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/qanpx skills add dean0x/devflow --skill qagit 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 | $0.00031 | $0.01381 |
| Opus 5 | $0.00015 | $0.00691 |
| Sonnet 5 | $0.00006 | $0.00276 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
qa scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| HTTP status | Response code from curl/fetch | API endpoints | How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Patterns
Scenario-based acceptance testing methodology. Ensures implementations satisfy user-observable requirements beyond what unit tests cover.
Iron Law
VERIFY BEHAVIOR FROM THE USER'S PERSPECTIVE [1][2]
Test what the user asked for, not implementation details. Every acceptance criterion gets at least one scenario. Every scenario produces observable evidence. If you can't demonstrate it works from the outside, it doesn't work. [3][8]
Scenario Types [1][2][6]
Five categories ensure comprehensive coverage:
| Type | Purpose | Example |
|---|---|---|
| Happy path | Core functionality works as described | "Add item → item appears in list" |
| Boundary/edge | Limits, empty, maximum, minimum values | "Add item with 1000-char name → truncated or rejected" |
| Negative path | Invalid inputs, missing permissions, errors | "Add item without auth → 401 returned" |
| Integration | Components work together correctly | "Add item → appears in search results" |
| Regression | Existing behavior preserved after changes | "Old items still load after schema migration" |
Minimum coverage: At least one scenario per acceptance criterion. At least one boundary and one negative scenario per feature. [1][6]
Scenario Design from Acceptance Criteria [4][8][9]
Extract testable claims using Given/When/Then:
Acceptance criterion: "Users can upload files up to 10MB"
S1 (happy): Given auth user, When upload 5MB file, Then 200 + file accessible
S2 (boundary): Given auth user, When upload 10MB file, Then 200 (exact limit)
S3 (boundary): Given auth user, When upload 10.1MB file, Then 413 rejected
S4 (negative): Given no auth, When upload 5MB file, Then 401
S5 (negative): Given auth user, When upload empty file, Then 400
Extracting criteria [4]: If no explicit acceptance criteria, derive from the request:
- What new behavior was requested? → happy path scenarios
- What inputs does it accept? → boundary scenarios [7][10]
- What should it reject? → negative scenarios
- What existing behavior must survive? → regression scenarios
What ships with it
5 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 · 137 lines · 31 tokens per session scan A 4331908ca167
qa is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 1,381 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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。.