loomkin: Skill for Claude Code

.agents/skills/vault-prep/SKILL.md

vault-prep is a skill for Claude Code from pass-agent/loomkin. It costs 17 tokens per session (503 once invoked), scanned A, original, MIT.

A meeting-preparation skill that builds an agenda with background gathered from a connected knowledge base.

In plain words
What is it for?
Use it to collect context, identify open decisions and action items, and prepare a structured meeting agenda.
Why use it?
It saves time spent searching past meetings, follow-up tasks, check-ins, goals, and milestones before a meeting. It can add topics to an existing preparation note or create a new one.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is pass-agent/loomkin's own configuration. It tells Claude Code how to work on loomkin itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything loomkin configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/pass-agent/loomkin/main/.agents/skills/vault-prep/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pass-agent/loomkin

Made for: Claude Code.

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.

agentmods badge for vault-prep

README.md
[![agentmods](https://agentmods.dev/badge/skills/pass-agent/loomkin/vault-prep/github.svg)](https://agentmods.dev/skills/pass-agent/loomkin/vault-prep)
Your own site
<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.

agentmods 80×15 button for vault-prep

Your own site · 80×15
<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>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 503 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2mo ago against content hash 3d73dd8d5f61, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.agents/skills/vault-prep/SKILL.md · 56 lines

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)

  1. Recent meetings: vault_search(query: "*", entry_type: "meeting") last 3
    • Extract discussion topics, open action items, decisions
  2. Open follow-ups: vault_kanban(action: "list") filtered to items with meeting sources
  3. Recent checkins: vault_search(query: "*", entry_type: "checkin") since last meeting
    • Summarize as "async updates" — no need to rehash in the meeting
  4. At-risk OKRs: vault_search(query: "*", tags: ["okr"]) — check frontmatter for status
  5. 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

Changes

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.

  1. 2mo ago First seen · 56 lines · 17 tokens per session scan A 3d73dd8d5f61

Subscribe to this mod's changes

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.

Related

vault-prep compared with skills from other repositories

vault-prep next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vault-preppass-agent/loomkinSkill1825mo agoMITA17Claude Code
elixirericrisco/rsc-harnessSkill5032d agoMITA72Claude Code, Codex
phoenixericrisco/rsc-harnessSkill5032d agoMITB89Claude Code, Codex
offensive-vuln-classesMiosa-osa/OSASkill788d agoApache-2.0A69Claude Code, Codex
offensive-social-engineeringMiosa-osa/OSASkill788d agoApache-2.0A193Claude Code, Codex
offensive-crypto-attacksMiosa-osa/OSASkill788d agoApache-2.0A199Claude Code, Codex
offensive-parameter-pollutionMiosa-osa/OSASkill788d agoApache-2.0A57Claude Code, Codex