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/skrun-dev/skrun/knowledge-base-from-vaultnpx skills add skrun-dev/skrun --skill knowledge-base-from-vaultgit clone --depth 1 https://github.com/skrun-dev/skrunWrote 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/skrun-dev/skrun/knowledge-base-from-vault)<a href="https://agentmods.dev/skills/skrun-dev/skrun/knowledge-base-from-vault"><img src="https://agentmods.dev/badge/skills/skrun-dev/skrun/knowledge-base-from-vault.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 | $0.00091 | $0.01451 |
| Opus 5 | $0.00046 | $0.00726 |
| Sonnet 5 | $0.00018 | $0.00290 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
knowledge-base-from-vault 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 3d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base from Vault
You are a knowledge curator. You take a folder of unstructured Markdown notes and turn it into a polished, navigable static site (single kb.zip artifact). Across multiple runs, you maintain a concept graph — terms that appear in multiple vaults gain count and importance, building a richer index over time.
State you receive
If this is not the first run, the runtime injects Previous state containing the concept graph:
{
"concept_graph": {
"event-sourcing": {
"count": 3,
"first_seen_run": "2026-04-15",
"last_seen_run": "2026-04-22",
"related_pages": ["concepts/event-sourcing.html", "how-to/event-replay.html"]
}
},
"runs_processed": 4
}
If no state, treat as the first run with concept_graph: {} and runs_processed: 0.
Workflow
-
Read the vault — call
read_vaultwith the user'svault_dir. The tool returns an array of:{ path, slug, title, frontmatter, headings, internal_links, content_preview }where
internal_linksare both[[wiki-style]]and[markdown](url)references. -
Extract concepts — for each note, identify 3–7 key concepts:
- Extract candidates from H2/H3 headings, bolded terms, and
[[wiki-links]]. - Normalize to kebab-case, lowercase.
- Skip generic terms ("the", "and", "introduction"), short tokens (< 3 chars), and stopwords.
- Extract candidates from H2/H3 headings, bolded terms, and
-
Update the concept graph (deep merge with prior state):
- For each concept seen in this run:
- If new: add
{ count: 1, first_seen_run: today, last_seen_run: today, related_pages: [pages_containing_it] }. - If existing: increment
count, updatelast_seen_runto today, unionrelated_pageswith new findings.
- If new: add
- Today is derived from the run date — use
2026-04-26if no other source available.
- For each concept seen in this run:
-
Build the index page —
index.htmlbody:- Site title H1
- Short paragraph (1-2 sentences) describing the vault's contents (synthesize from note titles)
- "All notes" section: a
<ul>with one<li>per note (linked to its slug.html) - "Concept index" section: a
<ul>of the top concepts by count (descending). Each item: concept name + count badge (e.g., "event-sourcing (3 runs)") linked to a fragment on the page or to a per-concept page if you generated one. - "Stats" footer:
<p>withpages_count,concept_count,runs_processed.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agent.yaml 3.4 KB
- fixtures/sample-vault/concepts/cluster-design.md 1.2 KB
- fixtures/sample-vault/concepts/event-sourcing.md 1.0 KB
- fixtures/sample-vault/glossary.md 1.1 KB
- fixtures/sample-vault/how-to/run-locally.md 848 B
- fixtures/sample-vault/intro.md 1.2 KB
- package.json 261 B
- README.md 5.0 KB
- scripts/build_site_zip.ts 5.3 KB runs code
- scripts/read_vault.ts 4.3 KB runs code
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.
- 3d ago First seen · 92 lines · 91 tokens per session scan A 9f4540a8ddc4
knowledge-base-from-vault is a skill published in the GitHub repository skrun-dev/skrun (208 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 1,451 once invoked, about $0.0005 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
jentic-api-scorecard
Use the @jentic/api-scorecard-cli to score an OpenAPI document against the Jentic API AI Readiness Framework (JAIRF). Use this skill whenever the user wants to score, grade, lint, or assess the AI-readiness / agent-readiness / quality of an OpenAPI (Swagger) spec — by local file or URL — or asks how to run the…
whisperx
Use when someone needs word-level timestamps from audio — lyric alignment, cut-safe line boundaries, or caption source timing before burn-in with video-editing.
flowise-builder
Use when flowise visual LLM workflow builder — drag-drop chatflows, API endpoints, document loaders, tools. Use when working with flowise builder.
google-workspace
Google Docs, Sheets, and Drive operations via REST API.
generate-pdf
Turn HTML or Markdown into a styled PDF, or render a public web page to PDF, and get a download link.
doc-writer
Skill "doc-writer" from Nikolahuang/nova-cli, covering 文档生成策略, 1. 代码文档, 2. api 文档, 3. 项目文档 and 实现步骤.