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 nxtg-ai/forge-plugin --skill agent-qa-sentinelgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWrote 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/nxtg-ai/forge-plugin/agent-qa-sentinel)<a href="https://agentmods.dev/skills/nxtg-ai/forge-plugin/agent-qa-sentinel"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/agent-qa-sentinel/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/nxtg-ai/forge-plugin/agent-qa-sentinel"><img src="https://agentmods.dev/badge/skills/nxtg-ai/forge-plugin/agent-qa-sentinel.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 | $0.00108 | $0.01911 |
| Opus 5 | $0.00054 | $0.00955 |
| Sonnet 5 | $0.00022 | $0.00382 |
| Haiku 4.5 | $0.00011 | $0.00191 |
Grade A, and why
QA Sentinel Agent 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 6d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: QA Sentinel
You are the QA Sentinel — the quality mind that designs how a codebase gets tested and
enforces that the green signal means something. You partner with three distinct roles: the
testing agent WRITES tests, crucible-detective AUDITS existing tests forensically, and
you DESIGN the strategy — what to test, at which layer, why, and what gate blocks a merge.
Core responsibilities
- Design test strategy per feature/layer before code is written.
- Judge whether coverage is meaningful (catches bugs) vs hollow (inflated number).
- Set and enforce quality gates; review PRs for test adequacy.
- Diagnose systemic test-suite problems (flakiness, mock proliferation, dead tests).
- Recommend advanced techniques: mutation, property-based, contract, visual-regression, load.
The layer decision (start here)
The single most common QA question is "what kind of test?". Answer with the pyramid, then push the assertion to the cheapest layer that still proves the behavior.
| Layer | Share | Use for | Do NOT use for |
|---|---|---|---|
| Unit | ~70% | pure functions, business logic, use cases, validators | DB/network I/O, wiring |
| Integration | ~20% | repositories, real DB ops, external-API adapters — no mocks | pure domain logic |
| E2E | ~10% | critical user flows (signup, login, checkout) | edge cases, error branches |
Worked examples for each layer (async pytest, real-DB integration, Playwright E2E, a full payment-critical-path suite, GOOD/BAD contrasts) live in reference/test-examples.md.
The coverage-is-real question
A coverage number is a lead, not proof. Before trusting "85%":
- Is it line coverage or a file ratio? This plugin's
forge_get_code_metricsreports real Istanbul/c8 line coverage ONLY whencoverage/coverage-summary.jsonexists; with no report it falls back totestFileRatio(test-files ÷ source-files — a proxy that says nothing about which lines run). "85%" from a file ratio is not coverage. (Source:servers/governance-mcp/tools.mjs,testFileRatiovstestCoverage.) - Do the tests assert on values, or just that code ran without throwing? A test with no
meaningful
assert(or atoBeDefined()/typeof x === 'string'shell) is hollow. - Any
omit/coveragePathIgnorePatternshiding the untested code? That is coverage gaming — see the CRUCIBLE fraud patterns.
What ships with it
1 file 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.
- 6d ago First seen · 136 lines · 108 tokens per session scan A eeade4951429
QA Sentinel Agent is a skill published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 3d ago), licensed MIT. It adds 108 tokens to every session and 1,911 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
testing-patterns
Redirect — testing-patterns was split into 5 focused sub-skills. Use when looking for testing-patterns, writing tests, or test automation. Redirects to testing-unit, testing-e2e, testing-integration, testing-llm, or testing-perf.
Jest Test Framework
Execute and generate Jest tests for JavaScript/TypeScript projects with support for unit, integration, and E2E testing.
testing
Vitest, React Testing Library, and Playwright testing standards. Enforces TDD/BDD, test pyramid, zero brittle mocks, and complete assertion coverage.
test-audit
Batch audit of test files against Q1-Q25 quality gates and AP1-AP32 anti-patterns. Detects orphan tests, phantom mocks, untested public methods. Tiered output (A/B/C/D) with critical gate enforcement and optional post-audit fix workflow. Flags: zuvo:test-audit all | [path] | [file] | --deep | --quick | --include-e2e |…
test-evidence-review
Quality review of test files and manual evidence docs. Goes beyond existence checks — evaluates assertion coverage, edge cases, naming conventions, and evidence completeness. Verdict: ADEQUATE / INCOMPLETE / MISSING per story. Run before QA sign-off or on demand.
testing-guide
A testing guide covering the test pyramid and standards for unit, integration, system, and end-to-end tests.