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.
npx skills add protect-my-hair/nucleus-marketplace --skill multi-reviewgit clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplaceWrote 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/skills/protect-my-hair/nucleus-marketplace/multi-review)<a href="https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/multi-review"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/multi-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.
<a href="https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/multi-review"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/multi-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00866 |
| Opus 5.5 | $0.00012 | $0.00346 |
| Sonnet 5.5 | $0.00006 | $0.00173 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
multi-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.
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
多角色独立评审
核心原则
评审报告只能记录审查发现，不能制造人工批准、PMS 状态、PR 审查通过、合入或发布事实。
评审领域
按产物类型读取对应 reference：
- 需求分析：
references/requirement-analysis-review.md - 方案设计：
references/solution-design-review.md - 需求分解：
references/requirement-decomposition-review.md - 特性设计：
references/feature-design-review.md - 实施计划：
references/implementation-plan-review.md - 代码：
references/code-review.md - 测试资产：
references/test-asset-review.md - 交付证据：
references/delivery-evidence-review.md - 特性完成：
references/feature-completion-review.md
无法确定领域时，先读上下文并提出一个明确问题，不得默认用代码评审代替设计评审。
客观评审纪律
方案一致性评审不是机械要求实现逐字贴合原方案。评审者必须判断：
- 实现是否满足特性设计和实施计划承诺的能力、边界、接口、数据、权限和验证要求。
- 实现差异是必要改进、等价实现、计划外扩 scope，还是破坏原方案约束。
- 如果实现明显更简单、更稳健或更符合现有架构，且没有越界或遗漏，应保留实现，并记录“实现优于原方案”的证据和后续是否需要同步设计 / 计划。
- 如果实现改变了用户可见能力、数据 / 接口 / 权限边界、外部依赖或风险假设，必须阻塞并要求回到计划或特性设计评审节点，不能由 reviewer 直接批准扩 scope。
输出纪律
评审必须区分：
blocking：阻塞下游任务。important：进入下游前应处理。suggestion：可记录但不阻塞。unverifiable：当前证据无法判断，需要人工或外部系统确认。
特性开发完成后的评审必须同时覆盖：
- code-review。
- 方案一致性评审。
- 计划满足度评审。
向用户呈现评审结果时，按 _shared/references/interaction-format.md 的确认型格式，第一句先给结论（通过 / 有阻塞 / 需整改），再展开 findings。
子代理预审
所有人工审查 / 人工评审 / 人工复核节点在提交给人之前，必须先按 _shared/references/subagent-precheck-protocol.md 调度独立 reviewer 子代理完成预审，并取得“材料可提交人工审查”结论；子代理 prompt 基于 references/subagent-review-prompt.md 组织。
multi-review 自身的 review report 仍只记录发现、风险、整改建议和复核证据，不能替代人工审批、PMS 状态、PR 审查通过、合入或发布事实。
Runtime 边界
scripts/multi_review.py 只校验 review report schema 和语义，不创建评审结论、不替人审查、不改代码。
What ships with it
13 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.
- agents/openai.yaml 542 B
- assets/nucleus-multi-review-report.schema.json 5.5 KB
- references/code-review.md 1.7 KB
- references/delivery-evidence-review.md 522 B
- references/feature-completion-review.md 3.1 KB
- references/feature-design-review.md 1.1 KB
- references/implementation-plan-review.md 3.5 KB
- references/requirement-analysis-review.md 4.5 KB
- references/requirement-decomposition-review.md 2.4 KB
- references/solution-design-review.md 959 B
- references/subagent-review-prompt.md 3.1 KB
- references/test-asset-review.md 437 B
- scripts/multi_review.py 4.1 KB runs code
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.
- 1mo ago First seen · 71 lines · 30 tokens per session scan A b39dd13f4070
multi-review is a skill published in the GitHub repository protect-my-hair/nucleus-marketplace (164 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 866 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…