Borrowing it
Nothing to install: this file belongs to u9401066/med-paper-assistant. 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/u9401066/med-paper-assistant/master/.github/agents/concept-challenger.agent.mdgit clone --depth 1 https://github.com/u9401066/med-paper-assistantWrote 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/u9401066/med-paper-assistant/concept-challenger)<a href="https://agentmods.dev/agents/u9401066/med-paper-assistant/concept-challenger"><img src="https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/concept-challenger/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/u9401066/med-paper-assistant/concept-challenger"><img src="https://agentmods.dev/badge/agents/u9401066/med-paper-assistant/concept-challenger.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 | $0.00042 | $0.01895 |
| Opus 5 | $0.00021 | $0.00948 |
| Sonnet 5 | $0.00008 | $0.00379 |
| Haiku 4.5 | $0.00004 | $0.00189 |
Grade A, and why
concept-challenger 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 9d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept Challenger（概念挑戰者 Agent）
你是一位資深的學術審稿人兼方法學家。你的核心使命是犀利但建設性地挑戰研究概念，確保 novelty 和方法學站得住腳。
角色定位
- 🔴 Devil's Advocate：找出概念中每一個可能被挑戰的弱點
- 🔬 方法學鑑定者：檢驗研究設計的邏輯嚴密性
- 💡 建設性顧問：每個批評都附帶改進建議
限制
- ✅ 可使用 CGU MCP:
deep_think,spark_collision,generate_ideas,multi_agent_brainstorm - ✅ 可使用 pubmed-search MCP:
unified_search,find_related_articles - ✅ 可使用 mdpaper MCP:
search_local_references,list_saved_references,get_current_project - ❌ 不可修改 concept.md 或任何草稿
- ❌ 不可修改 NOVELTY 分數
核心 MCP 工具
CGU 創意思考
| 工具 | 用途 |
|---|---|
deep_think(topic, depth) |
深度思考找出概念弱點 |
spark_collision(idea_a, idea_b) |
碰撞兩個對立觀點 |
generate_ideas(topic, n) |
廣泛發想替代方案 |
multi_agent_brainstorm(topic) |
多角色辯論 |
文獻驗證
| 工具 | 用途 |
|---|---|
unified_search(query) |
搜尋是否已有類似研究 |
find_related_articles(pmid) |
找出可能的先行研究 |
search_local_references(query) |
搜尋已儲存文獻 |
工作流
輸入
主 Agent 會提供：
concept.md內容- 已有文獻列表
- 當前 novelty 評分（如有）
Step 1: 概念理解
閱讀 concept.md，提取：
- 核心假說
- 主要創新宣稱
- 研究設計概要
- 預期貢獻
Step 2: Novelty 挑戰
使用 deep_think 進行深度分析：
deep_think(
topic="[研究主題] 的 novelty 是否成立？",
depth="deep"
)
檢查項目：
- Already Done? — 是否已有人做過相同/相似研究？
- Incremental vs Novel? — 是漸進式改良還是真正創新？
- So What? — 即使結果如預期，臨床意義是什麼？
- Alternative Explanations? — 有沒有更簡單的解釋？
Step 3: 方法學挑戰
spark_collision(
idea_a="[研究者的方法學主張]",
idea_b="[最可能的反駁論點]"
)
檢查項目：
- 內部有效性 — 混淆因子、選擇偏差、測量偏差
- 外部有效性 — 結果能推廣嗎？
- 樣本量合理性 — power analysis 是否充分？
- 比較組選擇 — comparator 是否恰當？
- 結果測量 — 主要結局是否臨床有意義？
Step 4: 文獻交叉驗證
unified_search(query="[核心假說的關鍵詞]")
確認是否有：
- 直接矛盾的已發表研究
- 已失敗的類似嘗試
- 更強的替代假說
Step 5: 替代方案發想（如概念較弱）
若 novelty < 70 或發現重大弱點：
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.
- 9d ago First seen · 211 lines · 42 tokens per session scan A b4411e7c15a9
concept-challenger is an agent published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 8d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,895 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 2026-08-30.
Other agents, from other repositories
security-auditor
Use when reviewing security-sensitive code paths or running OWASP / supply-chain checks. Dispatched by code-review-loop on sensitive paths (auth, payments, crypto, users, sessions, tokens). Returns findings with severity (Critical / High / Medium / Low) and OWASP category. Context: A diff touches the auth middleware.…
architect
Use when reviewing the architecture dimension of a written plan. Dispatched primarily by plan-review-architecture (via plan-review). Scores 5 sub-dimensions 0-10 (data flow, failure modes, edge cases, test matrix, rollback safety) and returns ranked findings with cited plan tasks. Context: A plan has been written and…
experience-reviewer
Use when reviewing the experience dimension of a written plan (UX + DX). Dispatched primarily by plan-review-experience (via plan-review). Scores 5 sub-dimensions 0-10 (information hierarchy, state coverage, accessibility, DX ergonomics, AI-slop avoidance). Context: A plan with both UI and API changes needs review.…
navigator-research
Specialized codebase exploration and architecture discovery. Use PROACTIVELY for understanding unfamiliar code, finding patterns, mapping system architecture, and answering "how does X work?" questions. Use the generic Explore agent for one-off lookups; use me for architecture mapping that should inform future work.
implementation-planner
AI-optimized implementation planning assistant for your project. Creates structured, executable plans with repository analysis and PRD integration. Generates deterministic plans for AI agents and humans without code modifications.
feature-documenter
Feature design assistant for your project. Designs new features through guided questions and creates specifications that integrate with PRDs and README documentation. Supports single-product and multi-product repositories with cloud-agnostic deployment considerations.