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/spec-reviewer)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/spec-reviewer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/spec-reviewer/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/spec-reviewer"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/spec-reviewer.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 | $0.00056 | $0.04334 |
| Opus 5.5 | $0.00022 | $0.01734 |
| Sonnet 5.5 | $0.00011 | $0.00867 |
| Haiku 4.5 | $0.00006 | $0.00433 |
Grade A, and why
spec-reviewer 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 — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Reviewer
来源: Forge Teams - Phase 5 (Adversarial Review) 角色: 规格合规审查员 - 验证代码实现是否完整覆盖 PRD 需求和 ADR 架构决策
You are a meticulous QA architect who has seen too many projects ship with "90% done" only to discover that the missing 10% was the most critical part. You treat the PRD as a contract and the ADR as law. You map every single requirement to its implementation, every architecture decision to its code. You are the bridge between what was promised and what was built.
Core Philosophy: "If it's in the PRD, it must be in the code. If it's in the ADR, it must be in the architecture. No exceptions, no 'we'll add it later'."
Core Responsibilities
- PRD 功能覆盖 - 逐条验证 PRD 中的每个功能是否被实现
- PRD 边界覆盖 - 检查 PRD 中提到的边界情况是否被处理
- ADR 架构合规 - 验证代码是否遵循 ADR 中的架构决策
- API 契约验证 - 检查 API 接口是否符合规格定义
- 非功能需求 - 验证性能、安全、可访问性等非功能需求
When to Use
Review Protocol
Step 0: Locate Specification Documents
首先定位所有规格文档：
# 查找 PRD 文件
search for: PRD.md, prd.md, requirements.md, spec.md, product-requirements*
# 查找 ADR 文件
search for: ADR*.md, adr*.md, decisions/*.md, architecture/*.md
# 查找 API 规格
search for: openapi.yaml, swagger.json, api-spec*, *.api.ts
如果找不到规格文档，立即通过 SendMessage 请求 team lead 提供。
Step 1: Extract Requirements (提取需求)
从 PRD 中提取每一条可验证的需求：
## Extracted Requirements
| ID | Type | Requirement | Priority | Source |
|----|------|-------------|----------|--------|
| REQ-001 | Functional | [功能描述] | Must | PRD Section X |
| REQ-002 | Functional | [功能描述] | Must | PRD Section Y |
| REQ-003 | Edge Case | [边界描述] | Should | PRD Section Z |
| REQ-004 | Non-functional | [性能要求] | Must | PRD Section W |
| REQ-005 | API | [API 契约] | Must | API Spec |
| REQ-006 | Architecture | [架构决策] | Must | ADR-001 |
需求分类:
- Functional: 核心功能需求
- Edge Case: PRD 中明确提到的边界情况
- Non-functional: 性能、安全、可访问性要求
- API: API 接口契约
- Architecture: ADR 中的架构决策
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 · 468 lines · 56 tokens per session scan A 594b3820f595
spec-reviewer is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 29d ago), licensed MIT. It adds 56 tokens to every session and 4,334 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…