oc-architect

oc-architect is a command for Claude Code from TheophilusChinomona/claude-openclaw-plugin. It costs 30 tokens per session (569 once invoked), scanned B, original, MIT.

A command for creating or improving the workspace files that define an OpenClaw agent's role, identity, memory, rules, and goals. It can work from an interview or by scanning an existing workspace.

In plain words
What is it for?
Use it to build a new agent workspace or optimize an existing one, including files such as SOUL.md, IDENTITY.md, AGENTS.md, MEMORY.md, and GOALS.md.
Why use it?
It helps create the instructions an agent needs or find areas where those instructions need improvement.

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 Use it to build a new agent workspace or optimize an existing one, including files such as SOUL.md, IDENTITY.md, AGENTS.md, MEMORY.md, and GOALS.md.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/theophiluschinomona/claude-openclaw-plugin/oc-architect"><img src="https://agentmods.dev/badge/commands/theophiluschinomona/claude-openclaw-plugin/oc-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 569 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00030 $0.00569
Opus 5 $0.00015 $0.00284
Sonnet 5 $0.00006 $0.00114
Haiku 4.5 $0.00003 $0.00057

Measured 10d ago against content hash c18f8706fd0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

oc-architect scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Recommend `chmod 444` on SOUL.md and IDENTITY.md after finalizing
plugins/openclaw/commands/oc-architect.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/oc-architect Command

Build or optimize OpenClaw agent workspace files through the openclaw-agent-architect skill.

Arguments

The user provides: $ARGUMENTS

Parse:

  • Subcommand (default: build): build or optimize
  • workspace-path (optional): Path to the agent workspace. Default: ~/.openclaw/workspace

If no subcommand is given, use build.

Skill Reference

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

build

Run Mode 1: Build from Scratch. Conduct the 5-phase interview (SOUL → IDENTITY → AGENTS → MEMORY → GOALS), then generate each file after its phase. Use templates as scaffolding only; customize from the user's answers. See skills/openclaw-agent-architect/references/templates.md for file structure.

  • Phase 1: SOUL.md — role, personality, values, boundaries, communication style
  • Phase 2: IDENTITY.md — name, emoji, status line
  • Phase 3: AGENTS.md — memory rules, safety, workflows, tool rules
  • Phase 4: MEMORY.md — user profile, projects, preferences, people
  • Phase 5: GOALS.md — active goals, milestones, review schedule

Write files into the given workspace path. Keep SOUL.md under 2,000 words; ensure persona coherence across all files.

optimize

Run Mode 2: Scan & Optimize. Read all existing workspace markdown files at the given path, then:

  1. Audit for completeness (which files exist, which are missing or sparse)
  2. Check consistency (SOUL vs AGENTS, GOALS vs MEMORY)
  3. Check for bloat (SOUL over 2,000 words, redundancy)
  4. Check for vagueness (generic instructions)
  5. Check persona coherence
  6. Propose specific improvements with before/after; show changes before writing

Preserve the user's intent; tighten language for token awareness.

Guidelines

  • Never include API keys, passwords, or tokens in any generated file
  • Recommend chmod 444 on SOUL.md and IDENTITY.md after finalizing
  • GOALS.md is a custom addition (OpenClaw loads all .md from workspace)—mention this to the user

Read the full file on GitHub · 55 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 · 55 lines · 30 tokens per session scan B c18f8706fd0b

Subscribe to this mod's changes

oc-architect is a command published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 569 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.