oc-team

oc-team is a command for Claude Code from TheophilusChinomona/claude-openclaw-plugin. It costs 7 tokens per session (1,090 once invoked), scanned A, original, MIT.

A command for creating and managing a shared workspace for multiple software agents, including their files, identities, logs, and memory.

In plain words
What is it for?
Use it to initialize a team workspace, create an agent's SOUL.md template, validate the registry, or view the team structure.
Why use it?
It removes the manual setup work involved in organizing agents and checking whether their workspace registry is valid.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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

Good fit Use it to initialize a team workspace, create an agent's SOUL.md template, validate the registry, or view the team structure.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-team"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,090 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 $0.00007 $0.01090
Opus 5 $0.00003 $0.00545
Sonnet 5 $0.00001 $0.00218
Haiku 4.5 $0.00001 $0.00109

Measured 12d ago against content hash 5446400fd68b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

oc-team 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.

plugins/openclaw/commands/oc-team.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/oc-team Command

Manage agent team workspace — scaffold directories, generate SOUL.md templates, validate registry, show team structure.

Arguments

The user provides: $ARGUMENTS

Parse:

  • subcommand (required): init, soul, validate, or show
  • agent-id (required for soul): lowercase slug identifier for the agent

Subcommands

init

Scaffold the agent team workspace directory structure.

  1. Ask the user for the workspace path (default: current directory).
  2. Ask for a comma-separated list of agent IDs to create (or use a sensible default like jarvis).
  3. Create the directory structure:
WORKSPACE="<path>"
mkdir -p "$WORKSPACE"/{agents,team-memory,clawport}

for agent in <agent-list>; do
  mkdir -p "$WORKSPACE/agents/$agent"/{logs,output}
  touch "$WORKSPACE/agents/$agent/MEMORY.md"
  touch "$WORKSPACE/agents/$agent/SOUL.md"
done

touch "$WORKSPACE/team-memory"/{market-brief,icp-profile,competitor-map,brand-voice,content-calendar}.md
touch "$WORKSPACE/MEMORY.md"
  1. Create a starter clawport/agents.json with the first agent as orchestrator (reportsTo: null) and the rest as direct reports.
  2. Report what was created.

soul <agent-id>

Generate a SOUL.md template for the given agent.

  1. If clawport/agents.json exists, read it to get the agent's name, role, reports-to, and direct-reports.
  2. Generate a SOUL.md template using this structure:
# AGENT_NAME -- Role Title

## Identity
I am AGENT_NAME, the [Role Title]. [Describe personality and communication style].

## Expertise
- [Domain 1]
- [Domain 2]

## Operating Rules
- [Constraint 1]
- [Constraint 2]

## Relationships
- Reports to: [Parent Agent] ([Role])
- Manages: [Child agents, if any]
- Collaborates with: [Peer agents]

## Memory
- Persistent knowledge lives at agents/<id>/MEMORY.md
- Daily logs written to agents/<id>/logs/
  1. Write the template to agents/<agent-id>/SOUL.md.
  2. Tell the user to customize the personality, expertise, and constraints.

Read the full file on GitHub · 134 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. 12d ago First seen · 134 lines · 7 tokens per session scan A 5446400fd68b

Subscribe to this mod's changes

oc-team is a command published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 1,090 once invoked, about $0.0000 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.