Borrowing it
Nothing to install: this file belongs to mindroom-ai/mindroom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mindroom-ai/mindroom/main/.claude/skills/live-test/SKILL.mdgit clone --depth 1 https://github.com/mindroom-ai/mindroomWrote 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/mindroom-ai/mindroom/live-test)<a href="https://agentmods.dev/skills/mindroom-ai/mindroom/live-test"><img src="https://agentmods.dev/badge/skills/mindroom-ai/mindroom/live-test/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/mindroom-ai/mindroom/live-test"><img src="https://agentmods.dev/badge/skills/mindroom-ai/mindroom/live-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Rogue Agent · line 54 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00085 | $0.01167 |
| Opus 5.5 | $0.00034 | $0.00467 |
| Sonnet 5.5 | $0.00017 | $0.00233 |
| Haiku 4.5 | $0.00009 | $0.00117 |
Grade A, and why
live-test 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live Test
Run the real product and collect runtime evidence.
⚠️ NixOS Environment
On NixOS hosts, run commands inside the repo Node.js 24 dev shell so libstdc++.so.6 is available.
Without it, numpy fails to import and you get AttributeError: module 'mindroom' has no attribute 'bot'.
nix-shell shell.nix
# then run normally inside the shell:
uv run pytest ...
uv run mindroom run
If nix-shell shell.nix cannot resolve <nixpkgs>, use:
nix-shell -I nixpkgs=/nix/var/nix/profiles/per-user/root/channels/nixos shell.nix
See references/core-mindroom.md for details.
The root shell includes Linux Chromium only on Linux so the backend and Node.js tools also work on macOS.
Workflow
- Choose the surface you need to test.
- For the core MindRoom runtime, local Matrix, Matty, and bundled dashboard, read references/core-mindroom.md.
- For the core frontend screenshot flow, frontend-only dev server, SaaS sandbox, and platform frontend screenshots, read references/frontend-and-platform.md.
- Prefer isolated local runs when the worktree or machine is already busy.
- Existing local instances often collide on ports, Matrix usernames, room aliases, and dashboard API ports.
- If you see conflicts, create an isolated config, set a unique
MINDROOM_NAMESPACE, use a uniquemindroom_user.username, isolateMINDROOM_STORAGE_PATH, and choose a non-default--api-port. - If the isolated run writes its own
.env, inspect it before hitting authenticated/api/*routes because it may contain the instance-specificMINDROOM_API_KEY. - Keep config, storage, logs, transcripts, and snapshots in an isolated persistent directory under
.baspowers/sdd/or~/.codex/worktrees/. - If you create
.baspowers/sdd/yourself, add a.gitignorecontaining*to it so no evidence can be committed. - Do not put live-test evidence in a temporary directory.
- Verify behavior, not just startup.
- For chat flows, send a real message and inspect the actual reply thread.
- For backend changes, hit the live endpoint on the same instance you started.
- For frontend changes, capture screenshots and inspect the generated PNGs.
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.
- 9d ago Changed · +24 lines 9bcaf3f82bc8
- 1mo ago First seen · 56 lines · 85 tokens per session scan A d744eed8419d
live-test is a skill published in the GitHub repository mindroom-ai/mindroom (346 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,167 once invoked, about $0.0003 per session on Opus 5.5. 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
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…