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 Evyasys-Software-Solutions/EvyaGovernance --skill evyasys-qagit clone --depth 1 https://github.com/Evyasys-Software-Solutions/EvyaGovernanceWrote 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/evyasys-software-solutions/evyagovernance/evyasys-qa)<a href="https://agentmods.dev/skills/evyasys-software-solutions/evyagovernance/evyasys-qa"><img src="https://agentmods.dev/badge/skills/evyasys-software-solutions/evyagovernance/evyasys-qa/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/evyasys-software-solutions/evyagovernance/evyasys-qa"><img src="https://agentmods.dev/badge/skills/evyasys-software-solutions/evyagovernance/evyasys-qa.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 | $0.00000 | $0.01659 |
| Opus 5.5 | $0.00000 | $0.00664 |
| Sonnet 5.5 | $0.00000 | $0.00332 |
| Haiku 4.5 | $0.00000 | $0.00166 |
Grade A, and why
evyasys-qa 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 17d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: evyasys-qa
/evyasys:Qa merges StartQa + FinishQa + GenerateReleaseNote with whole-application regression planning. One command, five modes:
| Mode | Purpose | Typical use |
|---|---|---|
plan |
Build / extend the workbook — application, modules, or one feature | /evyasys:Qa plan Vendor Management |
run |
Execute cases and record results with date, environment and build | /evyasys:Qa run --env dev |
signoff |
Story gates: In QA at start, Done at the end, release notes | /evyasys:Qa signoff EVYA-1042 |
audit |
Consistency scan (UI + back end) and Playwright upkeep | /evyasys:Qa audit |
release |
Compile signed-off stories into one branded PDF release document (grouped by epic, gates consolidated, version proposed from history) | /evyasys:Qa release EVYA-1042 EVYA-1043 |
Flags: --env <name>, --url <url>, --specs (generate / update Playwright).
What makes it trustworthy
- No data on production — enforced in code, not by prompt.
scripts/lib/qa-env.jsclassifies every environment;local,devandtestaccept writes only when registered,stagingonly withallowWrites: true,prodand anything unregistered never.qa-http.jsis the only way the agent calls an API; it refuses disallowed writes, never logs tokens, and records every call. The hook converts any Pass/Fail the agent claims for a data-writing case on a read-only environment into Skipped, and the generated Playwright fixture aborts non-read requests there. - Static first. Cases carry a Verified By basis:
static-rule/static-data(read from the code, nothing created) →read-only(observed on existing data) →live-write(minimum QA_AUTO_ records on a writable non-production environment; tracked in.evyasys/qa/ledger.jsonand blocking sign-off until removed). The Data Rules sheet lists what static rules replaced. - History in the file. Last Passed On and Passed In Env(s) on every case; Run History is append-only; Environments and Summary show the latest outcome per environment. Edits you make in Excel are read back and kept; a case whose definition changes resets to Not Run.
- One bug per root cause, only when you approve. Failures are clustered (same defect key, or same endpoint + error). Each cluster is a
draft with reproduction, expected/actual, linked cases, endpoints, suspected files, evidence and an AI-assisted-fix context in
.evyasys/qa/defects/<runId>.md. The hook asks per cluster; approval files one work item with every linked case. - Release readiness for managers. Every run ends with GO / CONDITIONAL / NO-GO and the reasons (
qa-readiness.js): failing P0/P1 = NO-GO; an unpassed P0, under 80% executed, an untouched module, leftover test data or results older than 14 days = CONDITIONAL. It also shows how much of the confidence is static versus observed on a running app. - Sign-off is computed.
scripts/lib/qa-signoff.js: every case has an outcome, no open severity 1–2 defect, every acceptance criterion passed or waived with a follow-up story, every applicable domain gate passed, no QA test data left behind. Otherwise the story stays In QA. - Consistency module.
scripts/lib/consistency-scan.jsfinds the shared UI/back-end parts and the tokens in use, then reports hard-coded colours/fonts/sizes, inline styles, raw buttons, mixed response shapes, key casing and pagination names per module.
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.
- 17d ago First seen · 70 lines · 0 tokens per session scan A d0a3e641b2c4
evyasys-qa is a skill published in the GitHub repository Evyasys-Software-Solutions/EvyaGovernance (7 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,659 tokens. 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 2026-10-08.
Other skills, from other repositories
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…
test-conversion-reviewer
Reviewer for converting unit tests to browser tests for Project Bedrock. Invoke this when the user needs to review their work while removing complex Browser dependencies from tests.
playwright-e2e-review
Audit Playwright E2E tests in the gc.platform suite (tests/playwright) against the four hard rules — no mocks, Page Object Model, work-by-fixture, one folder per frontend feature module — plus strict-TypeScript quality. Use whenever the user wants to review, check, audit, or "make sure it follows the conventions" for…
test-case-coverage
Audits an already-automated test case (TC-XXX) — one end-to-end journey across several use cases — against its document and reports a coverage matrix: which Flow rows, Validation items, and postconditions have a test step and code behind them, which are still open, and which test steps have drifted away from the test…
full-stack-e2e-review
Run a rigorous end-to-end product or feature review across architecture, data, APIs, permissions, billing, tests, and real browser UX. Use for requests such as review this branch end to end, test everything, ensure no bugs, perform a full visual pass, or validate a multi-user workflow before merge or deploy.
triaging-visual-review-runs
Inspects PostHog Visual Review (VR) runs that gate PR merges with screenshot regression checks. Use when the user mentions "visual review", "VR", "snapshot diff", "screenshot test", "storybook regression", "playwright snapshot", "quarantine", asks why a PR is blocked or what changed visually, wants to triage the VR…