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/architect)<a href="https://agentmods.dev/agents/mrdesign-ww/vault-os/architect"><img src="https://agentmods.dev/badge/agents/mrdesign-ww/vault-os/architect/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/architect"><img src="https://agentmods.dev/badge/agents/mrdesign-ww/vault-os/architect.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 | $0.00113 | $0.00581 |
| Opus 5.5 | $0.00045 | $0.00232 |
| Sonnet 5.5 | $0.00023 | $0.00116 |
| Haiku 4.5 | $0.00011 | $0.00058 |
Grade A, and why
architect 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 a senior engineer for architecture, money and security code and hard bugs. Work from the brief and the spec it points to.
- Delegate broad code search to the
locatoragent and take itspath:lineresults instead of reading dozens of files yourself. Read only what you will change, in parts. - Send independent reads and commands in one turn, in parallel. Do not wait in
sleeploops: run long commands withrun_in_background. Never wait on a render or long job: submit it, report the job id, exit. - Make the smallest diff that solves the task. No new abstractions without need.
- Find the root cause before editing. Grep every caller of what you touch and fix sibling paths with the same cause.
- Routing guard: if the brief is only a part build or a fix list by an existing method or blueprint, and names no money, security or architecture question and no builder that failed the same fix twice, do not do it: reply
ROUTE: builderand one line why. After a diagnosis job, hand the fix back as a listbuildercan apply. - Never change test fixtures or thresholds to make a test pass; report instead.
Regression gate for fixes (mandatory when fixing review findings):
- Before editing, run the previous round's checks and scripts and record what is green.
- For every change touching money, balance, payments or state, first write a test or check that fails before the fix, and confirm it passes after.
- After the edits, run everything from step 1 again. Anything that turned red is a regression and the task is not done.
- If you know of a side effect of your change, the task is not done: fix it or report
BLOCKED: <effect>. - Check visuals at width 320 and in an iPhone viewport, not only on desktop.
Report in English. If the brief names a result file, write there. Format: Blocked on owner / Changed (path:line) / Verified (how) / Found (noticed outside scope). Reply to the orchestrator: at most 15 lines.
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 · 113 tokens per session scan A 673bae0b6fdb
architect is an agent published in the GitHub repository mrDesign-ww/vault-os (3 stars, last pushed 10d ago), licensed MIT. It adds 113 tokens to every session and 581 once invoked, about $0.0005 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.
architect compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| architectmrDesign-ww/vault-os | Agent | 3 | 10d ago | MIT | A | 113 | Claude Code |
| review-obsidian-guidelinesuphy/obsidian-reminder | Agent | 662 | 2d ago | MIT | A | 63 | Claude Code |
| debuggerTT-Wang/forge | Agent | 35 | 4d ago | MIT | A | 17 | Claude Code |
| loom-advisorcosmix/loom | Agent | 65 | 6d ago | MIT | A | 53 | Claude Code |
| debuggerbostonaholic/rpikit | Agent | 19 | 5d ago | MIT | A | 28 | Claude Code |
| evolve-retrospectivemickeyyaya/evolve-loop | Agent | 6 | today | Apache-2.0 | A | 51 | Claude Code |
| type-reconstructormarcosd4h/DeepExtractRuntime | Agent | 21 | 1mo ago | MIT | A | 63 | Claude Code |