
linggan-talking-cards
将中文或英文口播文案与可选截图拆成 3–10 张 PPT 式演示卡片，输出文字准确的 PNG 卡片、结构化 manifest 和带逐卡口播台词的响应式 HTML 预览页。支持 3:4、16:9、9:16、4:3 四种比例，以及苹果白色毛玻璃、糖果、Obsidian、新丑风等 10 种视觉系统；适用于“口播文案拆解PPT生多图”“把逐字稿做成卡片”“给口播配 slides”“截图放进讲解卡片”“生成多图和预览页”“换一种 PPT 风格”以及修改指定卡片的请求。.
k6-load-testing
Comprehensive k6 load testing skill for API, browser, and scalability testing. Write realistic load scenarios, analyze results, and integrate with CI/CD.