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.
npx agentmods add skills/pass-agent/loomkin/vault-streamnpx skills add pass-agent/loomkin --skill vault-streamgit 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-stream)<a href="https://agentmods.dev/skills/pass-agent/loomkin/vault-stream"><img src="https://agentmods.dev/badge/skills/pass-agent/loomkin/vault-stream.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00283 |
| Opus 5 | $0.00006 | $0.00142 |
| Sonnet 5 | $0.00003 | $0.00057 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
vault-stream 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 6d 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
Smart capture for content/show planning. Detect type from input:
Guest profile (input is about a person):
- Names someone specific
- Describes who they are, what they've built
- Mentions "guest", "have on", "should interview"
Action: vault_create_entry(entry_type: "guest_profile", ...)
Stream idea (input is about a topic/concept):
- Describes what the episode would be about
- Mentions a format (interview, vibe coding, demo, news)
- Has talking points
Action: vault_create_entry(entry_type: "stream_idea", ...)
When ambiguous (just names a person with no clear topic), default to guest profile.
Guest Profiles
Extract: name, about, why they'd be good, relationship type (personal/network/cold), contact info, potential topics.
Stream Ideas
Extract: topic, format, potential guest, planned date if mentioned.
Link
Link to the parent project entry for the show via vault_link(link_type: "parent").
Check for duplicates: vault_search(query: "{name or topic}") — if similar exists, suggest updating instead.
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.
- 6d ago First seen · 42 lines · 13 tokens per session scan A 6c651294d770
vault-stream is a skill published in the GitHub repository pass-agent/loomkin (179 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 283 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
elixir
Use when writing or refactoring Elixir/OTP on the BEAM — GenServers, supervision trees and restart strategies, pattern matching, mix projects and releases — or when processes misbehave (restart loops, mailbox growth, call timeouts). NOT a Phoenix web app, LiveView, Ecto or channels (that is phoenix).
phoenix
Use when building an Elixir web app with Phoenix — contexts, Ecto schemas, changesets and migrations, LiveView, channels and PubSub, the generators, and the boundary between domain logic and the web layer. Covers the classic LiveView over-rendering and Ecto N+1 traps. NOT pure OTP work with no web or Ecto layer …
sync-docs
This skill should be used when the user asks to "sync docs", "update guides", "check docs against official", "refresh documentation", "compare guides to official docs", "update docs from upstream", or mentions syncing the SDK documentation guides with the official Claude Agent SDK documentation.
cli-sync
This skill should be used when the user asks to "check CLI schema", "sync CLI version", "check for new CLI options", "update bundled CLI", "compare SDK structs", "check schema drift", "align message structs", "verify CLI compatibility", "check control protocol", or mentions CLI compatibility, schema alignment, or…
code-review
Reviews code changes for quality, security, and best practices.
unit-converter
Converts between common units of measurement including temperature, distance, and weight.