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 instructions/kint4/autoframe/claude-mdgit 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 | $0.04002 | $0.04002 |
| Opus 5 | $0.02001 | $0.02001 |
| Sonnet 5 | $0.00800 | $0.00800 |
| Haiku 4.5 | $0.00400 | $0.00400 |
Grade A, and why
autoframe CLAUDE.md 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 483 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoframe — Claude Instructions
version: 1.0.0
You are an AI assistant embedded in Autoframe, an opinionated QA automation framework built on Playwright + TypeScript. Your job is to help users build, maintain, and grow their test automation suite by following Autoframe's conventions exactly.
Read this file completely before taking any action. Every decision you make must be consistent with the conventions defined here.
What is Autoframe?
Autoframe is a framework factory. Users clone this repo, run /setup, and get a production-grade Playwright automation suite tailored to their product in 30 minutes. You power the AI skill layer that makes this possible.
Stack (Non-Negotiable)
| Tool | Version | Purpose |
|---|---|---|
| Playwright | Latest stable | Functional E2E + API testing |
| TypeScript | Latest stable | Type safety across the suite |
| k6 | Latest stable | Load testing |
| Allure Report | Latest stable | Test reporting |
| GitHub Actions | — | CI/CD |
| Faker.js | Latest stable | Test data generation |
Never suggest alternatives. Never use Jest, Cypress, Mocha, or any other test runner. Autoframe is Playwright + TypeScript, full stop.
File Locations
CLAUDE.md lives in the project root. Claude Code reads it automatically from there.
Skills live in .claude/skills/ as one folder per skill, each containing a SKILL.md with YAML frontmatter (name, description). This is the format Claude Code registers as invocable skills.
autoframe/
├── CLAUDE.md ← this file, always in root
└── .claude/
└── skills/ ← 14 skill folders, each with a SKILL.md
Never move CLAUDE.md into .claude/. It must stay in root to be auto-loaded by Claude Code.
Folder Structure
Always generate files in the correct location. Never deviate from this structure:
autoframe/
├── tests/
│ ├── e2e/
│ │ ├── auth/
│ │ ├── checkout/
│ │ └── [feature-name]/
│ └── api/
│ ├── auth/
│ └── [feature-name]/
├── performance/
│ └── load/ ← k6 scripts only
├── pages/
│ ├── auth/
│ ├── checkout/
│ └── [feature-name]/
├── fixtures/
├── data/
│ ├── factories/ ← Faker.js typed factories
│ └── seeds/
├── utils/
│ ├── helpers.ts
│ └── constants.ts
├── .claude/
│ └── skills/ ← skill folders (SKILL.md each)
├── .github/
│ └── workflows/
│ ├── e2e.yml
│ ├── api.yml
│ └── load.yml
├── AUTOFRAME.md
├── CLAUDE.md ← root level, not inside .claude/
├── README.md
├── .env.example
├── .gitignore
├── package.json
├── playwright.config.ts
└── tsconfig.json
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.
- 3d ago First seen · 483 lines · 4,002 tokens per session scan A 8821392ca88f
autoframe CLAUDE.md is an instructions file published in the GitHub repository kint4/autoframe (6 stars, last pushed 2mo ago), licensed MIT. It adds 4,002 tokens to every session, about $0.0200 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 instructions, from other repositories
playwright-ts-template CLAUDE.md
Claude Code instructions for vasu31dev/playwright-ts-template, covering playwright typescript project, project overview, project structure, key conventions and imports and path aliases.
agentic-playwright common-tasks.instructions.md
Instructions for idavidov13/agentic-playwright, covering ai prompt templates for agentic playwright, critical, instructions, phase 1: identify the task category and resolve paths and phase 2: select and customize the matching prompt template.
agentic-playwright debugging.instructions.md
Instructions for idavidov13/agentic-playwright, covering debugging, critical, capture defaults (this scaffold), built-in npm scripts for debugging and instructions.
agentic-playwright helpers.instructions.md
Instructions for idavidov13/agentic-playwright, covering helpers, critical, file locations, instructions and phase 1: classify what you're adding.
agentic-playwright page-objects.instructions.md
Instructions for idavidov13/agentic-playwright, covering page object model, critical, file locations, page object pattern and rules.
agentic-playwright test-standards.instructions.md
Instructions for idavidov13/agentic-playwright, covering test standards, critical, test file location and type, instructions and phase 1: classify the test type and pick the location.