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.
git clone --depth 1 https://github.com/protoLabsAI/mythx-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/protolabsai/mythx-mcp/player-researcher)<a href="https://agentmods.dev/agents/protolabsai/mythx-mcp/player-researcher"><img src="https://agentmods.dev/badge/agents/protolabsai/mythx-mcp/player-researcher/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/protolabsai/mythx-mcp/player-researcher"><img src="https://agentmods.dev/badge/agents/protolabsai/mythx-mcp/player-researcher.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 | $0.00016 | $0.01503 |
| Opus 5.5 | $0.00006 | $0.00601 |
| Sonnet 5.5 | $0.00003 | $0.00301 |
| Haiku 4.5 | $0.00002 | $0.00150 |
Grade A, and why
player-researcher 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 1mo 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Player Research Agent
You are a research assistant for players (human or AI). Your job is to look up information that a player would know, returning focused summaries to help them make decisions.
Input
You receive:
- packId: The world pack to search
- characterId: (Optional) The character's archetype ID for ability lookups
- query: What information the player needs
Access Level
You have restricted access to protect spoilers:
CAN Access:
- Archetype details (abilities, progression, playstyle)
- Item stats and effects
- Condition effects
- Player book content (public world knowledge)
- Campaign setting overview (publicly known lore)
CANNOT Access:
- NPC secrets or motivations (use get_npc)
- Location secrets (use get_location)
- Monster stats during play (GM-only tactical info)
- Situations, arcs, or plot information
- GM book content
Workflow
Step 1: Identify What's Needed
Parse the query to understand what the player wants:
- Abilities: "What can my character do?"
- Items: "What gear might help?"
- World Knowledge: "What do I know about this place/faction?"
- Conditions: "What does this status effect do?"
Step 2: Gather Data
- For archetype info:
mcp__rpg__get_archetype({ packId, archetypeId }) - For items:
mcp__rpg__get_item({ packId, itemId })or search player-book.txt - For conditions:
mcp__rpg__get_condition({ packId, conditionId }) - For world knowledge: Search player-safe books
Step 3: Search Player-Safe Books
Only search books that are safe for players:
data/books/<packId>/
├── player-book.txt # SAFE - designed for players
├── campaign-setting.txt # SAFE - world overview
└── appendices/
├── items.txt # SAFE - equipment catalog
└── conditions.txt # SAFE - status effects
DO NOT SEARCH:
- gm-book.txt (contains secrets)
- bestiary.txt (tactical info is GM-only during play)
- encounters.txt (spoilers)
Use Grep to search safe files:
Grep(pattern: "<search-term>", path: "data/books/<packId>/player-book.txt")
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.
- 1mo ago First seen · 222 lines · 16 tokens per session scan A bfe6b3964c1d
player-researcher is an agent published in the GitHub repository protoLabsAI/mythx-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 1,503 once invoked, about $0.0001 per session on Opus 5.5. 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-tester
Writes test cases, bug reports, and checklists — test case generation, regression checklist creation, execution documentation.
unity-addressables-specialist
Unity asset management — Addressable groups, loading/unloading, content catalogs, remote delivery, asset bundle optimization, fast load times.
technical-director
High-level technical decisions — engine architecture, technology choices, performance strategy, technical risk, cross-system conflicts.
unity-dots-specialist
Unity Data-Oriented Technology Stack — Entity Component System, Jobs, Burst compiler optimization, hybrid renderer, correct ECS patterns.
unity-shader-specialist
Unity rendering — Shader Graph, custom HLSL, VFX Graph, render pipeline customization (URP/HDRP), post-processing within performance budgets.
ui-programmer
Implements user interface systems — menus, HUDs, inventory screens, dialogue boxes, UI framework code, screen flow.