Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/atman-33/workhubnpx agentmods add skills/atman-33/workhub/vault-setupWrote 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/atman-33/workhub/vault-setup)<a href="https://agentmods.dev/skills/atman-33/workhub/vault-setup"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/vault-setup/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/atman-33/workhub/vault-setup"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/vault-setup.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 | $0.00073 | $0.01254 |
| Opus 5.5 | $0.00029 | $0.00502 |
| Sonnet 5.5 | $0.00015 | $0.00251 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
vault-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vault-setup — Prepare a machine for a workhub vault
End-to-end environment setup: software → vault → Claude harness → OpenCode sync → verification. Steps that are already satisfied are skipped; nothing is installed without telling the user first.
1. Resolve the vault path
- Use the argument if given.
- Else
WORKHUB_VAULTenv var, thenvault_pathin%APPDATA%\workhub\config.json(~/.config/workhub/config.jsonoff Windows). - If none resolves, ask the user where the vault is (or should be created).
2. Check required software
Probe each tool and collect what is missing (do not install yet):
| Tool | Check | Needed for |
|---|---|---|
| git | git --version |
repos, plugin marketplace fetch |
| Node.js ≥ 20 | node --version |
.opencode/scripts/*.mjs sync scripts |
| Claude Code | claude --version |
the primary agent harness |
| OpenCode | opencode --version |
optional second agent; skip if unused |
| Obsidian | Windows: Test-Path "$env:LOCALAPPDATA\Obsidian" |
optional, human vault editing |
| herdr | herdr --version |
optional, the default AI-task workspace launcher |
Present the missing list with the exact install commands and ask before running any of them:
- Windows:
winget install Git.Git,winget install OpenJS.NodeJS.LTS,npm install -g @anthropic-ai/claude-code,npm install -g opencode-ai,winget install Obsidian.Obsidian - macOS/Linux: the same npm installs; git/node via the platform's package manager.
- herdr: install via the
setup-herdrskill (agent-ops plugin) rather than a package manager — see Phase 6.
Obsidian, OpenCode, and herdr are optional — offer, don't push.
3. Ensure the vault exists
- If the resolved path is missing or empty, run the
vault-initskill with that path (it copiesvault-template/and registers the vault in the app config), then continue here. - If the path exists but lacks
.claude/settings.jsonor.opencode/, it predates the current template — suggest thevault-migrateskill instead of patching files ad hoc.
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.
- 1mo ago Changed · +3 lines 3fba1f8b06d6
- 1mo ago First seen · 100 lines · 73 tokens per session scan A 44cc4dd3688d
vault-setup is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 1,254 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 2026-09-03.
Other skills, from other repositories
recipe-plan
Create work plan from design document and obtain plan approval.
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
routine-craft
Write a routine that runs well with nobody watching: no duplicates, a self-contained prompt, a fitting schedule, stop rules, a quiet "nothing new" reply, and a known place for results to land.
session-librarian
Organize sessions by prompt: find, rename, archive, prune.
recruit-init
Uma habilidade que prepara um espaço de trabalho para recrutamento, com pastas, documentos de referência, registros e instruções para agentes de programação. Ela verifica dependências como Node.js, ferramentas de vagas e, opcionalmente, o Feishu.
job
Daily routines for a corporate software engineering job. Start mode triages the inbound review queue, your own open PRs, and the issue tracker's plan for today. End mode clears the outbox, surfaces review debt, sweeps worktrees for unpushed work, and tidies tracker state for tomorrow. Use via /job, /job start, /job…