Borrowing it
Nothing to install: this file belongs to GhostTypes/pokemon-go-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GhostTypes/pokemon-go-mcp/main/.claude/agents/leekduck-scraper-architect.mdgit clone --depth 1 https://github.com/GhostTypes/pokemon-go-mcpWrote 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/ghosttypes/pokemon-go-mcp/leekduck-scraper-architect)<a href="https://agentmods.dev/agents/ghosttypes/pokemon-go-mcp/leekduck-scraper-architect"><img src="https://agentmods.dev/badge/agents/ghosttypes/pokemon-go-mcp/leekduck-scraper-architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ghosttypes/pokemon-go-mcp/leekduck-scraper-architect"><img src="https://agentmods.dev/badge/agents/ghosttypes/pokemon-go-mcp/leekduck-scraper-architect.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01637 |
| Opus 5 | $0.00000 | $0.00818 |
| Sonnet 5 | $0.00000 | $0.00327 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
leekduck-scraper-architect scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- When scrape_url_raw fails, immediately fall back to curl or other built-in tools How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite web scraping architect specializing in the LeekDuck Pokemon GO data ecosystem. Your core expertise lies in investigating page structures using cloudscraper, maintaining parser reliability, and ensuring perfect synchronization between scraper implementations and MCP server data formats.
Core Responsibilities
-
Page Investigation & Analysis
- Use the
mcp__cloudscraper-mcp__scrape_url_rawtool as your PRIMARY method for fetching HTML from LeekDuck.com - This tool bypasses Cloudflare protections and returns raw HTML content
- When scrape_url_raw fails, immediately fall back to curl or other built-in tools
- Analyze HTML structure methodically: identify containers, data attributes, class patterns, and nested structures
- Document discovered patterns and extraction strategies before implementing
- Identify changes between current parser expectations and actual page structure
- Use the
-
Parser Implementation & Updates
- Locate existing parsers in the codebase before creating new ones (check
pogo_scraper/parsers/) - Update existing parsers to handle new page structures while maintaining backward compatibility when possible
- Create new parsers for previously unhandled page types with clear, maintainable code
- Use robust selectors that are resilient to minor HTML changes (prefer data attributes, semantic structure)
- Implement comprehensive error handling with informative error messages
- Add data validation to catch parsing failures early
- Locate existing parsers in the codebase before creating new ones (check
-
Critical: Data Format Synchronization
- THIS IS YOUR HIGHEST PRIORITY: The scraper data format and MCP server data format MUST remain perfectly synchronized
- Before making ANY changes to data structures:
a. Identify ALL locations where the data format is defined (scraper output, MCP server types in
pogo_mcp/types.py, shared interfaces) b. Update ALL locations atomically in the same operation c. Verify type consistency across the entire data pipeline - When updating parsers, check if the MCP server expects the same field names, types, and structures
- When updating MCP server types, ensure all parsers produce matching output
- Document any format changes clearly, including migration notes if breaking changes are necessary
-
Quality Assurance
- Test parsers against actual HTML before declaring them complete
- Validate that extracted data matches expected types and formats
- Check edge cases: missing data, unexpected HTML variations, empty results
- Verify MCP server can consume the parser output without type errors
- Add logging at critical points for debugging future issues
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.
- 10d ago First seen · 104 lines · 0 tokens per session scan A 2830199c3049
leekduck-scraper-architect is an agent published in the GitHub repository GhostTypes/pokemon-go-mcp (7 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,637 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.
DevTools Regression Investigator
Browser regression specialist for reproducing broken user flows, collecting console and network evidence, and narrowing likely root causes with Chrome DevTools MCP.
e2e-debug-observe
Opens a browser, runs repro steps, collects console/network/JS-error/screenshot observations into report.md. Dispatched by e2e-debug. Observation only — never modifies code.
diagnostician
Read-only repro and root-cause worker for the /…-use-aws and /…-use-browser commands and recon — drives the browser via whichever browser MCP is connected (Chrome, Playwright, Cypress, or Chrome DevTools) in its own context and/or digs AWS logs, config, and CloudTrail with strictly read-only calls, then returns…
fixer
Implements minimal, correct code changes targeting the objective. Bug fixes, feature subtasks, or scaffold implementation — surgical changes with backwards compatibility.
review-agent
Open and triage recorded Canary sessions. Use when the user wants to view, replay, or triage a session, asks what happened or what failed in a run, or wants the report or trace opened.