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/hogu-dev/llmkb/kb-initnpx skills add hogu-dev/llmkb --skill kb-initgit clone --depth 1 https://github.com/hogu-dev/llmkbWhat 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 | $0.00044 | $0.00335 |
| Opus 5 | $0.00022 | $0.00168 |
| Sonnet 5 | $0.00009 | $0.00067 |
| Haiku 4.5 | $0.00004 | $0.00034 |
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.
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
- Scaffold. Run
llmkb init <dir> --name <name> --description "<one line>". This creates the directory structure,kb.yaml, a starterSCHEMA.md, the.llmkb/gitignore, emptyindex.md/log.md, and a git repo. - 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?
- Tailor
SCHEMA.mdwith their answers — add project-specific page-type guidance, tag vocabulary, and tone/length rules. Keep the required frontmatter contract intact. - Confirm health. Run
llmkb lint(an empty KB should be clean) and append a## [YYYY-MM-DD] init | <name>line towiki/log.md.
Done when
The KB exists, SCHEMA.md reflects the project, and llmkb lint is clean.
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.
- yesterday First seen · 32 lines · 44 tokens per session scan A 4beef2fb7d93
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.
Other skills, from other repositories
recursive-decomposition
Handle tasks that exceed the context window by decomposing them: size and filter the input, chunk it, run recursive sub-agents on independent parts, verify on small windows, and synthesise programmatically, following the Recursive Language Models (RLM) research by Zhang, Kraska and Khattab (2025). Use when a task…
agentica-sdk
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration.
agentica-claude-proxy
Guide for integrating Agentica SDK with Claude Code CLI proxy.
ast-grep-find
AST-based code search and refactoring via ast-grep MCP.
braintrust-analyze
Analyze Claude Code sessions via Braintrust.
agent-orchestration
When the user asks to implement something, use implementation agents to preserve main context.