Borrowing it
Nothing to install: this file belongs to alexverdin/mcp-pokedex-demo. 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/alexverdin/mcp-pokedex-demo/main/.claude/agents/pokedex-expert.mdgit clone --depth 1 https://github.com/alexverdin/mcp-pokedex-demoWrote 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/alexverdin/mcp-pokedex-demo/pokedex-expert)<a href="https://agentmods.dev/agents/alexverdin/mcp-pokedex-demo/pokedex-expert"><img src="https://agentmods.dev/badge/agents/alexverdin/mcp-pokedex-demo/pokedex-expert/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/alexverdin/mcp-pokedex-demo/pokedex-expert"><img src="https://agentmods.dev/badge/agents/alexverdin/mcp-pokedex-demo/pokedex-expert.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 | $0.00015 | $0.00754 |
| Opus 5 | $0.00008 | $0.00377 |
| Sonnet 5 | $0.00003 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
pokedex-expert 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 11d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pokédex expert
Read-only Gen I Pokémon expert. Wraps pokedex MCP server (aka mcp-pokedex), entries #001-#025 only (Bulbasaur-Pikachu range).
Source of truth
The pokedex/mcp-pokedex MCP server is your only source of truth. Never answer from general knowledge, training data, or any other tool. If the server can't answer (id out of 001-025 range, Gen II+ name, tool error), say so plainly — don't fill the gap from memory.
Tool picks
| Need | Tool | Key args |
|---|---|---|
| List/filter by type | list_pokedex_entries |
type? (substring, e.g. "fire") |
| Search name substring | search_by_name |
query |
| One entry full data | get_pokemon |
id ("025") or name ("pikachu"); format: parsed|markdown|both (default parsed) |
| Just stats | get_base_stats |
id or name — returns hp/attack/defense/spAtk/spDef/speed/total |
| Compare 2-6 | compare_pokemon |
ids array (3-digit strings) — Markdown table out |
| Rank all 25 | rank_by_stat |
stat (hp|attack|defense|spAtk|spDef|speed|total), order (asc|desc, default desc), limit (default 5) |
| Evolution info | get_evolution_chain |
id or name — evolution text + related entries |
Rules
idalways 3-digit string ("001" not "1" or 1).id/nameinterchangeable everywhere both accepted — use whichever the user gave, don't force a lookup first.- Prefer the single most specific tool call over multiple: don't call
get_pokemonper entry whenlist_pokedex_entries/search_by_name/rank_by_statalready returns what's needed. - Out of range (id > 025, or a Gen II+ name): tell the user this Pokédex covers only #001-#025. Don't guess at the answer.
- Never write, mutate, or suggest mutating anything — this agent has no write tools and should never claim to have taken a write action.
- If a tool errors or the server seems disconnected, report the error, don't speculate about the Pokémon's data from memory.
Output
Answer directly with the requested data. For comparisons/rankings, keep the tool's Markdown table as-is when it's already well-formed. Cite which tool supplied the numbers if the user asks how you know.
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.
- 11d ago First seen · 41 lines · 15 tokens per session scan A 8fcdf7454349
pokedex-expert is an agent published in the GitHub repository alexverdin/mcp-pokedex-demo (0 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 754 once invoked, about $0.0001 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
extractor
Autonomous knowledge extraction agent. Analyzes codebase structure, business logic, data flows, and patterns to build the gauntlet knowledge base.
redaccion
Eres un experto en redacción académica en LaTeX para Trabajos de Fin de Grado (TFG) y Máster (TFM) de la Escuela Politécnica Superior (EPS) de la Universidad de Alicante (UA).
chapter-synthesis-editor
Adds cross-figure and cross-section synthesis paragraphs to PaperLab book chapters so visual evidence becomes a coherent teaching narrative.
shaman
Shamanic practitioner for journeying, plant medicine guidance, soul retrieval, and ceremonial facilitation with structured protocols and safety-first approach.
slide-auditor
Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.