OpenCompany is an application for creating AI employees that work on assigned jobs in the background on the user's computer, using teams of specialized agents coordinated by a lead agent. People connect these employees to tools such as email, calendars, messages, and code, then define their workflows through a visual editor.
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 skills add zeenie-ai/OpenCompany --skill agent-builder-skillgit clone --depth 1 https://github.com/zeenie-ai/OpenCompanyWrote 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/zeenie-ai/opencompany/agent-builder-skill)<a href="https://agentmods.dev/skills/zeenie-ai/opencompany/agent-builder-skill"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/agent-builder-skill/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.
<a href="https://agentmods.dev/skills/zeenie-ai/opencompany/agent-builder-skill"><img src="https://agentmods.dev/badge/skills/zeenie-ai/opencompany/agent-builder-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.02333 |
| Opus 5.5 | $0.00016 | $0.00933 |
| Sonnet 5.5 | $0.00008 | $0.00467 |
| Haiku 4.5 | $0.00004 | $0.00233 |
Grade A, and why
agent-builder-skill 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 16d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Builder
You are connected to an Agent Builder node. It gives you ONE tool,
agent_builder, with operations chosen by the operation field:
operation |
What it does |
|---|---|
inspect_canvas |
Read-only: the canvas, what is wired to you, and the catalogue of everything you may add. ALWAYS call this first. |
inspect_node |
Read the live parameter/output schemas, handles, credential requirements, locked fields, availability, and related documentation for a node ID or type. |
search_docs |
Search shipped node logic flows, plugin Markdown, skills, guides, RFCs, and project documentation. |
read_doc |
Read a bounded section by manifest document ID; follow the returned relative links by document ID. |
add_tool |
Wire a tool to you (node_type from available_tools). |
add_skill |
Give you a skill (skill_name from available_skills). |
add_subagent |
Team leads only: add a teammate (agent_type from available_agents). |
plan_update |
Validate a complete scoped change and report required owner access without mutating the graph. |
apply_update |
Apply the same authorized configuration, or apply saved capabilities at a safe point. |
create_workflow |
Create a fully configured employee team using the shared Hire pipeline, from a trusted owner request. |
Every call is agent_builder({operation: "<one of the above>", ...fields}).
The cardinal rule
Call agent_builder({operation: "inspect_canvas"}) before any change.
Inspect relevant capabilities with inspect_node, then search and read their
documentation before planning configuration or wiring. Live schemas, handles,
locked fields and availability override conflicting prose. Archived documents
are historical context. Document IDs are manifest identifiers, never arbitrary
paths; continue long reads with next_offset. Documentation describes access
requirements; it does not authorize gaining access.
Pick values only from its catalogues: available_tools[].type,
available_skills[].name, available_agents[].type. Never guess one.
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.
- 16d ago Changed · +1 lines 69fb3a5145f5
- 20d ago Changed · +19 lines 41b9b5dce62a
- 21d ago Changed · +32 lines 08255f966c32
- 27d ago Changed · -54 lines · +4 tokens per session bf02b87ef0a9
- 1mo ago First seen · 196 lines · 35 tokens per session scan A f2685b7ef8be
agent-builder-skill is a skill published in the GitHub repository zeenie-ai/OpenCompany (1,039 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 2,333 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
browser-automation
Use when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.
acp-router
Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Grok Build, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread…
imsg
Use the imsg CLI from OpenClaw agents for iMessage/SMS DMs, groups, replies, reactions, polls, watching, and private-API actions.
coding-agent
Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.
knowledge-unlinked-claims
Review remembered Knowledge claims still unlinked after deterministic relinking. Assign subject pages, create pages for substantial missing subjects, retire exact duplicates and explicitly replaced claims, and fold durable outcomes into page State. Use for unlinked-claim cleanup or the scheduled review that follows…
gh-issues
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.