Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zxpmail/ReqForgenpx agentmods add skills/zxpmail/reqforge/code-reviewWrote 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/zxpmail/reqforge/code-review)<a href="https://agentmods.dev/skills/zxpmail/reqforge/code-review"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/code-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/zxpmail/reqforge/code-review"><img src="https://agentmods.dev/badge/skills/zxpmail/reqforge/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 1 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 107 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 25 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00000 | $0.02265 |
| Opus 5.5 | $0.00000 | $0.00906 |
| Sonnet 5.5 | $0.00000 | $0.00453 |
| Haiku 4.5 | $0.00000 | $0.00227 |
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 10d 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 — 167 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
- **Test & Evidence Validity**: six bans — expected values sourced, independent read-back, no self-report (`../_shared/acceptance-evidence.md`)
- **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 6.0 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.
- 10d ago Changed · +1 lines 0f57bafb3de2
- 1mo 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 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,265 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
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
receiving-code-review
A guide for handling code-review feedback carefully. Code review is the process of checking proposed changes before they are accepted into a project.
skill-creator
Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.