adversarial-review

adversarial-review is a skill for Claude Code, Codex from BackToCimaCoppi/Praxis. It costs 111 tokens per session (4,318 once invoked), scanned A, original, Apache-2.0.

A process for having several independent reviewers inspect the same project evidence and report possible problems. The main agent then decides which findings are valid against the project's official specifications.

In plain words
What is it for?
It helps run a one-time adversarial review, compare independent findings, record decisions and their sources, and perform a later closed check of the agreed fixes.
Why use it?
It helps uncover missed issues while keeping review findings separate from the rules and requirements that determine the final decision.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; runs codex exec; mentions Codex.

Good fit It helps run a one-time adversarial review, compare independent findings, record decisions and their sources, and perform a later closed check of the agreed fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/backtocimacoppi/praxis/adversarial-review
Install

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.

Any agent
npx skills add BackToCimaCoppi/Praxis --skill adversarial-review
Clone the repo
git clone --depth 1 https://github.com/BackToCimaCoppi/Praxis

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for adversarial-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/backtocimacoppi/praxis/adversarial-review/github.svg)](https://agentmods.dev/skills/backtocimacoppi/praxis/adversarial-review)
Your own site
<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/adversarial-review"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/adversarial-review/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.

agentmods 80×15 button for adversarial-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/adversarial-review"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/adversarial-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,318 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.04318
Opus 5.5 $0.00044 $0.01727
Sonnet 5.5 $0.00022 $0.00864
Haiku 4.5 $0.00011 $0.00432

Measured 1mo ago against content hash 0581599a9dbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adversarial-review 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/cursor-review-runner.sh, scripts/discover_bridges.py, tests/test_discovery.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/adversarial-review/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

对抗评审

0. 硬边界

  1. 同一 review_id + object_hash + truth_baseline_hash 只开放一次,不自动开 R2/R3。对象或正式真值根本变化才可登记新身份。
  2. 每个实际选择的评审者都在授权项目根内独立只读调查,使用同一冻结对象与基线,不读其他人的结果。
  3. 当前主线程合并、核证和逐条裁决;评审者不代替用户选择新业务语义,不另设裁判模型。
  4. 评审报告是过程证据,正式 L1–L7 和授权裁决才是规格真值。
  5. 所有模型与运行参数禁用 Fast;不使用 Auto 或不明模型作为实际身份。

1. 触发时的桥接与模型选择

每次触发都从本 skill 目录运行 python3 scripts/discover_bridges.py。脚本仅报告三个 CLI 是否安装、是否登录、当前账户可见的模型 ID/名称和失败原因;不得把本机上一次的模型列表当作下一个用户的可用列表。读取脚本 JSON 后:

  1. 对不可用桥接明确说明未安装、未登录或查询失败;其他可用桥接照常提供。
  2. 按桥接展示模型标识和名称。可先筛出名称或描述中显示高推理能力的几个候选,提供完整清单的查询路径;候选筛选不能伪装成账户限制,也不能写死具体型号。
  3. 请用户选择至少一个“桥接 + 模型标识”;Codex 另选该模型实际支持的推理档。允许同一桥接选多个模型。若只有一个可用或用户只选一个,照样执行独立评审并给单模型发现报告;不得假造“对抗双方”、共识或排名。
  4. 用户选择后再次核对所选 ID 仍在本轮实时清单里。缺失、认证过期或模型已下架时告知用户并重选,禁止自行替换。
  5. 未收到选择时不启动评审。仅在用户已经提供本轮精确桥接/模型且核验通过时,直接继续。

发现脚本不输出账号、令牌或认证缓存。模型清单只证明可见,实际调用失败时按 §8 处理。

2. 总体流程

实时探测三个桥接 → 用户选择一个或多个桥接/模型 → 冻结评审身份与证据包
→ 所有已选模型同时独立只读评审 → 当前主线程合并与逐条裁决
→ 需要业务选择时请授权角色逐项裁决 → 多模型才点评排名
→ 按采纳项整改 → closed-remediation-review 固定范围验收 → PASS

