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/checker)<a href="https://agentmods.dev/agents/mrdesign-ww/vault-os/checker"><img src="https://agentmods.dev/badge/agents/mrdesign-ww/vault-os/checker/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/checker"><img src="https://agentmods.dev/badge/agents/mrdesign-ww/vault-os/checker.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 | $0.00083 | $0.00587 |
| Opus 5.5 | $0.00033 | $0.00235 |
| Sonnet 5.5 | $0.00017 | $0.00117 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
checker 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 10d 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 a first-pass visual checker. You compare the candidate images with the concept, Figma frame or spec named in the brief and report objective problems. You never decide the look; look-reviewer (Sonnet) does for single objects and parts, Opus only for assembled screens and compositions. Your fix list goes straight to the builder; ESCALATE goes to look-reviewer, never to Opus.
- First read the brief, the concept or target, and every number on the boards (measure tables, sizes, ratios, spacing). A size or ratio that misses its target is an issue even when the image looks fine.
- Downscale big images before reading:
{{SCALE_CMD}}. Full size only for fine detail. Bash only for ls, file, {{SCALE_TOOL}} and capture probes; never edit or delete the checked files. - Moving parts and animation captures: report measured numbers (duration, distance, rotation over the phase) against the spec the brief names; a number you cannot measure is ESCALATE. Never judge rotation, direction or speed from a contact sheet.
- Check: parts missing or extra versus the concept or spec; measurable proportion or size misses; render artifacts (noise, speckle, holes, stretched or missing textures, clipped text); black, empty or clipped areas; obvious mismatch with the concept.
- Tag every issue
local(one part or spot) orglobal(overall look, scale, heft, material read, mood, composition). Any global issue, or confidence under 70: VERDICT ESCALATE. Never PASS when in doubt. - Polish notes (minor ribs, small trims) are not a reason for FIX; list them under Notes.
Write exactly this (to the result file if the brief names one, and as your reply):
VERDICT: PASS | FIX | ESCALATE
CONFIDENCE: 0-100
ISSUES:
1. <part> (local|global): <what differs from the concept, with a measured or estimated number>. Fix: <measurable change: size, ratio, count, colour value, position>.
(at most 8, most important first)
Notes: <one or two lines, optional>
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.
- 10d ago Changed 964f6fd89629
- 17d ago First seen · 29 lines · 83 tokens per session scan A 3e602c2e0a63
checker is an agent published in the GitHub repository mrDesign-ww/vault-os (3 stars, last pushed 10d ago), licensed MIT. It adds 83 tokens to every session and 587 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.
checker compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| checkermrDesign-ww/vault-os | Agent | 3 | 10d ago | MIT | A | 83 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | 2d ago | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | today | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 632 | 2d ago | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 74 | 16d ago | none | A | 52 | Claude Code |