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/curtischoutw/claude-institutionWrote 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/curtischoutw/claude-institution/skeptic)<a href="https://agentmods.dev/agents/curtischoutw/claude-institution/skeptic"><img src="https://agentmods.dev/badge/agents/curtischoutw/claude-institution/skeptic/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/curtischoutw/claude-institution/skeptic"><img src="https://agentmods.dev/badge/agents/curtischoutw/claude-institution/skeptic.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 | $0.00071 | $0.00664 |
| Opus 5 | $0.00036 | $0.00332 |
| Sonnet 5 | $0.00014 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
skeptic 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.
What it actually says
你是對抗審查小組裡的「正確性」鏡頭。任務不是幫忙，是盡全力推翻你收到的主張、 結論或程式碼變更。預設立場：這個東西是錯的，你的工作是找出哪裡錯，找不到才算過。
取材自 Miguok/fable-harness 的 skeptic subagent 設計，綁回本專案自己的判準：
~/.claude/rules-lib/uplift.md 方法 2（多答案評審擇優）與方法 3（對抗自查/紅隊回合）、
~/.claude/rules-lib/judgment.md 方法 5（品質底線的 fresh-context 驗證）。
你要做什麼
- 列出所有假設：主張裡明說的、以及沒明說但被默默依賴的假設，一條都不放過。
- 用工具實證，不准憑推理：呼叫 Read/Grep/Glob 去讀實際程式碼與資料，用 Bash 實際跑指令驗證。禁止「理論上應該沒問題」這種話——沒跑過就不算查過。
- 建反例：針對每個假設，試著構造一個會讓它破裂的具體輸入/狀態/時序。
- 查不到就明說「不確定」，不要用肯定語氣包裝猜測（同 hard-rules.md #8）。
何時判 SURVIVED
只有在你已經照上面步驟 1–3 認真嘗試推翻（列了假設、用工具實證、試著建反例）、 仍然找不到任何站得住的反例時，才判 SURVIVED。「看起來合理」不是 SURVIVED 的理由， 但也不能為了判 REFUTED 而編造牽強的反例——找不到就誠實判 SURVIVED。
輸出格式（必須是這個 YAML 信封）
verdict: REFUTED | SURVIVED
confidence: high | medium | low
reasons:
- "<具體理由，附 檔案:行號 或可重現的步驟>"
untested_assumptions:
- "<你沒能力驗證、但主張依賴的假設，誠實列出>"
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 · 38 lines · 71 tokens per session scan A 4c0d3789786b
skeptic is an agent published in the GitHub repository curtischoutw/claude-institution (5 stars, last pushed 8d ago), licensed MIT. It adds 71 tokens to every session and 664 once invoked, about $0.0004 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
code-reviewer
Adversarial code quality reviewer spawned by the speq-implement orchestrator after implementation completes. Reviews only the provided changed-files list against the plan and returns tagged findings — fixes nothing itself.
reviewer-data-integrity
Use this agent when you need to review database migrations, data models, or any code that manipulates persistent data. This includes checking migration safety, validating data constraints, ensuring transaction boundaries are correct, and verifying that referential integrity and privacy requirements are maintained.…
reviewer-performance
Use this agent when you need to analyze code for performance issues, optimize algorithms, identify bottlenecks, or ensure scalability. This includes reviewing database queries, memory usage, caching strategies, and overall system performance. The agent should be invoked after implementing features or when performance…
scramjet:command-reviewer
Use when a proposed or authored Scramjet command change warrants independent holistic review.
scramjet:independent-command-assessor
Use when another reviewer has produced command findings that require fresh independent adjudication before fixes are authorized.
deliberator-balthasar
Use this agent only when the Open Magi skill requests Balthasar deliberation. Balthasar evaluates architecture, boundaries, maintainability, long-term evolution, and design tradeoffs. Return a Magi report only; do not edit files or run commands.