Borrowing it
Nothing to install: this file belongs to pass-agent/loomkin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pass-agent/loomkin/main/.agents/skills/vault-prep/SKILL.mdgit clone --depth 1 https://github.com/pass-agent/loomkinWrote 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/pass-agent/loomkin/vault-prep)<a href="https://agentmods.dev/skills/pass-agent/loomkin/vault-prep"><img src="https://agentmods.dev/badge/skills/pass-agent/loomkin/vault-prep/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/pass-agent/loomkin/vault-prep"><img src="https://agentmods.dev/badge/skills/pass-agent/loomkin/vault-prep.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 | $0.00017 | $0.00503 |
| Opus 5.5 | $0.00007 | $0.00201 |
| Sonnet 5.5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
vault-prep 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 2mo 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
Create or update a meeting prep file with topics and auto-gathered context.
Identify Contributor
Who is adding topics? Look for @mentions or ask.
Check for Existing Prep
vault_search(query: "prep", entry_type: "meeting") filtered to today's date.
- If exists: APPEND MODE — add this person's topics to the existing prep
- If not: CREATE MODE — gather full context and create new prep
Gather Context (CREATE MODE only)
- Recent meetings:
vault_search(query: "*", entry_type: "meeting")last 3- Extract discussion topics, open action items, decisions
- Open follow-ups:
vault_kanban(action: "list")filtered to items with meeting sources - Recent checkins:
vault_search(query: "*", entry_type: "checkin")since last meeting- Summarize as "async updates" — no need to rehash in the meeting
- At-risk OKRs:
vault_search(query: "*", tags: ["okr"])— check frontmatter for status - Upcoming milestones:
vault_search(query: "milestone", tags: ["in-progress"])
Parse Topics
From user input, extract:
- Topics they want to discuss
- Decisions that need to be made
- Questions they have
Create/Update Entry
CREATE: vault_create_entry(entry_type: "meeting", ...) with prep content, include prep_generated: true and contributors: ["{person}"] in extra_frontmatter
APPEND: vault_update_entry(append: "{person}'s topics:\n- [ ] Topic 1\n- [ ] Topic 2")
Also update contributors list in frontmatter.
Check for duplicate topics across contributors — note "(Also raised by {other person})" if similar.
Report
CREATE: Topics added, context gathered (follow-ups count, async updates, at-risk items) APPEND: Topics added, existing agenda summary, current contributors list
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.
- 2mo ago First seen · 56 lines · 17 tokens per session scan A 3d73dd8d5f61
vault-prep is a skill published in the GitHub repository pass-agent/loomkin (182 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 503 once invoked, about $0.0001 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 2026-08-30.
vault-prep compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vault-preppass-agent/loomkin | Skill | 182 | 5mo ago | MIT | A | 17 | Claude Code |
| elixirericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 72 | Claude Code, Codex |
| phoenixericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | B | 89 | Claude Code, Codex |
| offensive-vuln-classesMiosa-osa/OSA | Skill | 78 | 8d ago | Apache-2.0 | A | 69 | Claude Code, Codex |
| offensive-social-engineeringMiosa-osa/OSA | Skill | 78 | 8d ago | Apache-2.0 | A | 193 | Claude Code, Codex |
| offensive-crypto-attacksMiosa-osa/OSA | Skill | 78 | 8d ago | Apache-2.0 | A | 199 | Claude Code, Codex |
| offensive-parameter-pollutionMiosa-osa/OSA | Skill | 78 | 8d ago | Apache-2.0 | A | 57 | Claude Code, Codex |