跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

cross-agent-review

Adversarially review a specific change, design, or finding by having Claude debate one or more INDEPENDENT AI agents (e.g. Gemini or GPT in Antigravity, several models at once) over a shared file relay, with mandatory file:line citations, live read-only evidence, and a converge-or-two-positions outcome. Use when the user wants a different model's adversarial take before acting, mentions Antigravity / cross-agent / agent-exchange / "hash it out with Gemini", or wants a finding stress-tested by independent models. NOT for whole-project audits (that is committee-review) or quick single-pass checks. Needs at least one second agent the user drives and a shared directory both sides can read and write.

randommonicle · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add randommonicle/claude-skills --skill cross-agent-review

技能说明


name: cross-agent-review description: Adversarially review a specific change, design, or finding by having Claude debate one or more INDEPENDENT AI agents (e.g. Gemini or GPT in Antigravity, several models at once) over a shared file relay, with mandatory file:line citations, live read-only evidence, and a converge-or-two-positions outcome. Use when the user wants a different model's adversarial take before acting, mentions Antigravity / cross-agent / agent-exchange / "hash it out with Gemini", or wants a finding stress-tested by independent models. NOT for whole-project audits (that is committee-review) or quick single-pass checks. Needs at least one second agent the user drives and a shared directory both sides can read and write.

Cross-agent review

Two or more DIFFERENT AI agents (Claude here, the hub; plus one or more the user operates, e.g. Gemini or GPT in Antigravity) review one change by appending to a shared file, each forced to cite and to concede on evidence. The value over a solo review: an independent model catches what you are too close to, and you catch its mistakes, so a claim only survives if it survives the other agent. First run: PropOS, 2026-08-09 (five exchanges, one external agent). Second run: PropOS, 2026-08-25 (cross-firm isolation, four seats at once: Gemini 3.1 Pro, Gemini 3.7 Flash, Claude Sonnet 4.6, GPT), which added the multi-seat handle model, the hub-and-spoke turn rule, and the tracked-scaffolding git split below. Composes with findings-are-evidence, verified-citations, live-state-first, server-side-authority, confirm-before-push.

The reusable scaffolding (protocol, kickoffs, review template) is bundled in templates/ next to this file. Copy it into the exchange dir rather than retyping the rules from prose.

When to use, and when not

Use for a SCOPED target: one migration, one finding, one design decision, one document's claims. Three modes, all the same machinery:

  • Challenger-external: the other agent(s) produce findings, Claude verifies and rebuts.
  • Challenger-Claude: Claude puts up a claim or a provisional verdict, the other agent(s) attack it.
  • Peer design: all sides propose and critique a design; expected to diverge.

It scales to several independent seats at once (different models), which sharpens completeness work because each model hunts blind to what the others surface. Not for whole-project audits (use committee-review), and not for a quick check you can do yourself in one pass. It costs each agent's tokens per round and a human in the loop to drive the external agents.

Handles: how several models stay distinct and never reply to themselves

Every participant holds exactly ONE handle for the whole exchange, and a handle is a SEAT, not a model: if two chats run the same model they still get different handles.

  • CLAUDE = the hub, in this repo. BEN (or the operator's name) = the human.
  • Each external chat = a distinct handle assigned in its kickoff: GEMPRO, GEMFLASH, SONNET, GPT.

The handle is given to the model in the kickoff (the first human message in its chat); it must use that exact string and ignore any section under a different handle, even one that might be the same model in another chat. This is what lets the user open several chats on several models without them colliding.

Setup (once per session)

The relay is a shared directory both sides can read and write. It can live outside the repo (the first run used C:\Users\<user>\agent-exchange\) or inside it as exchange/ (the second run). Contents are code discussion and citations only; never personal data, credentials, secrets, or financial figures.

  • Copy the bundled templates in. PROTOCOL.md, TEMPLATE_REVIEW.md, and kickoffs/ from this skill's templates/ dir, filling the <<repo>> and handle slots.
  • Git split when the exchange dir is inside a repo (important for a regulated repo). Track the reusable scaffolding, gitignore the transcripts and local seat state, so debate scratch never gets committed but the machinery still travels between machines and survives a clone:
    exchange/**
    !exchange/README.md
    !exchange/PROTOCOL.md
    !exchange/TEMPLATE_REVIEW.md
    !exchange/kickoffs/
    !exchange/kickoffs/**
    
    Prove it does what you think with git add -n exchange/ (only the scaffolding should be listed) and git check-ignore -v on a sample REVIEW_*.md, before trusting it. Do not commit or push without the user's per-action say-so.
  • Claude arms a persistent Monitor that emits each NEW spoke header, so every reply wakes this session. Grep the review file for the spoke handles and diff against the previous set:
    f="<<repo>>/exchange/REVIEW_<topic>_<date>.md"
    prev=$(grep -oiE '^## \[(GEMPRO|GEMFLASH|SONNET|GPT)[^]]*\]' "$f" 2>/dev/null | sort -u)
    while true; do
      cur=$(grep -oiE '^## \[(GEMPRO|GEMFLASH|SONNET|GPT)[^]]*\]' "$f" 2>/dev/null | sort -u)
      comm -13 <(printf '%s\n' "$prev") <(printf '%s\n' "$cur"); prev="$cur"; sleep 5
    done
    
    Prove the watcher can fire before trusting its silence (a mistyped pattern makes "no replies yet" indistinguishable from "watcher broken"): grep a synthetic ## [GEMPRO round 1] and confirm it matches AND that the ## [CLAUDE ...] line does not. Monitors die with the session; re-arm at the start of any session resuming an open exchange. One watcher covers several handles; for a late-joining seat, arm a second watcher rather than restarting the first and risking a gap.
  • Human arms the external side. Each external chat is kicked off with its handle (below). Antigravity can also run a background daemon that watches the dir and wakes the agent; optional.
  • Optional but powerful: live read-only evidence. If a read-only data source is connected (Supabase MCP, a DB, an API), Claude grounds the debate in real numbers rather than argument. This is what turned a "debated in the dark" sign-of
阅读完整来源 ↗