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 antoinedc/MantaUI --skill manta-e2e-smokegit clone --depth 1 https://github.com/antoinedc/MantaUIWrote 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/antoinedc/mantaui/manta-e2e-smoke)<a href="https://agentmods.dev/skills/antoinedc/mantaui/manta-e2e-smoke"><img src="https://agentmods.dev/badge/skills/antoinedc/mantaui/manta-e2e-smoke/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/antoinedc/mantaui/manta-e2e-smoke"><img src="https://agentmods.dev/badge/skills/antoinedc/mantaui/manta-e2e-smoke.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00102 | $0.02967 |
| Opus 5 | $0.00051 | $0.01484 |
| Sonnet 5 | $0.00020 | $0.00593 |
| Haiku 4.5 | $0.00010 | $0.00297 |
Grade A, and why
manta-e2e-smoke 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 12d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
manta-e2e-smoke
typecheck proves the code compiles. Unit tests prove isolated logic.
npm run build proves the bundle produces artifacts. NONE of them prove the
Electron app renders correctly in a real renderer with real IPC wiring.
This gate exists because an empty renderer, a crashed main process, or a layout regression (sidebar collapsed onto nothing, chat panel off-screen) all pass a green build and green unit tests. A text fetch cannot see any of these. A real Electron renderer can. This skill is that renderer.
PUSH YOUR BRANCH BEFORE RUNNING THIS GATE. The Electron launch below can hang (first-run download, a wedged renderer, no display teardown) long enough to trip multica's 30-min "no new messages" force-stop. If you ran this gate before
git push, that timeout discards your entire implementation — the workdir is ephemeral and the rerun starts from a cleanoriginclone. Permanta-pr-workflowstep 8, your committed work must already be onoriginbefore you get here. If it isn't,git push -u origin <branch>NOW, then run the gate. Push any post-gate fixes again afterward.
You CAN run this — do not claim you can't. Playwright's
electron.launchspawns the actual built app. On the FIRST call it does a one-time Electron fetch + launch (~15-30s) — that is normal init, not a failure; wait for it. "My sandbox has no Electron / no display" is FALSE for this runtime on Linux — Playwright handles the headless display internally. The ONLY legitimate "I couldn't run it" is a launch step that actually errors — capture and quote that exact error.
When to run
manta-frontend/manta-backend: before marking ANY change to:src/renderer/(ChatPanel, Terminal, Sidebar, Settings, App, ProvidersCard)src/preload/(IPC bridge surface)src/main/(IPC handlers, setup, transport)src/shared/(types consumed by renderer) Paste the result into theTest resultsblock. A green build does NOT prove the sidebar renders, the chat panel mounts, or the app didn't crash on load.
manta-pr-workflow/manta-handle-reviewer-return: when verifying a delivered frontend feature (the per-task "verify on dev" step). This is the check that makes "renders in Electron, confirm no crash" a REAL gate instead of an unenforceable instruction.
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.
- 12d ago First seen · 253 lines · 102 tokens per session scan A 5c9baa14005e
manta-e2e-smoke is a skill published in the GitHub repository antoinedc/MantaUI (12 stars, last pushed 6d ago), licensed MIT. It adds 102 tokens to every session and 2,967 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 2026-08-31.
Other skills, from other repositories
tmux-real-user-testing
A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
qa-testing
Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.