# Send Cross-Model Review to your agent Use the source page and any available docs to guide the install because the item currently does not return a direct package file. ## Fast path - Open the source page via Open source listing. - If you can obtain the package, extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the source page and extracted files. ## Suggested prompts ### New install ```text I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required. Then review README.md for any prerequisites, environment setup, or post-install checks. ``` ### Upgrade existing ```text I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need. Then review README.md for any prerequisites, environment setup, or post-install checks. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "cross-model-review", "name": "Cross-Model Review", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/Don-GBot/cross-model-review", "canonicalUrl": "https://clawhub.ai/Don-GBot/cross-model-review", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/cross-model-review", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cross-model-review", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "CHANGELOG.md", "CONTRIBUTING.md", "README.md", "SECURITY.md", "SKILL.md", "package.json" ], "downloadMode": "manual_only", "sourceHealth": { "source": "tencent", "slug": "cross-model-review", "status": "source_issue", "reason": "not_found", "recommendedAction": "review_source", "checkedAt": "2026-04-30T22:22:25.399Z", "expiresAt": "2026-05-01T22:22:25.399Z", "httpStatus": 404, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cross-model-review", "contentType": "text/plain", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cross-model-review", "contentDisposition": null, "redirectLocation": null, "bodySnippet": null, "slug": "cross-model-review" }, "scope": "item", "summary": "Known item issue.", "detail": "This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.", "primaryActionLabel": "Open source listing", "primaryActionHref": "https://clawhub.ai/Don-GBot/cross-model-review" }, "validation": { "installChecklist": [ "Open the source listing and confirm there is a real package or setup artifact available.", "Review SKILL.md before asking your agent to continue.", "Treat this source as manual setup until the upstream download flow is fixed." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/cross-model-review", "downloadUrl": "https://openagent3.xyz/downloads/cross-model-review", "agentUrl": "https://openagent3.xyz/skills/cross-model-review/agent", "manifestUrl": "https://openagent3.xyz/skills/cross-model-review/agent.json", "briefUrl": "https://openagent3.xyz/skills/cross-model-review/agent.md" } } ``` ## Documentation ### Metadata name: cross-model-review version: 2.0.0 description: > Adversarial plan review using two different AI models. v2: Alternating mode — models swap writer/reviewer each round. Fully autonomous loop — no human input between rounds. Use when: building features touching auth/payments/data models, plans that will take >1hr to implement. NOT for: simple one-file fixes, research tasks, quick scripts. triggers: - "review this plan" - "cross review" - "challenge this" - "is this plan solid?" - "adversarial review" ### When to Activate Activate this skill when the user: Says any trigger phrase above Shares a plan and asks for adversarial/second-opinion review Asks you to "sanity check" a multi-step implementation plan Do NOT activate for: simple fixes, one-liners, pure research tasks. ### Static Mode (v1 — backward compatible) Fixed roles: planner always writes, reviewer always reviews. Requires human to trigger each round. ### Alternating Mode (v2 — recommended) Models swap roles each round. Fully autonomous — no human input between rounds. Flow: Round 1: Model A writes the plan. Model B reviews. Round 2: Model B rewrites (based on its own review). Model A reviews. Round 3: Model A rewrites (based on its own review). Model B reviews. ...continues alternating until both agree (reviewer says APPROVED) or max rounds hit. Why this works: Each model must implement its own critique — can't nitpick without owning the fix The other model catches over-engineering or proportionality issues Natural convergence: each round addresses the other's concerns ### Autonomous Orchestration (Alternating Mode) You (the main agent) run this loop. It's fully autonomous after kickoff. ### Step 1 — Save the plan and init node review.js init \\ --plan /path/to/plan.md \\ --mode alternating \\ --model-a "anthropic/claude-opus-4-6" \\ --model-b "openai-codex/gpt-5.3-codex" \\ --project-context "Brief description for reviewer calibration" \\ --out /home/ubuntu/clawd/tasks/reviews Captures workspace path from stdout. ### Step 2 — The autonomous loop while true: step = next-step(workspace) if step.action == "done": break # APPROVED! if step.action == "max-rounds": ask user: override or manual fix break if step.action == "review": spawn sub-agent with step.model, step.prompt save response to workspace/round-N-response.json parse-round(workspace, round, response) continue if step.action == "revise": spawn sub-agent with step.model, step.prompt save output plan to temp file save-plan(workspace, temp file, version) continue ### Step 3 — Finalize When the loop exits with APPROVED: node review.js finalize --workspace Present: rounds taken, issues found/resolved, rubric scores, plan-final.md location. ### CLI Reference Commands: init Create a review workspace next-step Get next action for autonomous loop parse-round Parse a reviewer response, update issue tracker save-plan Save a revised plan version from writer output finalize Generate plan-final.md, changelog.md, summary.json status Print current workspace state init options: --plan Path to plan file (required) --mode "static" (default) or "alternating" --model-a Model A — writes first (alternating mode, required) --model-b Model B — reviews first (alternating mode, required) --reviewer-model Reviewer model (static mode, required) --planner-model Planner model (static mode, required) --project-context Brief project context for reviewer calibration --out Output base dir (default: tasks/reviews) --max-rounds Max rounds (default: 5 static, 8 alternating) --token-budget Token budget for context (default: 8000) next-step options: --workspace Path to review workspace (required) Returns JSON: { action, model, round, prompt, planVersion, saveTo } Actions: "review", "revise", "done", "max-rounds" parse-round options: --workspace Path to review workspace (required) --round Round number (required) --response Path to raw reviewer response (required) save-plan options: --workspace Path to review workspace (required) --plan Path to revised plan markdown (required) --version Plan version number (required) finalize options: --workspace Path to review workspace (required) --override-reason Reason for force-approving with open issues --ci-force Required in non-TTY mode when overriding status options: --workspace Path to review workspace (required) Exit codes: 0 Approved / OK 1 Revise / max-rounds 2 Error ### Spawning reviewers step = next-step(workspace) # action: "review" response = sessions_spawn(model=step.model, task=step.prompt, timeout=120s) # Save raw response to workspace/round-{step.round}-response.json parse-round(workspace, step.round, response_file) System instruction for reviewer: "You are a senior engineering reviewer. Output ONLY valid JSON matching the schema. No tool calls. No markdown fences. No preamble." ### Spawning writers step = next-step(workspace) # action: "revise" revised_plan = sessions_spawn(model=step.model, task=step.prompt, timeout=300s) # Save raw output as temp file save-plan(workspace, temp_file, step.planVersion) System instruction for writer: none needed — the prompt is self-contained. ### Error handling Reviewer timeout/failure: retry once, then ask user Writer timeout/failure: retry once, then ask user Parse error on review JSON: re-prompt reviewer once with "Your response was not valid JSON" Max rounds hit: present status to user, ask for override or manual fix ### Convergence The loop converges when the reviewer says APPROVED with no open CRITICAL/HIGH blockers. The script enforces this — if reviewer says APPROVED but blockers remain, it overrides to REVISE. ### Static Mode (v1 — backward compatible) For static mode, the original orchestration from v1 still works: ### Step 1 — Init node review.js init --plan --reviewer-model --planner-model ### Step 2 — Manual loop For each round: build reviewer prompt from template, spawn reviewer, parse-round, revise plan yourself, continue. ### Step 3 — Finalize Same as alternating mode. ### Integration with coding-agent Before dispatching any plan to coding-agent that: Touches auth, payments, or data models Has 3+ implementation steps The user hasn't already reviewed adversarially Run cross-model-review first. Only proceed if exit code 0. ### Notes Workspace persists in tasks/reviews/ — referenceable later issues.json tracks full lifecycle of all issues meta.json stores mode, models, current round, verdict, needsRevision flag next-step is the state machine — always call it to determine what to do Dedup warnings help catch semantic drift across rounds Models must be from different provider families (cross-provider enforcement) --project-context is injected into reviewer prompts for calibration ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Don-GBot - Version: 2.1.0 ## Source health - Status: source_issue - Known item issue. - This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file. - Health scope: item - Reason: not_found - Checked at: 2026-04-30T22:22:25.399Z - Expires at: 2026-05-01T22:22:25.399Z - Recommended action: Open source listing ## Links - [Detail page](https://openagent3.xyz/skills/cross-model-review) - [Send to Agent page](https://openagent3.xyz/skills/cross-model-review/agent) - [JSON manifest](https://openagent3.xyz/skills/cross-model-review/agent.json) - [Markdown brief](https://openagent3.xyz/skills/cross-model-review/agent.md) - [Download page](https://openagent3.xyz/downloads/cross-model-review)