Borrowing it
Nothing to install: this file belongs to hlalljie/agent-workflow-presets. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hlalljie/agent-workflow-presets/main/.cursor/skills/testing/run-tests/SKILL.mdgit clone --depth 1 https://github.com/hlalljie/agent-workflow-presetsWrote 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/hlalljie/agent-workflow-presets/run-tests)<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/run-tests"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/run-tests.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00058 | $0.00857 |
| Opus 5 | $0.00029 | $0.00428 |
| Sonnet 5 | $0.00012 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
testing-run-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 8d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run tests
Job
Execute automated + manual steps aligned with the test plan (add tests), without ad-hoc skips unless the plan marks N/A.
Strong default: If the diff changes UI or could regress what users see on a route (shared shell, layout, widgets, styles, client navigation), treat manual browser checklists as expected, not optional—add or extend tests/manual/*.md when no checklist exists yet (write manual browser test).
Before running
- Open the test plan —
### Test planin the task file and/ortests/plans/*.md. - If missing but tests exist, run
npm testand note plan gap in the report.
Dev vs preview (Next.js)
npm run dev— Fast iteration; Turbopack, HMR. Good while building the slice (including quick manual smoke if the checklist allows a temporary dev URL).npm run build+npm run start— production-like behavior. Anything that can differ between dev and prod (bundling, SSR, env) should be checked here before the slice is "done."
During run task loop: Vitest always; manual steps may use dev first for speed, but before handoff run the same checklist (or critical path) against preview if the doc's Start state uses start—otherwise align the doc.
During verify commit: Automated checks already run build; manual browser passes should use preview (Start state in the doc), and spot-check in dev only as extra, not instead of preview.
Order (default)
- Targeted Vitest —
npx vitest run <paths…>for files listed in the plan (fast signal). - Full Vitest —
npm testwhen the slice can affect shared code or you need full regression. - Feature smoke — project-specific regression scripts (see
package.json). Run any that cover the areas you touched. - Manual browser — spawn a subagent using
[MODEL:browser-tester]for eachtests/manual/*.mdtied to the plan, following run manual browser test (Start state, then procedure). For UI- or shell-related work, skipping this step is not a default win—report BLOCKED only when the environment truly prevents it (no server, no browser tool, auth wall). - Build —
npm run buildwhen verifying types/integration.
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.
- 8d ago First seen · 50 lines · 58 tokens per session scan A d5a869f11fb4
testing-run-tests is a skill published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 857 once invoked, about $0.0003 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
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
ui-aqa-flow
Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
qa
Visual + a11y QA — screenshot-first critique, contrast, touch targets, mockup-vs-impl diff. For adversarial logic checks use /verify. Triggers "visual QA", "QA check", "does this look right", "a11y check", "contrast check", post-component changes.
verify
Adversarial verification — three competing agents (issue-finder, disprover, judge). Triggers "verify", "double check", "are you sure", "poke holes"; pre-prod, post-critical-fix.