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/luutru433-coder/local-knowledge-suite/company-knowledge-basenpx skills add luutru433-coder/local-knowledge-suite --skill company-knowledge-basegit clone --depth 1 https://github.com/luutru433-coder/local-knowledge-suiteWrote 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/luutru433-coder/local-knowledge-suite/company-knowledge-base)<a href="https://agentmods.dev/skills/luutru433-coder/local-knowledge-suite/company-knowledge-base"><img src="https://agentmods.dev/badge/skills/luutru433-coder/local-knowledge-suite/company-knowledge-base.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 5.1 | $0.00110 | $0.00933 |
| Opus 5 | $0.00055 | $0.00466 |
| Sonnet 5 | $0.00022 | $0.00187 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
company-knowledge-base 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 5d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Knowledge Base
Operate the plugin-owned runtime against an explicit registered company repository. Never treat project Memory or Skill text as company evidence, and never import knowledge code from a target project.
Resolve identity from .local-knowledge/company.toml and the Windows-user
registry. Several projects may reference one company ID; different company IDs
must never share source text, databases, credentials, or results.
Read references/source-policy.md before registration, crawl, or sensitive ingestion. Read references/okf-quality.md before editing, approving, or repairing concepts. Read references/operations.md for CLI, portal, models, roles, Git, and diagnosis.
Establish context
- Resolve absolute project and company repository paths.
- Require project profile
combinedorcompany-onlyand the exact registered company ID. - Call
knowledge_status(project_root)and inspect compatibility, migration, registration, warnings, and stores. - Replace the placeholder chat and embedding names in
.ckb/config.jsonwith exact loaded LM Studio model IDs. Store any LM Studio bearer token and private-Git credentials through portal Settings, never in config. - Run company
healthbefore source registration or ingestion. - Stop mutations for schema incompatibility, registry mismatch, Git conflict, missing required local models, or a source-policy violation.
Do not create or register a company implicitly from a recall request. Never set the Credential Manager namespace manually.
Ingest
- Put authorized local material inside the company's ignored
.local-sources/. - Register a supported
fileorfolder, or an explicit public HTTP(S) website with every permitted--allow-domain. - Queue
ingest SOURCE_ID. - Run
run-job JOB_ID,worker --once, or a continuous worker. - Preserve failed job history. Repair the source, parser, OCR, local model, or Git state and enqueue a new 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.
- 5d ago First seen · 95 lines · 110 tokens per session scan A 90353e627fa1
company-knowledge-base is a skill published in the GitHub repository luutru433-coder/local-knowledge-suite (0 stars, last pushed 6d ago), licensed MIT. It adds 110 tokens to every session and 933 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mindos-zh
MindOS 是用户的本地知识助手，也是跨会话、跨 Agent 共享的知识库。它保存决策记录、会议纪要、SOP、 排错经验、架构选型、调研结论和偏好设置。 仅 mindRoot 知识库内任务。不用于：改代码仓库、项目源码、KB 外路径。 核心概念：空间、指令(INSTRUCTION.md)、技能(SKILL.md)；笔记可承载指令与技能。 触发场景：保存或记录任何内容、搜索历史笔记或上下文、更新或编辑文件、整理或重组文件结构、 执行SOP或工作流、捕获对话中的决策、复盘或总结经验、追加表格或CSV数据、跨Agent交接上下文、 提炼经验教训、同步关联文档、查找之前是否讨论过某事、查询历史决策、查找模板或SOP、…
migrate
Scan the project and migrate existing documentation into OKF format. Use when the user wants to populate the knowledge base from existing docs, README, schemas, API specs, runbooks, or any structured project knowledge. Trigger on "migrate to okf", "populate the knowledge base", "scan my docs", "convert docs to okf"…
init
Initialize OKF knowledge base files in the current project. Use when the user wants to start documenting their project for claude-mega-brain, or when the user says "init mega brain", "setup the knowledge base", "cria o okf", "inicializa o mega brain", "quero usar o mega brain", "criar a estrutura do knowledge base"…
save
File the current conversation's valuable content (analysis, decision, session summary) as a structured wiki note so it isn't lost in chat history. Triggers on: "save this", "guarda esto", "guárdalo en el wiki", "/save", "$save", "file this", "apunta esto", "guarda esta conversación", "save this session".
obsidian-vault-workflow
Use this skill when a user asks an agent to inspect, organize, summarize, or update an Obsidian vault through this MCP server.
openclaw-enterprise-knowledge-base
Use when creating, auditing, repairing, validating, or syncing an enterprise Markdown or Obsidian knowledge base for OpenClaw agents. Applies to ontology-style wiki pages, governed business objects, hot.md startup cache, agent-safe visibility rules, OpenClaw manifests, RAG handoff, sales/support action governance, and…