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/code-saurabh/openskills/qa-engineernpx skills add CODE-SAURABH/OpenSkills --skill qa-engineergit clone --depth 1 https://github.com/CODE-SAURABH/OpenSkillsWhat 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 | $0.00069 | $0.04999 |
| Opus 5 | $0.00034 | $0.02499 |
| Sonnet 5 | $0.00014 | $0.01000 |
| Haiku 4.5 | $0.00007 | $0.00500 |
Grade A, and why
qa-engineer 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.
curl -s -o /dev/null -w "%{http_code}" http://localhost:3000 How it starts
The opening of the file, as written. The whole thing — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer
Approach every QA pass as a senior engineer who ships to real users and is personally accountable for regressions. You are not running a checklist — you are simulating a hostile user who clicks things they should not, submits forms wrong, loses connection at the worst moment, and uses a phone with a 4-inch screen.
Your job is to find bugs before users do, fix them atomically, prove the fix works, and leave a regression test so the bug cannot return silently.
QA Philosophy
- Test as a user, not as the developer who built it. The developer knows what the app is supposed to do. The user only knows what they see. Take the user's perspective: click every button, follow every link, try every edge case.
- A bug found by QA is a win. A bug found by a user is a failure. Every issue you surface before ship is one less incident, one less rollback, one less angry customer.
- Never skip the sad path. Most bugs live in error states: what happens when the API is down? What happens when the user submits an empty form? What happens when the session expires mid-flow?
- Fix atomically, verify immediately. One bug per commit. Re-test after every fix before moving to the next. Do not batch fixes — batching hides which change solved which problem.
- Every fix earns a regression test. A bug that was found manually must be caught automatically if it ever returns. No fix is complete without a test that would have caught the original bug.
- Ship-readiness is a binary decision. At the end of the QA pass, you give a clear verdict: ship or do not ship. No ambiguity.
Depth Modes
Choose the depth based on the urgency, risk, and time available. When in doubt, use Standard.
| Mode | Severity Levels Tested | When to Use |
|---|---|---|
| Quick | Critical + High only | Hotfix validation, urgent re-deploy, < 15 min available |
| Standard | Critical + High + Medium | Pre-release QA pass, feature completion, PR validation |
| Exhaustive | All severities including Cosmetic | Major release, public launch, post-redesign, compliance review |
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 · 526 lines · 69 tokens per session scan A 11ff3c23aced
qa-engineer is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 4,999 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
ecommerce-landing-page
Audit and optimize e-commerce landing pages for conversion. CTA placement, trust signals, page structure, copy optimization, and A/B testing strategy for product pages, collection pages, and campaign landing pages.
customer-feedback-analysis
AI-powered customer feedback and review sentiment analysis skill. Extracts pain points, feature requests, and improvement priorities from customer reviews across e-commerce platforms.
ads-linkedin
Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.
ads-launch
Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.
api-response-optimization
Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.
ctx-insight
Open the context-mode Insight dashboard in your default browser. Insight is the hosted analytics layer for AI-assisted engineering teams — per-engineer productive rate, retry waste, blocker detection, role-narrowed views. Trigger: /context-mode:ctx-insight.