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 commands/luanmorenommaciel/agentspec/create-kbgit clone --depth 1 https://github.com/luanmorenommaciel/agentspecWrote 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/commands/luanmorenommaciel/agentspec/create-kb)<a href="https://agentmods.dev/commands/luanmorenommaciel/agentspec/create-kb"><img src="https://agentmods.dev/badge/commands/luanmorenommaciel/agentspec/create-kb.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 | $0.00032 | $0.00550 |
| Opus 5 | $0.00016 | $0.00275 |
| Sonnet 5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
create-kb 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 2d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Knowledge Base Command
Single entrypoint for KB domain creation: a light single-pass build by default, a high-assurance source-verified build with
--validated, and a health audit with--audit.
Usage
/create-kb <DOMAIN> [--validated]
/create-kb --audit
Examples: /create-kb redis, /create-kb pandas --validated, /create-kb --audit
Choosing the mode
Default (light) suits quick, low-stakes domains where kb-architect's own confidence model suffices. --validated suits foundational or high-stakes domains where every claim must be source-cited and independently fact-checked — it costs more tokens and buys assurance. When unsure: if many agents will trust this domain as ground truth, use --validated.
What Happens
Default (light):
- Validates prerequisites — checks
_templates/and_index.yamlexist - Invokes the kb-architect agent — single-pass build with the agent's confidence model
- Reports completion — shows score and files created
--validated (high-assurance):
- Loads the kb-build skill and follows its six stages — ground → plan → research with adversarial refutation → build via
kb-architectsubagents → independent fact-check gate → additive_index.yamlregistration - Reports completion — verification summary, citation coverage, files created
--audit:
- Invokes the kb-architect agent's audit capability — scores existing domains against the 100-point rubric
Options
| Command | Action |
|---|---|
/create-kb <domain> |
Create new KB domain (light, single-pass) |
/create-kb <domain> --validated |
Create with source verification: research, adversarial checks, independent fact-check gate |
/create-kb --audit |
Audit existing KB health |
See Also
- Skill (
--validatedmode):.claude/skills/kb-build/SKILL.md - Agent (light mode + audit):
.claude/agents/architect/kb-architect.md - Templates:
.claude/kb/_templates/ - Registry:
.claude/kb/_index.yaml
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.
- 2d ago First seen · 54 lines · 32 tokens per session scan A 80a6c544d432
create-kb is a command published in the GitHub repository luanmorenommaciel/agentspec (244 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 550 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 2026-09-01.
Other commands, from other repositories
agent-brain-index
Index documents for semantic search.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
rag-publish-todo-list
Command "rag-publish-todo-list" from lucky-aeon/AgentX, covering rag 发布功能 todo list, 阶段一：数据库设计和基础架构 🗄️ ✅ 已完成, 1. 数据库表创建, 2. 领域层实现 and 3. 基础领域服务.
data
Create example data in a specific domain and upload to a Weaviate collection.
ingest
Manually add knowledge to the Weaviate store.
rag-retrieval
RAG pipeline patterns for grounded LLM responses. Use when building a Q&A system, adding citations, implementing a knowledge base, or preventing hallucinations. Triggers on RAG, retrieval augmented, knowledge base, Q&A pipeline, citations, hybrid search, context retrieval, hallucination prevention.