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 skills add markoblogo/abvx-agent-skills --skill knowledge-base-enrichmentgit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote 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/markoblogo/abvx-agent-skills/knowledge-base-enrichment)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/knowledge-base-enrichment"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/knowledge-base-enrichment/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/markoblogo/abvx-agent-skills/knowledge-base-enrichment"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/knowledge-base-enrichment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01058 |
| Opus 5 | $0.00029 | $0.00529 |
| Sonnet 5 | $0.00012 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
knowledge-base-enrichment 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 10d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base Enrichment
Turn raw Markdown notes into a traceable knowledge base without silently rewriting the source layer.
Use When
- enriching one note with tags, source attribution, or related-note links;
- organizing a vault or Markdown corpus into generated wikis;
- refreshing a wiki from new or changed source notes;
- preparing durable, source-grounded context for an agent or reader workflow.
Default Layout
vault/
raw/ # source notes; read-only by default
wikis/ # generated synthesis; writable only in the selected scope
tags.md # shared tag registry
.knowledge-base/
state.json
proposals/
logs/
Adapt to an existing layout after inspecting it. Do not create a parallel vault when a clear local structure already exists.
Workflow
- State the source root, writable output scope, and whether the user explicitly authorized apply.
- Read the local tag registry and the target wiki's
AGENTS.md/index.mdbefore proposing changes. - Read the target note and inspect existing frontmatter without rewriting its body.
- Propose only evidence-backed metadata:
- reusable kebab-case topic tags;
sourceandurlwhen the origin is real and known;- links to related notes that actually exist.
- Keep the proposal under
.knowledge-base/proposals/until it is inspected and explicitly applied. - On apply, write derived metadata/state and generated wiki pages in the selected scope. Keep
raw/content unchanged unless the user explicitly authorizes a source edit. - Record changed sources, skipped ambiguities, unresolved links, and the verification result in a log.
Idempotence
- Track enrichment state in
.knowledge-base/state.json, not by adding silent stamps to raw notes. - Skip notes whose content hash and enrichment inputs are unchanged.
- Reuse existing tags; add a new tag only when it is broadly reusable and record why.
- Never invent source URLs, related-note targets, claims, or wiki entities.
What ships with it
2 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.
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.
- 10d ago First seen · 111 lines · 58 tokens per session scan A 5a99ed2cd308
knowledge-base-enrichment is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,058 once invoked, about $0.0003 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
fix-mermaid
Validates and repairs mermaid diagrams in markdown files. Scans for mermaid blocks, validates syntax, and auto-repairs common errors.
joycraft-add-fact
Invoked by session-end or the human after a fact surfaces — route it to the correct context document (production map, dangerous assumptions, decision log, institutional knowledge, troubleshooting).
qa
QA testing — browse like a real user, document bugs, report only. Never fixes.
typescript-providers
Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
pdf-debug-unbuffered
Debug Python PDF generation errors by using unbuffered output and stderr inspection to reveal actual tracebacks.