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/dean0x/devflow/review-methodologynpx skills add dean0x/devflow --skill review-methodologygit clone --depth 1 https://github.com/dean0x/devflowWhat 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 | $0.00024 | $0.01021 |
| Opus 5 | $0.00012 | $0.00511 |
| Sonnet 5 | $0.00005 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
review-methodology 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Methodology
The canonical review process for all Devflow review agents. Ensures consistent, fair, and actionable code reviews.
Iron Law
NEVER BLOCK FOR PRE-EXISTING ISSUES
Only issues in YOUR CHANGES can block a PR. Pre-existing issues are informational only. If you didn't add it, you don't own it. Fair reviews focus on the diff, not the codebase.
Core Philosophy
- Focus on changed lines first - Developer introduced these
- Context matters - Issues near changes should be fixed together
- Be fair - Don't block PRs for legacy code
- Be specific - Exact file:line with examples
- Be actionable - Clear fixes, not vague complaints
6-Step Review Process
Step 1: Identify Changed Lines
Get the diff to understand what changed. Identify base branch and extract changed files/lines.
Step 2: Categorize Issues
| Category | Scope | Priority | Action |
|---|---|---|---|
| 1. Issues in Your Changes | Lines ADDED/MODIFIED in this branch | BLOCKING | Must fix before merge |
| 2. Issues in Code You Touched | Same file/function, but not your line | HIGH | Should fix while here |
| 3. Pre-existing Issues | Lines you didn't touch at all | INFORMATIONAL | Fix in separate PR |
Note: All categories and severities — including suggestions — are reported for resolution. Categories affect PR merge-blocking, not whether issues get resolved. The resolve workflow evaluates everything.
Step 3: Analyze with Domain Expertise
Apply your specialized lens (security, performance, tests, etc.) to each category:
- Category 1 - Maximum scrutiny, any issue blocks PR
- Category 2 - Should fix together with your changes
- Category 3 - Note but don't block, suggest separate issues
Step 4: Prioritize by Severity
| Severity | Description | Examples |
|---|---|---|
| CRITICAL | Immediate risk, must fix | Security vulnerabilities, data loss risks, breaking API changes |
| HIGH | Significant risk, should fix | Performance degradation, missing error handling |
| MEDIUM | Moderate risk, consider fixing | Style inconsistencies, missing documentation |
| LOW | Minor improvements | Naming suggestions, optional optimizations |
What ships with it
3 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.
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 · 122 lines · 24 tokens per session scan A 8f5bb1ba2b27
review-methodology is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 1,021 once invoked, about $0.0001 per session on Opus 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
data-engineering
Skill "data-engineering" from fengshao1227/ccg-workflow, covering 数据工程域 · data engineering, 域概览, 数据管道编排, 框架对比 and airflow 核心模式.
verify-change
变更校验关卡。分析代码变更，检测文档同步状态，评估变更影响范围。当用户提到变更检查、文档同步、代码审查、提交前检查、diff分析时使用。在设计级变更、重构完成时自动触发。.
verify-quality
代码质量校验关卡。检测复杂度、重复代码、命名规范、函数长度等质量指标。当用户提到代码质量、复杂度检查、代码异味、重构建议、lint检查、代码规范时使用。在复杂模块、重构完成时自动触发。.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
gen-docs
文档生成器。自动分析模块结构，生成 README.md 和 DESIGN.md 骨架。当用户提到生成文档、创建README、创建DESIGN、文档骨架、文档模板时使用。在新建模块开始时自动触发。.