3. 证据包

复杂场景同时读取 references/证据包制作规范.md;本节是强制最小集。

3.1 冻结内容

  • review_id / object_hash / truth_baseline_hash。
  • 评审对象:短小、临时或评审通道不可直接访问时内嵌全文;同一工作区内的大对象给绝对路径、哈希和精确范围,禁止摘要替代。
  • 正式真值基线:适用的 L1–L7、冻结规格、工程红线和任务边界。
  • 已决策·不得重开区:每项必须引用正式规格或 DEC-x;没有证据不得放入。
  • 本次口径卡:设计、测试用例、章程或代码评审口径。
  • 授权项目根 REVIEW_ROOT:默认解析为被评审对象所在 Git 工作树根;非 Git 项目才用用户明确授权的项目根。不得为了少给上下文而降成对象目录。
  • 起始导航,以及明确的禁止读取项、禁止动作、输出格式和严重度预算。

钉对象,不钉视野;读得宽,评得窄:全部已选评审者必须评同一对象、同一真值基线和同一口径,但必须各自在 REVIEW_ROOT 内做独立勘察。证据包是冻结核心与调查种子,不是穷举白名单;各方实际发现路径可以不同。补读结论要给精确位置,调查得到的背景只能用于判断冻结对象,不能重开已决策项或改评整个项目。

证据包本身也要受审:评审者必须核验起始材料是否遗漏冲突真值、关键生产者/消费者或已经失效;发现缺口时用事实报告,不能默认制包方天然完整。

3.2 路径与临时目录

  • 报告路径必须先解析为绝对路径,且位于用户授权的任务目录。
  • 临时目录每轮用独立 mktemp -d,不得使用全局固定文件名。
  • 记录评审前工作树快照;全部已选评审者完成后核验目标文件和工作树没有被它们修改。
  • 原始 各实际评审者输出保留到报告验收完成,随后可清理临时目录。

4. 全部评审者共用指令

证据包末尾必须加入以下语义,各评审者仅替换角色名:

你是独立评审者,不是设计者、裁判或施工者。

开工顺序(强制):
1. 读完冻结对象、真值基线和起始导航;
2. 在授权项目根内亲自做一次独立只读勘察,不得只凭证据包清单作答;
3. 按任务相关性检索同一概念、业务标识、状态与错误码,核对正式规格、生产者、消费者、测试、配置/迁移/运行手册;
4. 把证据包完整性也当作待核验声明;继续检索已不再改变本次口径内结论后再收口。

Read the full file on GitHub · 226 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 1mo ago Changed · -115 lines · -104 tokens per session 0581599a9dbb
  2. 1mo ago First seen · 341 lines · 215 tokens per session scan A a1327fc6463d

Subscribe to this mod's changes

adversarial-review is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 111 tokens to every session and 4,318 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

ork-review-pr

Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, review a diff, find real bugs, assess merge risk, or provide evidence-backed review findings. Do not use for implementation or style-only cleanup.

yonatangross/orchestkit · 64 tokens

ork-assess

Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate, compare, identify trade-offs, evaluate readiness, or decide whether an approach is good enough. Do not use for a full pull-request review or to implement a chosen…

yonatangross/orchestkit · 68 tokens

ork-verify

Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove, check readiness, run the relevant tests, or distinguish a claimed result from an observed one. Do not use to write missing tests or fix failures.

yonatangross/orchestkit · 65 tokens

chief-of-staff

The CEO's right hand — maintains validated project context, prepares task contracts, logs cross-department decisions, and runs the weekly review. Use when the user says "what's in flight", "resume the project", "log this decision", "weekly review", "turn this idea into a brief", or when multi-department work needs…

alebgl77/claude-inc · 79 tokens

appsec-review

Produces a bounded defensive application security review: threat model, security-sensitive diff, dependencies, and secrets hygiene with source-grounded findings. Use when the user says "security-review this release", "check this integration before shipping", "review the auth change", or "audit our agent's data access".

alebgl77/claude-inc · 0 tokens

close-management

Runs the month-end close: generates a day-by-day runbook from D-2 to D+5 as CLOSE- .md with an owner matrix, dependency-ordered tasks (subledgers → accruals → reconciliations → flux → lock), numeric flux thresholds, a preparer/reviewer sign-off log, and close metrics such as days-to-close and reopened entries. Use…

alebgl77/claude-inc · 113 tokens