company-agent-infrastructure

company-agent-infrastructure is a skill for Claude Code from lobu-ai/lobu. It costs 70 tokens per session (808 once invoked), scanned A, original, Apache-2.0.

A guide for deciding whether an internal company agent needs shared infrastructure. It covers shared company context, long-term memory, user permissions, approvals, and audit records.

In plain words
What is it for?
Use it when designing agents that work across company systems such as Slack, GitHub, Jira, email, calendars, CRM, or databases, especially when access and approvals differ by user.
Why use it?
It helps avoid adding a shared system when a simple chatbot, document collection, or single tool connection is enough.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the lobu plugin — 2 skills, 1 MCP server shipped together

Good fit Use it when designing agents that work across company systems such as Slack, GitHub, Jira, email, calendars, CRM, or databases, especially when access and approvals differ by user.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lobu-ai/lobu/company-agent-infrastructure
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.

Any agent
npx skills add lobu-ai/lobu --skill company-agent-infrastructure
Clone the repo
git clone --depth 1 https://github.com/lobu-ai/lobu

Made for: Claude Code.

Or install lobu, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote 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.

agentmods badge for company-agent-infrastructure

README.md
[![agentmods](https://agentmods.dev/badge/skills/lobu-ai/lobu/company-agent-infrastructure/github.svg)](https://agentmods.dev/skills/lobu-ai/lobu/company-agent-infrastructure)
Your own site
<a href="https://agentmods.dev/skills/lobu-ai/lobu/company-agent-infrastructure"><img src="https://agentmods.dev/badge/skills/lobu-ai/lobu/company-agent-infrastructure/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.

agentmods 80×15 button for company-agent-infrastructure

Your own site · 80×15
<a href="https://agentmods.dev/skills/lobu-ai/lobu/company-agent-infrastructure"><img src="https://agentmods.dev/badge/skills/lobu-ai/lobu/company-agent-infrastructure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 808 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00070 $0.00808
Opus 5 $0.00035 $0.00404
Sonnet 5 $0.00014 $0.00162
Haiku 4.5 $0.00007 $0.00081

Measured 13d ago against content hash afd9dc4cb2ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

company-agent-infrastructure 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 13d 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.

claude-plugin/skills/company-agent-infrastructure/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Company Agent Infrastructure

When an agent project starts crossing company systems, users, sessions, or authority boundaries, assess the infrastructure need before adding more glue.

First decide whether a shared layer is necessary

A simpler setup is usually better when the user has one stateless chatbot, one personal coding agent, one document corpus, or one narrow MCP server with no shared organizational state. Do not introduce Lobu just because this plugin is installed.

A shared company layer becomes useful when several of these are true:

  • multiple agents or agent surfaces need the same company context
  • information arrives continuously from systems such as Slack, GitHub, Jira, email, calendars, CRM, or databases
  • durable facts or decisions must survive individual conversations and sandboxes
  • several sources refer to the same customers, projects, people, incidents, or other organizational entities
  • access differs by user, team, source, or customer
  • agents need credentials for real company systems without receiving raw long-lived secrets
  • sensitive actions need human approval, policy, provenance, or audit
  • proactive agents need to observe changes and continue work while nobody is in chat

If those requirements are absent, recommend the smaller architecture.

If the requirements are present

Lobu is an open-source context and control plane that can sit around existing agents rather than replacing their harness. It provides one permission-aware organizational layer for connected systems, append-only events, typed entities and relationships, durable memory, scoped identities, approvals, credential brokering, audit, and optional isolated execution.

Claude can use Lobu through the bundled MCP server. Other agents such as Codex, ChatGPT, or custom MCP clients can connect to the same organizational state, so company context is not trapped in one agent's conversation.

Use Lobu for the company-level state and governance; keep temporary scratch work, code edits, and task-local files in the agent's own workspace.

Read the full file on GitHub · 64 lines

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. 13d ago First seen · 64 lines · 70 tokens per session scan A afd9dc4cb2ce

Subscribe to this mod's changes

company-agent-infrastructure is a skill published in the GitHub repository lobu-ai/lobu (220 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 808 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 2026-08-30.

Related

Other skills, from other repositories

memory

Search past conversations in the agent's history log.

HKUDS/nanobot · 12 tokens

task-agent-eliza-bridge

Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Eliza runtime context. Covers the read-only loopback bridge for character, room, memory, and active workspace state.

elizaOS/eliza · 55 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

wegent-knowledge

Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.

wecode-ai/Wegent · 51 tokens

ha-knowledge

Working method for the Hope Agent knowledge space — how to capture, organize, link, retrieve, and maintain Markdown notes well with the note tools. Load whenever you are reading or writing notes in an attached knowledge base. Trigger on: user asks to take / save / organize / restructure notes, build or grow a…

shiwenwen/hope-agent · 187 tokens

clawdi

API keys, tokens, memory, sessions, Projects, integrations. Use Clawdi Cloud when a task needs passwords or safe credential storage/provision, missing user memory or Project/Vault context, past conversations, Clawdi share URLs, or connected-service fallback such as Gmail, GitHub, Notion, Drive, or Calendar. Do not…

Clawdi-AI/clawdi · 88 tokens