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 olegvg/olegvg-skills --skill kb-buildgit clone --depth 1 https://github.com/olegvg/olegvg-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/olegvg/olegvg-skills/kb-build)<a href="https://agentmods.dev/skills/olegvg/olegvg-skills/kb-build"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/kb-build/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/olegvg/olegvg-skills/kb-build"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/kb-build.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 | $0.00069 | $0.01735 |
| Opus 5 | $0.00034 | $0.00868 |
| Sonnet 5 | $0.00014 | $0.00347 |
| Haiku 4.5 | $0.00007 | $0.00173 |
Grade A, and why
kb-build 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 11d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kb-build — Build a Three-Layer Knowledge Base
When to use
User points you at a corpus (codebase, notes archive, docs folder) and wants a fresh .kb/ built from scratch. One-shot operation.
If .kb/ already exists at the target path, STOP. Ask the user whether to overwrite, and get explicit confirmation before proceeding.
Input
- Corpus root path — argument from the user. If missing, ask for it before starting. Default is not the current directory unless the user confirms.
--include <path>(optional, repeatable) — override a default exclusion. See references/default-exclusions.md.
Output (created inside the corpus root)
.kb/
├── indexes/_root.md
├── indexes/<area>.md (one per semantic domain)
├── summaries/<area>/overview.md
├── summaries/<area>/<leaf>.md
├── decisions/ (empty directory — populated only by kb-record-decision)
└── .kb-state.json
Default exclusions
Build never ingests dated planning artifacts, vendored directories, build outputs, or timestamped scratch directories. Full list and rationale: references/default-exclusions.md. Override individual paths with --include.
Workflow
Build runs in three passes. The structure is deliberate: it keeps the main agent's context bounded regardless of corpus size, and it parallelizes the expensive pass. Do NOT collapse it into a single pass even on small corpora — the workflow is the teaching.
Pass 1 — Survey and group (main agent, light context)
Walk the corpus at a high level. Do NOT read full file contents in this pass.
ls <corpus-root>for the top-level layout.- Read README if present.
- For each directory worth sampling, read only file headers: first 30–50 lines, docstrings, imports, exported names.
- Cluster files into semantic domains. Produce a draft of
_root.mdin memory — list of areas + which files belong to each.
Context budget for Pass 1: roughly 5–10% of the corpus. If you catch yourself opening full file bodies in Pass 1, stop — that's Pass 2's job.
What ships with it
4 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.
- 11d ago First seen · 135 lines · 69 tokens per session scan A 52fe47b5aaf5
kb-build is a skill published in the GitHub repository olegvg/olegvg-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 1,735 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 2026-08-31.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.