kb-init

A setup skill for creating an llmkb knowledge base, which is a structured collection of project notes and reference pages. It initializes the files and tailors the rules for the project's subject area.

In plain words
What is it for?
It is for creating the knowledge-base structure, defining its schema and naming rules, checking it with a linter, and recording the initialization.
Why use it?
It gives a new project an organized place for reusable knowledge instead of leaving information scattered across documents.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/hogu-dev/llmkb/kb-init
Any agent
npx skills add hogu-dev/llmkb --skill kb-init
Clone the repo
git clone --depth 1 https://github.com/hogu-dev/llmkb

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.00335
Opus 5 $0.00022 $0.00168
Sonnet 5 $0.00009 $0.00067
Haiku 4.5 $0.00004 $0.00034

Measured yesterday against content hash 4beef2fb7d93, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kb-init 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 yesterday.

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.

skills/kb-init/SKILL.md · 32 lines

What it actually says

kb-init

Create and tailor a new llmkb knowledge base for a project.

When to use

Starting a KB for a new project, or the user asks to set one up.

Steps

  1. Scaffold. Run llmkb init <dir> --name <name> --description "<one line>". This creates the directory structure, kb.yaml, a starter SCHEMA.md, the .llmkb/ gitignore, empty index.md/log.md, and a git repo.
  2. Interview briefly. Ask the user:
    • What domain does this KB cover, and what will it mostly ingest?
    • Any naming or tagging conventions they want enforced?
    • What counts as a concept vs an entity here?
  3. Tailor SCHEMA.md with their answers — add project-specific page-type guidance, tag vocabulary, and tone/length rules. Keep the required frontmatter contract intact.
  4. Confirm health. Run llmkb lint (an empty KB should be clean) and append a ## [YYYY-MM-DD] init | <name> line to wiki/log.md.

Done when

The KB exists, SCHEMA.md reflects the project, and llmkb lint is clean.

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. yesterday First seen · 32 lines · 44 tokens per session scan A 4beef2fb7d93

Subscribe to this mod's changes

kb-init is a skill published in the GitHub repository hogu-dev/llmkb (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 335 once invoked, about $0.0002 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.