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 laurigates/claude-plugins --skill comfyui-pack-live-smokegit clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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/laurigates/claude-plugins/comfyui-pack-live-smoke)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/comfyui-pack-live-smoke"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfyui-pack-live-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/laurigates/claude-plugins/comfyui-pack-live-smoke"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfyui-pack-live-smoke.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 115 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00048 | $0.02291 |
| Opus 5 | $0.00024 | $0.01145 |
| Sonnet 5 | $0.00010 | $0.00458 |
| Haiku 4.5 | $0.00005 | $0.00229 |
Grade B, and why
comfyui-pack-live-smoke scanned grade B with 2 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 5d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
# restart the service (systemd: sudo systemctl restart comfyui.service; else however yours restarts) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Result **toasts** (`extensionManager.toast`, ~4 s `life`) vanish before you can assert | Don't assert on the transient toast. Assert on a **persistent** signal instead — an in-modal status banner, the re-rendered list, How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
comfyui-pack-live-smoke
A ComfyUI pack's just check (pytest + vitest + tsc + build) can be fully
green while the pack is broken in the running app, because the two
halves are tested in isolation: pytest stubs server/folder_paths, vitest
only covers DOM-free pure helpers, and the modal DOM + the frontend↔backend
contract (route names, JSON shapes, gating predicates) are exercised by
neither. Stand the pack up in a real ComfyUI and click through it (or
drive it headlessly over the API) before opening the registry/gitops PR.
This is where bugs that ship green actually surface.
Canonical break (
comfyui-touch-manager, 2026-06): every gate green, jsdom modal mount green — yet live in the running app the Install-from-URL button was disabled on the normal127.0.0.1setup. The frontend gated onconfig.allow_remote_installalone (the non-loopback env override) while the backend/installgate actually permits the clone whenis_loopback || override. The headline feature was dead in the common case; only a browser smoke caught it.
When to Use This Skill
| Use this skill when... | Use instead when... |
|---|---|
| Verifying a pack end-to-end in a running ComfyUI instance before opening a PR | Writing the pack's code in the first place -> comfyui-node-authoring |
| Confirming an edited/built workflow JSON actually runs | Editing the workflow JSON itself -> comfy-workflow-json |
Target host — COMFYUI_HOST
Every recipe below reads the target instance from the COMFYUI_HOST
environment variable, defaulting to 127.0.0.1:8188 (a local/CPU-fork
smoke). Set it in .claude/settings.local.json's env block (gitignored,
per-machine) to point at a different install without hardcoding a host in
any command:
{ "env": { "COMFYUI_HOST": "192.0.2.10:8188" } }
Lesson 1: frontend gating must mirror the backend gate's full predicate
When the backend enforces a security/permission gate, the frontend's show/enable/disable logic must replicate the entire predicate, not a convenient sub-flag. Gating on a partial predicate silently disables a feature in the case the backend would have allowed.
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.
- 5d ago First seen · 167 lines · 48 tokens per session scan B 89fa5cdb3386
comfyui-pack-live-smoke is a skill published in the GitHub repository laurigates/claude-plugins (58 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 2,291 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
flutter-skill
Automate and test Flutter applications — launch apps, inspect widgets, tap elements, enter text, scroll, swipe, take screenshots, validate state, and debug via Dart VM Service Protocol. Use when the user wants to run Flutter app tests, automate Flutter UI interactions, inspect widget trees, debug a running Flutter…
debugging
Playwright test debugging conventions for the scaffold — reading failure messages, classifying failure modes (TimeoutError, ZodError, strict-mode violation, locator not found, network errors, schema drift), the playwright.config.ts capture defaults (trace on-first-retry, screenshot only-on-failure, video…
quality-engineering-test-healing
Failure taxonomy and allowed/forbidden repairs for a failing E2E test. Use when a Playwright/Maestro/Detox/XCUITest/Espresso/Appium test fails and you must decide whether to repair the test or route to a real bug.