oc-planner

oc-planner is a command for Claude Code from TheophilusChinomona/claude-openclaw-plugin. It costs 24 tokens per session (558 once invoked), scanned A, original, MIT.

A command for planning teams of OpenClaw agents, where each agent has a defined role and permissions.

In plain words
What is it for?
Exploring your needs, proposing agents, mapping what each agent may do, designing how they work together, and writing the plan to a Markdown file.
Why use it?
It turns a vague idea for an agent team into a documented design with responsibilities, access limits, and communication rules.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.md; built for openclaw.

Part of the openclaw plugin — 31 skills, 22 commands, 4 agents, 3 hooks shipped together

Good fit Exploring your needs, proposing agents, mapping what each agent may do, designing how they work together, and writing the plan to a Markdown file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/theophiluschinomona/claude-openclaw-plugin/oc-planner
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.

Clone the repo
git clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-plugin

Made for: Claude Code.

Or install openclaw, the plugin that ships this one along with the rest of its 31 skills, 22 commands, 4 agents, 3 hooks.

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 oc-planner

README.md
[![agentmods](https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-planner/github.svg)](https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-planner)
Your own site
<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-planner"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-planner/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 oc-planner

Your own site · 80×15
<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-planner"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 558 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.
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 $0.00024 $0.00558
Opus 5 $0.00012 $0.00279
Sonnet 5 $0.00005 $0.00112
Haiku 4.5 $0.00002 $0.00056

Measured 10d ago against content hash 28a3079032d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

oc-planner 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 10d 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.

plugins/openclaw/commands/oc-planner.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/oc-planner Command

Run the openclaw-agent-planner skill to brainstorm, design, and document OpenClaw agent teams, then produce Agent Team Documentation.

Arguments

The user provides: $ARGUMENTS

Parse:

  • output-path (optional): Where to write the generated markdown document. If omitted, write to the current workspace or ask the user.

Skill Reference

Apply the full workflow from the openclaw-agent-planner skill (under skills/openclaw-agent-planner/SKILL.md).

Stage 1: Discovery

Understand the user's world: role & context, pain points & automation appetite, existing setup, constraints. Ask focused questions; don't re-ask what you can infer.

Stage 2: Design

  • 2.1 Agent brainstorm: Propose a table of agents (Name, Role, Why, Channel). Refine with the user (must-haves, overlaps, gaps, priority).
  • 2.2 Capability mapping: For each agent, build a permission matrix (Autonomous / Confirm / Restricted / Denied). Use references/permissions-reference.md in the planner skill for capability categories and archetype profiles (Personal Assistant, DevOps, Sales Dev, Research, SHEQ).
  • 2.3 Inter-agent design: If multiple agents, define communication, delegation, shared vs isolated resources, conflict resolution. Recommend the OpenClaw multi-agent pattern (per-agent workspace, shared AGENTS.md).
  • 2.4 Model selection: Recommend Opus/Sonnet/Haiku per agent based on task and cost.

Stage 3: Document

Generate the Agent Team Documentation with the exact structure in the skill: Team Overview, Agent Profiles (per agent: role, persona, capabilities, boundaries, workflows, memory strategy, goals, config snippet), Team Interaction Rules, Security & Governance, Implementation Roadmap, Appendix.

Save as markdown at the given output path. If the user wants .docx, use the docx skill to produce a formatted Word document.

Quality Checks

Before delivery, verify: every agent has a full profile; permission levels are consistent; no orphan agent references; roadmap has concrete steps; security covered; persona aligns with role.

Read the full file on GitHub · 48 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. 10d ago First seen · 48 lines · 24 tokens per session scan A 28a3079032d6

Subscribe to this mod's changes

oc-planner is a command published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 558 once invoked, about $0.0001 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.