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/rome-os/rome/app_verificationnpx skills add rome-os/rome --skill app_verificationgit clone --depth 1 https://github.com/rome-os/romeWrote 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/rome-os/rome/app_verification)<a href="https://agentmods.dev/skills/rome-os/rome/app_verification"><img src="https://agentmods.dev/badge/skills/rome-os/rome/app_verification.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 5.1 | $0.00000 | $0.01407 |
| Opus 5 | $0.00000 | $0.00704 |
| Sonnet 5 | $0.00000 | $0.00281 |
| Haiku 4.5 | $0.00000 | $0.00141 |
Grade A, and why
app_verification 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 6d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Verification
Use this skill after app creation has finished commit and
system:app_management { op: "install", ... }. Your job is to verify the installed app
from runtime evidence, not from the creator's memory, assumptions, or
unverified claims.
The parent/creator should pass only the verification handoff:
appId<app-root>absolute path- packed artifact path, normally
<app-root>/.rome/artifact(daemon-managed output of amode: "source"install) - dashboard base URL and internal API base URL, if known
- the user's original intent and the expected happy path
- any required credentials or external connections already known to be missing
- safe sample inputs for actions/API calls, if the app needs inputs
If any of those are missing, infer what you can from <app-root> and the local
Rome runtime. Ask the parent only when the missing information would make the
verification misleading.
Verification contract
You are a verifier, not the author. Default to read-only inspection plus safe runtime probes. Do not edit the app, commit, install, or paper over failures. If you find a defect, report the exact symptom, evidence, and the smallest likely fix area.
Before testing behavior, establish the app shape:
- Read
<app-root>/app.yaml,.rome_store/rome_store.yamlwhen present,README.md, and relevant files undersrc/. - Identify declared surfaces:
web,api,actions,agents,skills,hooks, anddb. - Confirm the expected behavior from the handoff maps to those surfaces.
Required checks
1. Build and install evidence
From <app-root>:
pnpm build
git status --short
test -d .rome/artifact
test -f .rome/artifact/app.yaml
The build must pass. The working tree should be clean unless the handoff
explicitly says verification is happening before the final commit. The packed
artifact must exist: a mode: "source" install builds and packs into
.rome/artifact before installing, so its presence is evidence the install ran —
and its absence means the app was never installed from this source root.
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.
- 6d ago First seen · 157 lines · 0 tokens per session scan A ff6617b31cbf
app_verification is a skill published in the GitHub repository rome-os/rome (471 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,407 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 2026-08-30.
Other skills, from other repositories
langbot-testing
Test LangBot WebUI and core product flows with an automated browser and backend logs. Use when validating the configured LangBot frontend, pipeline Debug Chat, model provider setup and test buttons, bot and knowledge-base UI flows, or troubleshooting failed LangBot end-to-end tests.
sanity-check
Run the deferred AgentOS E2E smoke test from public npm packages. Use when the user asks to sanity check, smoke test, or verify a release works.
penguin-harness-manual-test
Use when standing PenguinHarness up to try a change by hand — launching the Web App, the desktop shell, the landing page or the docs site to click through it, screenshot it, or reproduce a report. Covers the four dev entry points and their ports, which data root each writes to, and the four ways a healthy setup looks…
gigacode-api-sanity
Compare GigaCode's OpenCode-compatible HTTP/SSE API with native OpenCode in isolated temporary workspaces. Use when asked to sanity-check, re-test, or manually validate Claude Sonnet streaming, multi-turn sessions, tool calls, permissions, file edits, cancellation, or post-cancel reuse.
local-test
Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.
senpi-qa
Manual QA harness for the senpi coding agent itself. MUST USE after changing packages/ai, packages/agent, packages/coding-agent, or packages/tui — a green typecheck and npm test are NOT QA. Drives the real CLI from source in an isolated sandbox (never touches /.senpi or real credentials) across four channels: remote…