Orchestrating Adversarial Reviews

What it does

When your agent uses it

• A fan-out task must produce trustworthy results — security audit
• Research synthesis
• Migration — and a single agents self-report cannot be trusted

Example prompts

• “done/fixed”
• “/orchestrating-adversarial-reviews”

Requirements

• Docker
• Pre-approved tools (allowed-tools): Read

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1不信单 agent 自报。 finder 会噪音误报，implementer 会谎称"已修复/全覆盖"。每个高价值结论必须被独立 agent 用不同视角尝试推翻。
2. 2可证伪 > 可声称。 修复必须配一个"退回漏洞代码就 FAIL、修好才 PASS"的 load-bearing 证明测试。没有证明测试的"已修复"等于没修。
3. 3失败方向要对。 守卫链里任何一步的退出码都不能被管道遮住；破坏性动作前置可逆检查。

What it can do on your machine

Read from SKILL.md and the folder at commit 2544577. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Orchestrating Adversarial Reviews loads about 858 tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 178 tokens; SKILL.md has 188 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~178

When it runs · the whole SKILL.md, loaded when a task matches

~858

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from telagod/code-abyss at commit 2544577, republished under its MIT licence (© telagod). 188 words, ~858 tokens.

name

orchestrating-adversarial-reviews

description

Multi-agent adversarial-verification orchestration for high-confidence conclusions. Fan-out finders, then verify every finding through a three-prism panel (exploitability / correctness / refutation) that defaults to disbelief, gate fixes behind load-bearing proof tests that catch agents who falsely claim "done/fixed", and roll out behind a build-first exit-code guard. Use when a fan-out task must produce trustworthy results — security audit, code review, research synthesis, migration — and a single agent's self-report cannot be trusted. Composes with securing-systems (what to look for) and shipping-changes (change closed loop); orchestration engine is the Workflow tool.

allowed-tools

Read

user-invocable

false

<!-- safety-scan: ignore RM_RF_ROOT,CURL_PIPE_SH,PROMPT_INJECTION 本 skill 把危险命令(| tail 吞退出码、docker rm 误删、agent 谎报)列为反模式教学，自身不执行 -->

<!-- safety-scan: ignore TOOLS_PRIVILEGED 知识型 skill，仅 Read；文中 Workflow / docker / go / git 命令由 agent 自有工具执行，非本 skill 落盘运行 -->

Recon (fan-out)     每维一个 finder, 并行深读, schema 出结构化 findings
   |                pipeline 而非 barrier: 维度A的发现可在维度B还在找时就进验证
   v
Verify (三棱镜)     每条 finding 派 N 个 verifier, 各执一镜, 默认怀疑
   |                可利用性 / 正确性 / 证伪猎杀 —— 票数 >= 多数 才保留
   v
Synthesize / Ship   合成定级报告; 若是修复任务 -> 证明测试 guard -> build-first 上线

© telagod, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/orchestrating-adversarial-reviews of telagod/code-abyss.

• SKILL.md
• references/workflow.md

Open the folder on GitHubat commit 2544577