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/documentationnpx skills add dean0x/devflow --skill documentationgit 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 | $0.00021 | $0.01055 |
| Opus 5 | $0.00010 | $0.00528 |
| Sonnet 5 | $0.00004 | $0.00211 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
documentation 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 yesterday.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Patterns
Domain expertise for documentation quality and alignment. Use alongside devflow:review-methodology for complete documentation reviews.
Iron Law
DOCUMENTATION MUST MATCH REALITY
Outdated documentation is worse than no documentation. It actively misleads. Every code change that affects behavior requires a documentation check. Comments that explain "what" instead of "why" are noise. The best documentation is code that doesn't need documentation.
Documentation Categories
1. Code Documentation Issues
| Issue | Problem | Fix |
|---|---|---|
| Missing docstrings | Complex functions without explanation | Add JSDoc with params, returns, throws |
| Outdated comments | Comments that contradict code | Update or remove |
| "What" comments | // Loop through users |
Explain "why" instead |
| Magic algorithms | Complex logic without explanation | Document algorithm and rationale |
| Transition residue | "We no longer do X" notes, in-file changelogs, or refs to removed code/sections | Remove — git holds the history |
Brief Example - Missing vs. Complete:
// BAD: No documentation on complex function
export function calculateProratedAmount(plan: Plan, startDate: Date, endDate: Date): number;
// GOOD: Purpose, params, returns, edge cases documented
/**
* Calculates prorated billing amount when switching plans mid-cycle.
* @param plan - The new plan to prorate to
* @returns Prorated amount in cents (can be negative for downgrades)
*/
export function calculateProratedAmount(plan: Plan, startDate: Date, endDate: Date): number;
2. API Documentation Issues
| Issue | Problem | Fix |
|---|---|---|
| Missing params | Callers don't know valid values | Document all params with types and constraints |
| Missing returns | Return shape unknown | Describe return structure and units |
| Missing errors | Callers don't know what to catch | List all thrown error types |
Brief Example - Incomplete vs. Complete:
// BAD: No params, no errors documented
/** Creates a subscription. */
async function createSubscription(userId: string, planId: string): Promise<Subscription>;
// GOOD: Full contract documented
/**
* @param userId - User's unique identifier
* @param planId - Plan ID from /plans endpoint
* @throws {UserNotFoundError} If userId doesn't exist
* @throws {PlanNotFoundError} If planId doesn't exist
*/
async function createSubscription(userId: string, planId: string): Promise<Subscription>;
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.
- yesterday First seen · 127 lines · 21 tokens per session scan A 3b52c97746d9
documentation is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,055 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-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。.
verify-module
模块完整性校验关卡。扫描目录结构、检测缺失文档、验证代码与文档同步。当用户提到模块校验、文档检查、结构完整性、README检查、DESIGN检查时使用。在新建模块完成时自动触发。.