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 | $0.00035 | $0.02017 |
| Opus 5 | $0.00017 | $0.01009 |
| Sonnet 5 | $0.00007 | $0.00403 |
| Haiku 4.5 | $0.00003 | $0.00202 |
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 12d 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 — 196 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 exposes ONE
LLM-callable tool, agentBuilder, which dispatches to FIVE
canvas-mutation operations via the operation field:
operation value |
Purpose |
|---|---|
inspect_canvas |
Read-only view of the canvas PLUS the full catalogue of every tool, agent, and skill you can spawn. ALWAYS call this first. |
add_tool |
Spawn a tool node + wire it to your input-tools handle. Idempotent — already-wired tools return success with no change. |
add_skill |
Toggle a skill on your Master Skill (auto-creates one if missing). Idempotent — already-enabled skills return success with no change. |
add_subagent |
Team-leads only — spawn a delegate agent + wire to your input-teammates. Idempotent — already-wired teammates return success with no change. |
create_workflow |
Temporarily disabled. Mutate the current workflow instead. |
Every call is agentBuilder({operation: "<one-of-above>", ...op-specific-fields}). There are no separate tools.
The cardinal rule
Call agentBuilder({operation: "inspect_canvas"}) BEFORE any
mutation. The response carries the full registry of spawnable types
(plus the live canvas) so you can pick the right one in a single
follow-up call instead of guessing. Skipping inspect_canvas means
you're flying blind on what's available.
Hot rebind (default: ON)
By default, tools / skills / teammates you spawn become callable in the same run, on your very next response. The mutation summary ends with "Available immediately — call it in your next response." Take this literally: you may invoke the new tool right away. No need to tell the user "send another message".
If the user has disabled the "Auto-Rebind Tools After Canvas Changes" toggle in Settings, mutation summaries end with "Available on your next turn." In that case the new wiring is staged but not callable this run — tell the user and stop calling that tool.
The summary text is your signal. Read it.
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.
- 12d 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 (883 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 2,017 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 2026-08-30.
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.
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.
acp-router
Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, 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 requests, read…
control-ui
Operate and troubleshoot the OpenClaw Control UI: navigate connected clients, organize sessions, build session dashboards, and handle direct or Tailscale-hosted Gateways.
gh-issues
Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.