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/open-software-network/os-clovy/agent-e2e-qanpx skills add open-software-network/os-clovy --skill agent-e2e-qagit clone --depth 1 https://github.com/open-software-network/os-clovyWrote 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/open-software-network/os-clovy/agent-e2e-qa)<a href="https://agentmods.dev/skills/open-software-network/os-clovy/agent-e2e-qa"><img src="https://agentmods.dev/badge/skills/open-software-network/os-clovy/agent-e2e-qa.svg" alt="Measured on agentmods" 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 | $0.00159 | $0.02780 |
| Opus 5 | $0.00079 | $0.01390 |
| Sonnet 5 | $0.00032 | $0.00556 |
| Haiku 4.5 | $0.00016 | $0.00278 |
Grade A, and why
agent-e2e-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 3d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent E2E QA
Use this skill to run the kind of QA a human would do with the product open: start Clovy, click through the affected workflow, observe the result, and leave evidence. This is an agent-assisted verification layer, not a substitute for deterministic unit, Rust, or CI tests.
Decision Tree
Pick the narrowest surface that proves the behavior.
- Web preview: Use
pnpm devand Browser for React-only flows, standalone preview pages, onboarding preview, HUD demo pages, and visual smoke tests that do not require real Tauri commands. The browser-surface technique (faking the Tauri IPC bridge, Playwright/CDP driving, screenshot suites, PR-embeddable GIFs) is owned by thebrowser-test-tauri-feskill — read it before driving this surface. - Background browser video: Use the bundled Playwright helper for web-reachable agent flows when the user is actively using the desktop or does not need to watch the run. This avoids foreground macOS screen capture. It may shim the Tauri shell while routing prompts through the isolated legacy Hermes QA dashboard.
- Native Tauri app: Use
pnpm tauri:devand Computer Use for WKWebView, native windows, tray/menu behavior, macOS permissions, dictation hotkeys, microphone/system audio, update prompts, and any flow that depends on Rust commands or sidecars. - External browser handoff: Use Chrome when the flow intentionally opens the user's real browser, such as OS Accounts login, checkout, account portal, or a page that depends on the user's browser session.
- Deterministic promotion: Recommend Playwright or Tauri WebDriver only after a flow is stable enough to run unattended. Do not add a dependency or CI job during a QA pass unless the user asked for that implementation.
If the requested flow touches payments, live accounts, OS permission prompts, microphone/camera/location access, or sends user data externally, get explicit confirmation at action time before performing that side effect.
What ships with it
3 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.
- 3d ago First seen · 260 lines · 159 tokens per session scan A 35b9d631c276
agent-e2e-qa is a skill published in the GitHub repository open-software-network/os-clovy (357 stars, last pushed 9d ago), licensed MIT. It adds 159 tokens to every session and 2,780 once invoked, about $0.0008 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
macparakeet-stt
Use when the user asks to transcribe audio or video, inspect or manage MacParakeet meeting recordings, search prior dictations/transcripts, or give an AI agent local speech-to-text tools on Apple Silicon.
verify-dictation
The canonical "prove VZT Flow actually works" checklist — the human hotkey test plus its automated equivalents. Use before claiming a dictation-pipeline change works, before a release, or when the user runs /verify-dictation.
release-murmur
Cut a signed, notarized macOS release of Murmur (Tauri 2 + Angular 22). The exact, proven step-by-step runbook — preflight gates → version bump (+ Cargo.lock sync) → QueaT commit → PR-merge to the murmur trunk (never direct-push) → rustup targets → stop dev → universal build → Developer-ID sign BY IDENTITY HASH (the…
ship-feature
Ship a Murmur feature through scope, isolated implementation, fresh adversarial and required security review, project gates, a QueaT commit, and a PR to murmur. Use the verifier-only Harness for risky, multi-step, or explicitly requested work; ordinary low-risk fixes keep the normal isolated-worktree route.
dreaming
Tryb kreatywnego śnienia o Murmurze — Codex nasiąka apką, wędruje po necie, kombinuje i WYMYŚLA co możemy dodać, nie jako suchy research tylko swobodne myślenie generatywne oparte o głębokie zrozumienie apki i o to, co akurat przyjdzie do głowy. Rozchodzi się szeroko (dużo dzikich pomysłów), skupia na iskrach, buduje…
retrieval-memory-brain
The MAP of Murmur's shipped retrieval + agent-memory stack by file:symbol (hybrid fusion, FTS5/vec0 schema, embedding models, the reranker seam, bitemporal facts, consolidation, the entity graph, the eval harness) plus the MEASURED gaps and the load-bearing invariants. Use for any task touching retrieval quality…