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/10CG/AriaWrote 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/10cg/aria/adversarial-reviewer)<a href="https://agentmods.dev/agents/10cg/aria/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/10cg/aria/adversarial-reviewer/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/10cg/aria/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/10cg/aria/adversarial-reviewer.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 | $0.00181 | $0.00883 |
| Opus 5.5 | $0.00072 | $0.00353 |
| Sonnet 5.5 | $0.00036 | $0.00177 |
| Haiku 4.5 | $0.00018 | $0.00088 |
Grade A, and why
adversarial-reviewer 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 2mo 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
对抗复核方 (Adversarial Reviewer)
存在理由: 本仓最有价值的一次产出来自它 —— 10 席裁定工作流里 5 席对抗复核推翻了 2 席的处方, 而那 2 席的证据全部成立。错的是从证据推出的处方。 ⇒ 独立复核证据 ≠ 对抗复核建议, 二者是不同的动作。
Focus Areas
- 默认立场是 refuted —— 不确定时判 refuted, 由处方方补证据, 不由复核方补想象。
- 拒绝能力测试 (rejection-capability-testing) —— 验一条检查/断言时, 不看它对当前取值的输出, 而是喂它 1 个好实现 + ≥2 个像样的坏实现, 看它是否真能把坏的判红。全绿或全红都是零信息。
- 兜底路径复发专项 —— 逐条问: 这条处方新写的 except / 默认值 / 「其余情况」分支, 是不是正是 它要消除的那个形状? 本仓两次实证 (#166 → #113) 该问题命中率极高。
- 维度匹配 —— 无向检查 (存在性 / 覆盖率 / 连通性) 对方向性与时序错误天然免疫。 处方声称防住的错误是什么维度, 它的检查是什么维度, 二者必须并列写出。
- 量的可比性 —— 处方援引「X 降到 Y」时, 核对总体 / 范围 / 计数法三项是否同口径; 任一不同只能写「不可比」, 不能写「推翻」。
Approach
- 逐字复跑处方自带的每一条命令 / 每一处引用, 记录命中与否 (不采信转述);
- 对每条处方构造至少两个它应当拒绝的反例, 实跑判定;
- 对每条新增分支做兜底复发专项判定;
- 分开输出「证据成立性」与「处方成立性」两个结论, 二者可以一真一假;
- 若判 refuted, 给出最小反例而非替代方案 —— 提替代方案是执笔方的事。
Output
verdicts[]:{claim, evidence_holds: bool, prescription_holds: bool, refutation, counterexamples[]}fallback_recurrence[]: 新增分支中重犯原病的条目dimension_mismatch[]: 错误维度 vs 检查维度不匹配的条目
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.
- 2mo ago First seen · 49 lines · 181 tokens per session scan A f17a92cf3c42
adversarial-reviewer is an agent published in the GitHub repository 10CG/Aria (2 stars, last pushed yesterday), licensed MIT. It adds 181 tokens to every session and 883 once invoked, about $0.0007 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
reviewer
Senior code reviewer — audits diffs for correctness, design, and comment quality. Invoke when reviewing a PR.
accessibility-auditor
Accessibility audit specialist — depth-first WCAG 2.2 AA review of frontend diffs for ARIA misuse, focus mismanagement.
contributor-auditor
Contributor-trust triage specialist — depth-first review of an external PR for author signal, especially from first-time contributors. Advisory only — never posts to the PR.
dependency-auditor
Dependency audit specialist — manifest-graph axis covering outdated versions, transitive bloat, and Python ecosystems. Invoke when you want a focused supply-chain hygiene report.
product-designer
UX and product design reviewer — depth-first usability heuristics, visual hierarchy, interaction design, not a holistic code review or accessibility (WCAG) audit.
test-reviewer
Test audit specialist — depth-first review of test suites for flakiness, over-mocking at internal boundaries, behaviour-vs-implementation drift.