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/lukedj78/dev-flow/write-testsnpx skills add lukedj78/dev-flow --skill write-testsgit clone --depth 1 https://github.com/lukedj78/dev-flowWhat 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 | $0.00165 | $0.02627 |
| Opus 5 | $0.00082 | $0.01314 |
| Sonnet 5 | $0.00033 | $0.00525 |
| Haiku 4.5 | $0.00016 | $0.00263 |
Grade A, and why
write-tests 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-tests — generate tests for one file at a time
This skill writes the test file that should sit next to a piece of source code. One invocation = one source file → one test file. It does not install test infrastructure (that's module-add test), does not debug failing tests (that's superpowers:systematic-debugging), and does not run an HTTP-based QA pass (that's qa).
The unit of work is deliberately small because tests rot when they're auto-generated in bulk. A single file at a time forces the user to read what was written and accept it before moving to the next.
When this skill applies
- The user names a source file: "scrivi i test per
lib/server/clienti.ts", "test perapp/checkout/page.tsx", "e2e per /scadenze". - The orchestrator routes here from
module_added(test infrastructure exists) when the user wants per-feature coverage. - The project has a wired test stack —
meta.json#stack.testis set, ORvitest.config.ts+playwright.config.tsexist at the root.
Contract
This skill follows the dev-flow contract — see references/contracts.md. Key facts:
- Reads
<root>/.workflow/meta.json#stack.testto confirm the test framework is wired. - Reads the project's existing
vitest.setup.ts,vitest.config.ts,playwright.config.ts, and any sibling test files to learn the mocking style — does not re-prescribe patterns from scratch. - Writes a single test file alongside the source (
__tests__/<name>.test.tsfor unit,e2e/<name>.spec.tsfor e2e). - Does NOT bump
phase— tests are continuous work, not a phase transition. - Appends to
meta.json#historywith the source file path, the test path, and the test type. - Idempotent: if the test file already exists, ask the user — either regenerate, append missing cases, or abort. Never silently overwrite.
Workflow
Step 1 — Verify prerequisites
Read <project-root>/.workflow/meta.json:
stack.testmust be set (e.g.,"vitest+playwright"). Ifnull, stop and tell the user: "Test infrastructure not wired. Runmodule-add testfirst, then come back."phaseshould bemodule_addedor later. If earlier, the project might not have anything testable yet — warn and ask whether to proceed.
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.
- 2d ago First seen · 161 lines · 165 tokens per session scan A 8d297b5afcc4
write-tests is a skill published in the GitHub repository lukedj78/dev-flow (5 stars, last pushed 4d ago), licensed MIT. It adds 165 tokens to every session and 2,627 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
analyze-performance-traces
Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…
test-automation
Execute Vitest and Playwright test suites with result collection and failure analysis.
moai-domain-frontend
Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture. Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management.
moai-domain-html-report
Markdown-to-single-file-HTML report renderer. Six modes (status, incident, plan, explainer, financial, pr) selected by report type, crossed with three audience tiers (expert, basic, learn) derived from the active output style. The basic and learn tiers enrich the HTML with mermaid flowcharts, worked examples, and…