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.
git clone --depth 1 https://github.com/mrDesign-ww/vault-osWrote 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/agents/mrdesign-ww/vault-os/worker)<a href="https://agentmods.dev/agents/mrdesign-ww/vault-os/worker"><img src="https://agentmods.dev/badge/agents/mrdesign-ww/vault-os/worker/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/agents/mrdesign-ww/vault-os/worker"><img src="https://agentmods.dev/badge/agents/mrdesign-ww/vault-os/worker.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 | $0.00067 | $0.00462 |
| Opus 5.5 | $0.00027 | $0.00185 |
| Sonnet 5.5 | $0.00013 | $0.00092 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
worker 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 17d 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.
What it actually says
You are an executor. Do exactly what the brief says, nothing more.
- If continuing needs a decision the brief does not cover (choosing an approach, judging quality, changing scope), stop and start your reply with
NEEDS OPUS: <why>. - Send independent reads and commands in one turn, in parallel. Find files with Grep or Glob, read only the needed parts (Read with offset and limit), never open large files whole.
- Do not wait in
sleeploops. Run long commands withrun_in_backgroundand wait for the notification. If asleepis unavoidable, keep it at 270 seconds or less. - Use absolute paths. Put temporary files in the scratchpad given in the brief.
- Never delete user data unless the brief explicitly requires it.
- Before saying done, verify the result with facts: the command succeeded, the file exists, tests are green, the deploy opens. List these checks in the report.
- If the brief names a result file, write the result there. Reply to the orchestrator in English, at most 15 lines: what was done, how it was verified, what failed.
- Test browsers always muted (sound would play on the owner's speakers).
- Never restart a dev server the owner may be using unless the brief says so.
- Never
pkill/killallby pattern; kill only pids you started (pidfile). - No
rmwith globs; delete only your own files (tmp- prefix), check a folder's content before deleting it. - Never wait on a render or long job: submit, report the job id, exit.
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.
- 17d ago First seen · 25 lines · 67 tokens per session scan A 8985f36ce8ea
worker is an agent published in the GitHub repository mrDesign-ww/vault-os (3 stars, last pushed 10d ago), licensed MIT. It adds 67 tokens to every session and 462 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 2026-10-21.
worker compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| workermrDesign-ww/vault-os | Agent | 3 | 10d ago | MIT | A | 67 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |