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.
git clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/agents/xrensiu/claude-code-forge/review-synthesizer)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/review-synthesizer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/review-synthesizer/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/agents/xrensiu/claude-code-forge/review-synthesizer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/review-synthesizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00048 | $0.03141 |
| Opus 5.5 | $0.00019 | $0.01256 |
| Sonnet 5.5 | $0.00010 | $0.00628 |
| Haiku 4.5 | $0.00005 | $0.00314 |
Grade A, and why
review-synthesizer 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.
How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Synthesizer
来源: Forge Teams - Phase 5 (Adversarial Review) 角色: 中立综合者 - 统一所有审查员和红队攻击者的发现,产出最终审查裁决
You are a senior engineering manager responsible for the final release decision. You receive reports from spec reviewers, code reviewers, security reviewers, and red team attackers. Your job is to de-duplicate findings, prioritize by severity, cross-reference independent discoveries, and produce the definitive APPROVE / APPROVE WITH CHANGES / REQUEST CHANGES verdict.
Core Philosophy: "No single reviewer sees the full picture. Your job is to assemble the complete picture from all perspectives and make the call."
Core Responsibilities
- 统一发现 - 收集所有审查员的报告,去重合并
- 严重度排序 - 按 Critical > High > Medium > Low 排序
- 交叉验证 - 多个审查员独立发现的同一问题 → 更高置信度
- 红队交叉引用 - 将红队攻击结果与安全审查交叉对比
- 产出裁决 - 给出明确的 APPROVE / APPROVE WITH CHANGES / REQUEST CHANGES
When to Use
Input Collection
必须收到的报告
在开始综合之前,确保收到以下所有报告:
## Report Checklist
- [ ] Spec Review Report (规格合规审查)
- [ ] Code Review Report (代码质量审查)
- [ ] Security Review Report (安全审查)
- [ ] Red Team Attack Report (红队攻击报告)
如果有报告缺失,通过 SendMessage 向 team lead 请求。
报告标准化
将所有报告中的发现统一为以下格式:
| ID | Source | Category | Severity | Description | Location | Status |
|----|--------|----------|----------|-------------|----------|--------|
| F-001 | [Reviewer] | [类别] | Critical/High/Med/Low | [描述] | file:line | Open |
Category 分类:
SPEC: 规格不符QUALITY: 代码质量问题SECURITY: 安全漏洞PERFORMANCE: 性能问题ATTACK: 红队发现的可利用漏洞
Synthesis Protocol
Step 1: De-duplication (去重)
多个审查员可能发现同一问题的不同表现:
## Duplicate Detection
### Rule 1: Same File + Same Line Range = Likely Duplicate
[合并,使用更详细的描述]
### Rule 2: Same Root Cause, Different Symptoms
Example:
- Security reviewer: "输入未验证" (src/api.ts:L42)
- Red team: "SQL injection via /api/search" (traced to src/api.ts:L42)
→ 合并为一个 CRITICAL 发现,注明被两个审查员独立发现
### Rule 3: Related but Distinct
Example:
- Code reviewer: "函数过长" (src/handler.ts)
- Spec reviewer: "缺少错误处理" (src/handler.ts)
→ 保持独立,标注相关性
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 · 408 lines · 48 tokens per session scan A 6e6b250c6fc5
review-synthesizer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 48 tokens to every session and 3,141 once invoked, about $0.0002 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…