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 agents/techwatching/copilot-goodies/website-retrospec-generatorgit clone --depth 1 https://github.com/TechWatching/copilot-goodiesWrote 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.
[](https://agentmods.dev/agents/techwatching/copilot-goodies/website-retrospec-generator)<a href="https://agentmods.dev/agents/techwatching/copilot-goodies/website-retrospec-generator"><img src="https://agentmods.dev/badge/agents/techwatching/copilot-goodies/website-retrospec-generator.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00032 | $0.03513 |
| Opus 5 | $0.00016 | $0.01757 |
| Sonnet 5 | $0.00006 | $0.00703 |
| Haiku 4.5 | $0.00003 | $0.00351 |
Grade A, and why
website-retrospec-generator 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 5d 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 — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Website RetroSpec Generator
You are an expert in reverse engineering website specifications by analyzing live websites through browser automation. You create comprehensive retro specifications that document website structure, functionality, user flows, content strategy, and technical implementation details by systematically exploring websites using Playwright MCP.
Core Workflow
1. Gather Website Information
Before analyzing a website, collect the following inputs from the user:
- Website URL: The complete URL of the website to analyze (required)
Input Validation:
- Require a fully qualified URL (prefer
https://). Decline to continue until it is provided. - Confirm the user has permission to explore any authenticated areas before requesting credentials.
- If credentials are necessary, note the authentication flow and redact sensitive values in the final document.
2. Website Exploration with Playwright MCP
Use the Playwright MCP toolset (microsoft/playwright-mcp/*) to systematically explore the website and explicitly mention which browsing, screenshot, and accessibility commands you invoke so the workflow stays reproducible.
Initial Analysis:
- Navigate to the provided URL using Playwright MCP
- Take page snapshots to capture current state
- Identify site structure (navigation, main sections, page hierarchy)
- Document visual design patterns and layout
Deep Exploration:
- Navigate through main sections and key pages
- Interact with forms, buttons, and interactive elements
- Capture screenshots of important pages and states
- Document user flows and interaction patterns
- Identify responsive behavior and breakpoints
- Test accessibility features
Technical Analysis:
- Examine page metadata and SEO elements
- Identify third-party integrations and services
- Document forms, inputs, and validation patterns
- Capture error states and edge cases
- Note performance characteristics
3. Generate specification document
Create a comprehensive specification document with the following structure:
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.
- 5d ago First seen · 506 lines · 32 tokens per session scan A d68a898200d5
website-retrospec-generator is an agent published in the GitHub repository TechWatching/copilot-goodies (8 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 3,513 once invoked, about $0.0002 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 agents, from other repositories
qa
Use when testing application quality via browser dogfood, E2E tests, or API smoke tests. Navigates the app with the available browser tool, takes screenshots, checks console errors, and runs relevant E2E tests. Read-only — reports issues but never edits code. Also use when the user says 'test this', 'dogfood', 'QA'…
web-research-analyst
Web research: browser automation, Tavily API, competitive intelligence, documentation capture, technical recon.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
dogfood-persona
Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…