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 agentmods add skills/zxpmail/reqforge/code-reviewnpx skills add zxpmail/ReqForge --skill code-reviewgit clone --depth 1 https://github.com/zxpmail/ReqForgeWhat 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 | $0.00000 | $0.02230 |
| Opus 5 | $0.00000 | $0.01115 |
| Sonnet 5 | $0.00000 | $0.00446 |
| Haiku 4.5 | $0.00000 | $0.00223 |
Grade A, and why
code-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 2d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: code-review description: Used when the user wants to review code, check quality, verify feature completeness, or needs to validate code implementation against Spec, DESIGN.md, and design mockups. Outputs a structured review report with evidence for each conclusion. version: 2.3.0 updated: 2026-07-16 requires: []
[Task] Review code implementation completeness and quality against Product-Spec.md, DESIGN.md (when present), and design mockups. Output a structured review report. Fixes are executed by the main Agent using dev-builder or bug-fixer Skill after receiving the report.
[Not For] - Fixing bugs -> use /bug-fixer instead - Writing new features -> use /dev-builder instead - Requirements gathering -> use /product-spec-builder instead
[Dependency Check] Automatically executed as the first step when the Skill starts:
Required:
- Product-Spec.md -> if missing, prompt to call /product-spec-builder first
- Project code exists -> if no code, prompt to call /dev-builder first
Optional (enhances review capability):
- `.forge/security-guidance.md` -> if present, **must read** for moderate/complex reviews or when `code-reviewer-security` runs
- DEV-PLAN.md -> if available, cross-reference Phase delivery checklist
- Design-Brief.md -> if available, cross-reference visual direction (direction only when DESIGN.md absent)
- DESIGN.md -> if available, cross-reference frozen tokens and components (priority over Brief for exact UI values)
- Design tool MCP -> if available, extract design values and compare with code (supplements DESIGN.md when both exist)
- Playwright plugin -> if available, automate UI interaction testing
- git -> if available, use git diff to trace change scope
[Shared Discipline]
Review 时重点查 Surgical Changes + Simplicity First → ../_shared/karpathy-discipline.md
每条 finding 带 action(auto-fix/ask-user/no-op,谁来修)→ ../_shared/finding-actions.md
[First Principles]
Review 前必读 references/first-principles.md
Tech Stack: 审查前读 .forge/dev-map.md 的技术栈节,按语言选择审查维度(Java 侧重 import/异常/DI;Python 侧重 import/类型标注;JS/TS 侧重类型/async/import 路径)。
Code Standards: 审查时同时加载 .forge/code-standards/<language>.md,对照规范逐项检查(命名、异常处理、依赖注入模式等)。
[Output Style]
→ references/output-style.md
[File Structure]
code-review/ ├── SKILL.md ├── commands/code-review.md └── references/ ├── first-principles.md ├── output-style.md ├── judgment-spectrum.md ├── anti-rationalization.md ├── anti-ai-slop-checklist.md ├── review-dimension-checklist.md ├── review-strategy.md ├── multi-perspective-dispatch.md # 4 维审查的平台无关分发(Mode A/B) ├── workflow.md # Step 1–5(必读) └── yolo-mode.md ../_shared/
[Output Artifacts] - Review report (screen output) — parallel agent review results with aggregated findings
[Judgment Spectrum]
→ references/judgment-spectrum.md
[Dimension Checklist] See references/review-dimension-checklist.md for the full review dimension checklist.
Must-have dimensions:
- **Functional Completeness**: every Spec requirement has a code implementation
- **Surgical Changes Audit**: every changed line traces to the original request
- **Simplicity First Audit**: no over-engineering or speculative abstraction
- **Security Scan**: hardcoded credentials, XSS, SQL injection, path leakage
- **Type Safety**: language-aware (TS `any`/`@ts-ignore`; other stacks per `code-standards` / types agent)
- **Performance (lightweight)**: N+1 / unbounded loops / hot-path sync I/O when visible in diff (owned by bug dimension)
What ships with it
12 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.
- commands/code-review.md 763 B
- references/anti-ai-slop-checklist.md 2.9 KB
- references/anti-rationalization.md 1.1 KB
- references/first-principles.md 2.4 KB
- references/judgment-spectrum.md 878 B
- references/multi-perspective-dispatch.md 6.5 KB
- references/output-style.md 1.2 KB
- references/review-dimension-checklist.md 4.8 KB
- references/review-strategy.md 2.0 KB
- references/workflow.md 9.0 KB
- references/yolo-mode.md 307 B
- skill.json 1.0 KB
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.
- 2d ago First seen · 166 lines · 0 tokens per session scan A 40ad99ee9e6d
code-review is a skill published in the GitHub repository zxpmail/ReqForge (18 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,230 tokens. 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
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
subagent-driven-development
当在当前会话中执行包含独立任务的实现计划时使用.
orchestration-team
Operating manual for the orchestration pod. Covers lead vs peer roles, monitoring with rig commands, permission handling, implementation pair gating, dogfood loops, review routing, agent behavioral models, intervention discipline, and communication culture.
adr
Create and manage Architecture Decision Records. Documents significant technical decisions with context, alternatives, and consequences. Also supports evaluate (assess proposals) and design (system design) modes.
deploy-checklist
Pre-deployment verification checklist. Generates customized checklists based on tech-stack with rollback triggers. Auto-invoked by /draft:upload.