Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/nemock/company-brain/vault-architect)<a href="https://agentmods.dev/skills/nemock/company-brain/vault-architect"><img src="https://agentmods.dev/badge/skills/nemock/company-brain/vault-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/skills/nemock/company-brain/vault-architect"><img src="https://agentmods.dev/badge/skills/nemock/company-brain/vault-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 | $0.00117 | $0.01536 |
| Opus 5 | $0.00059 | $0.00768 |
| Sonnet 5 | $0.00023 | $0.00307 |
| Haiku 4.5 | $0.00012 | $0.00154 |
Grade A, and why
vault-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 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vault-architect
This skill scaffolds a new company-brain vault. Run it once per vault. It delegates the actual work to the cb scaffold CLI command so the on-disk shape stays single-sourced with the schema package.
When to use
- The user is creating a brand-new company-brain vault.
- The user wants to refresh
_system/*.md,_branding/starters,.gitignore, or the vaultREADME.mdafter upgrading company-brain (use--force).
When NOT to use
- The user already has a vault and wants to add knowledge — point them at the
intakeoratomizeskills. - The user wants to change a vault's profile after the fact — that requires re-scaffolding into a new directory and migrating content by hand. The profile is not designed to be flipped in place.
Workflow
1. Confirm with the user
Ask, in order:
- Target directory. Where should the vault live? Default to the current working directory if the user doesn't specify. Resolve to an absolute path before passing to the CLI.
- Profile. Which industry profile? Offer these choices with brief explanations:
medical-device— patient-facing devices regulated by FDA / MDR / etc. Activates indications-for-use, regulatory-clearance, and ISO-14971-vocabulary risk node types. Generated documents carry the controlled-document-boundary footer.default— industry-agnostic. Only the epistemic and entity node types are active.saas,hardware,services— reserved slots. In v1 these behave likedefault; content lands in v2.
- Git. Confirm the user wants the vault initialized as a git repository (the default). Most company vaults benefit from this — it makes them shareable, version-controlled, and ready to push to GitHub / GitLab / Bitbucket / on-prem. Pass
--no-gitonly when:- The user does not have git installed.
- The vault will live inside another git repo (e.g., as an example vault tracked by a parent repo).
cb scaffoldwill detect this case automatically and skip git, so--no-gitis mainly an explicit signal.
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 First seen · 111 lines · 117 tokens per session scan A 68f8bec6c542
vault-architect is a skill published in the GitHub repository nemock/company-brain (5 stars, last pushed 3mo ago), licensed MIT. It adds 117 tokens to every session and 1,536 once invoked, about $0.0006 per session on Opus 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 2026-08-31.
Other skills, from other repositories
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.
tashanzhishi
A workflow for turning YouTube, Bilibili, podcast, or article content into a readable Chinese note stored under a knowledge folder called 他山之石. It separates the source author’s facts and opinions from the note writer’s interpretation.
extract-memory
Extract writing style, personality traits, and key insights from a collection of documents (Markdown, PDF, TXT, DOCX) and save them as a Claude Code memory file. Use when the user wants to capture their writing DNA, build a personal style guide, or create a reusable memory profile from their existing content.
spool
Search your local Claude Code and Codex CLI session history.