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 skills add petrkindlmann/qa-skills --skill qa-startgit clone --depth 1 https://github.com/petrkindlmann/qa-skillsWrote 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/petrkindlmann/qa-skills/qa-start)<a href="https://agentmods.dev/skills/petrkindlmann/qa-skills/qa-start"><img src="https://agentmods.dev/badge/skills/petrkindlmann/qa-skills/qa-start/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/petrkindlmann/qa-skills/qa-start"><img src="https://agentmods.dev/badge/skills/petrkindlmann/qa-skills/qa-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00130 | $0.01689 |
| Opus 5 | $0.00065 | $0.00844 |
| Sonnet 5 | $0.00026 | $0.00338 |
| Haiku 4.5 | $0.00013 | $0.00169 |
Grade A, and why
qa-start 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 9d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use This
Reach for qa-start whenever the answer to "where do we start with QA?" is unclear and no QA foundation exists yet:
- A brand-new project with no test infrastructure.
- Joining an existing codebase that has no QA setup at all — old code, but quality work was never formalized. Still
qa-start, notqa-project-bootstrap(that one is for joining a team that already has tests). - Rebooting QA after neglect — tests deleted, coverage collapsed, no strategy. You are rebooting QA from the foundation up.
If the codebase already has a real test suite and you are a QA engineer ramping onto the team, use qa-project-bootstrap instead.
Quick Route
Pick your entry point — skip any step whose artifact already exists.
| Situation | Start at |
|---|---|
| No QA at all (no context file, no strategy, no plan) | Step 1 |
.agents/qa-project-context.md already populated |
Skip Step 1 — invoke test-strategy (Step 2) |
| Context file AND strategy document both exist | Skip Steps 1 and 2 — invoke test-planning (Step 3) |
| All three done — what next? | After Step 3 |
| A QA engineer ramping onto an existing team with existing tests | Not this skill — see qa-project-bootstrap |
Step 1: Capture Project Context
Skill: qa-project-context
Creates .agents/qa-project-context.md in your project root. That file records your tech stack, test frameworks, CI/CD pipeline, environments, coverage goals, risk areas, and team structure. Every later skill reads it, so it never asks you the same questions twice.
What to do: Invoke qa-project-context and work through its discovery questions. The skill walks each section interactively, discovers what it can from the repo, and writes the file.
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.
- 9d ago First seen · 110 lines · 130 tokens per session scan A 6121480bb12c
qa-start is a skill published in the GitHub repository petrkindlmann/qa-skills (114 stars, last pushed 3mo ago), licensed MIT. It adds 130 tokens to every session and 1,689 once invoked, about $0.0006 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
meter-compare
Compare CocoMeter accuracy and cost results with correctness-first ordering. Usage: $meter compare .
test
Enter the Test phase of CocoBrew. Reads spec.md test requirements, generates test cases, executes SQL validation and quality checks, records results in test.md. Can be re-run without full rebuild. Requires Build phase completion.
afrexai-react-production
Complete methodology for building production-grade React applications with architecture decisions, component design, state management, performance optimization, testing, and deployment.
Vibe Coding Mastery
The complete operating system for building software with AI. From first prompt to production deployment — prompting frameworks, architecture patterns, testing strategies, debugging playbooks, and production graduation checklists. Works with Claude Code, Cursor, Windsurf, Copilot, and any AI coding tool.
contract
Outcome-driven Cortex function development — declares a behavioral contract before generation begins, enforces evidence-tiered proof before $ship, and defends against the self-oracle evaluation failure mode.
Angry User Simulator
Simulate aggressive user behavior patterns including rapid clicking, random navigation, form abuse, tab spamming, and unexpected interaction sequences to find UI resilience issues.