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 HoangNguyen0403/agent-skills-standard --skill quality-engineering-flaky-triagegit clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/quality-engineering-flaky-triage)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/quality-engineering-flaky-triage"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/quality-engineering-flaky-triage/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/hoangnguyen0403/agent-skills-standard/quality-engineering-flaky-triage"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/quality-engineering-flaky-triage.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00071 | $0.00820 |
| Opus 5.5 | $0.00028 | $0.00328 |
| Sonnet 5.5 | $0.00014 | $0.00164 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
quality-engineering-flaky-triage 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Engineering: Flaky Triage
Priority: P0 (CRITICAL)
Entry
Only a QUARANTINE_CANDIDATE verdict enters triage: the test fails intermittently across isolated reruns with no code change between runs. A deterministic failure is REAL_BUG_DO_NOT_HEAL and goes to dev-fix, never here.
Quarantine Contract
- Quarantine means the test still runs, its result is reported, and it does not gate merge; it never means
test.skip. - Every quarantined test carries a ticket with an owner and an expiry of at most 14 days. No ticket, no quarantine.
- On expiry: fixed and un-quarantined, or expiry extended once with a written reason, or the test is deleted with the coverage gap recorded in the coverage report. Silent expiry is forbidden.
- Record each entry in
flake_quarantine[]as{test, ticket, expiry, bucket}sotest-loopcarries it in its handoff.
Root-Cause Buckets
ORDER_DEPENDENCE · SHARED_STATE · TIMING · ENVIRONMENT · DATA · PRODUCT_NONDETERMINISM. Assign exactly one from the evidence in Root-Cause Buckets; UNKNOWN is allowed only with the reruns that were tried.
Evidence Required
Run the test alone 10 times sequentially in the foreground. Record pass count, the failing run's artifact, and whether the failure reproduces with a fresh environment. Fewer than 10 isolated runs is not evidence; a pass on plain CI rerun is not evidence.
Un-quarantine
A test leaves quarantine only when the root cause is fixed and it passes 10 consecutive isolated green runs after the fix. Retries, longer timeouts, or a wider matcher are not fixes; they hide the bucket.
Reliability Impact
Each flaky test counts against suite_reliability_pct in quality-engineering-automation-health until its root cause is fixed; quarantine removes its reds from the merge gate, not from the report. State the quarantine count and the oldest expiry next to release_confidence.
Red Flags
"just add retries: 3" · "skip it for now, we'll come back" · "it passes locally" · "extend the expiry again" — each hides a bucket instead of naming it. Stop, run the 10 isolated reruns, assign the bucket.
What ships with it
4 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.
- 1mo ago First seen · 66 lines · 71 tokens per session scan A 43aec22376d7
quality-engineering-flaky-triage is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (582 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 820 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
browser-automation
Playwright browser automation via MCP. Covers E2E testing, UI review, web scraping, screenshot capture, and general browser interaction. MCP-first — CLI is fallback only.
vue-idioms
Vue 3 Composition API patterns: syntax, reactive state with Pinia stores, reusable composables, and Vitest component testing. Use when developing or refactoring Vue 3 frontend applications.
python-idioms
Modern Python (3.11+) idioms: type annotations, typing Protocols, Pydantic models, asyncio, pytest fixtures, and Ruff/Mypy strict compliance. Use when writing, refactoring, or reviewing Python applications, APIs, or scripts.
testability-patterns
Implementation examples for the three testability rules (I/O isolation, pure logic, dependency direction) across Go, TypeScript, Python, Rust, and Dart. Loaded by reference from architectural-pattern.md — not triggered by file patterns.
testing-strategy
Detailed testing reference material: test doubles strategy, integration test infrastructure (Testcontainers, Firebase emulator), naming conventions per language, test organization patterns. Load when writing tests or setting up test infrastructure. The core mandates (TDD, AAA, pyramid) are in the testing-strategy rule…
react-testing
React testing guidance using React Testing Library and modern patterns.