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 CES-Ltd/TitanX --skill star-office-helpergit clone --depth 1 https://github.com/CES-Ltd/TitanXWrote 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/ces-ltd/titanx/star-office-helper)<a href="https://agentmods.dev/skills/ces-ltd/titanx/star-office-helper"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/star-office-helper/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/ces-ltd/titanx/star-office-helper"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/star-office-helper.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00082 | $0.02010 |
| Opus 5 | $0.00041 | $0.01005 |
| Sonnet 5 | $0.00016 | $0.00402 |
| Haiku 4.5 | $0.00008 | $0.00201 |
Grade B, and why
star-office-helper scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Your job is to DO it, not to TEACH it.** Execute every command yourself using your tools. Your response must never contain commands for the user to copy-paste or steps for the user to follow. If the user sees a shell How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Star Office Helper
Guide users from zero to usable visualization integration in Aion. Prefer Star-Office-UI first, then provide alternatives only when requested or when Star Office does not fit.
What is Star Office
Star Office UI is a third-party open-source local visualization companion for OpenClaw / Aion.
- Project: https://github.com/ringhyacinth/Star-Office-UI
- It turns chat-side agent status (idle / writing / researching / executing / syncing / error) into a live, interactive office-themed monitor view.
- It is not built-in to Aion — it runs as a separate local service (default
http://127.0.0.1:19000). - OpenClaw works independently without Star Office; Star Office only animates when its own backend+frontend and event bridge are active.
Capabilities when connected:
- Real-time visualization of conversation state changes
- Interactive office scene that reflects agent activity
- Live monitor accessible via the TV icon in the chat header
When a user asks "what is Star Office" or triggers the install flow, introduce it clearly with the above context before proceeding.
Connection Guidance
When Star Office is already detected on the local machine:
- Confirm the detected URL (e.g.
http://127.0.0.1:19000). - Guide the user to click the TV icon in the chat header to open the live monitor.
- Explain available interactions: real-time status view, office scene animation.
- If connection fails despite detection, enter troubleshooting (check port, process, auth, logs).
When Star Office is not detected:
- Follow the Install Workflow below.
- After install completes, guide the user to verify via the TV icon.
Workflow
- Confirm objective:
- Install and run a visualization companion locally (default: Star-Office-UI).
- Connect Aion preview/monitor URL to a running visualizer service.
- Diagnose why UI does not animate or shows
Unauthorized.
- Run environment diagnosis first:
- Execute
skills/star-office-helper/scripts/star_office_doctor.sh. - If
python3 -m pip installfails withexternally-managed-environment, switch to venv flow.
What ships with it
5 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.
- 12d ago First seen · 168 lines · 82 tokens per session scan B 263ff0bef80b
star-office-helper is a skill published in the GitHub repository CES-Ltd/TitanX (48 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 2,010 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ops-desk
Operate a project, workspace, or account from an agent or manager dashboard: inspect state, triage risks, prepare governed actions, route to the right skill lane, require approvals for consequential acts, and verify receipts after execution.
sourcey
Generate documentation for a project using Sourcey.
business-ops
Route one business signal through a replayable governed ops graph: classify, docs, release, work, outreach, spend, and proof, with consequential actions stopping at the right gate.
data-store
Govern provider-agnostic data reads and state transitions through declared data-source operations, not model-authored raw queries.
ledger
Answer a cross-run audit question against the receipt ledger, returning matched receipts and a chain-verification result.
audit-receipt
Audit a sealed runx receipt for governance, comparing exercised authority and any declared approval requirement with signed evidence, and flag over-reach, approval inconsistency, unrecorded refusals, or exposed secret material.