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 TheophilusChinomona/claude-openclaw-plugin --skill openclaw-agent-architectgit clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-pluginWrote 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/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-architect)<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-architect"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-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.
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-architect"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-agent-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00172 | $0.02288 |
| Opus 5 | $0.00086 | $0.01144 |
| Sonnet 5 | $0.00034 | $0.00458 |
| Haiku 4.5 | $0.00017 | $0.00229 |
Grade B, and why
openclaw-agent-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 11d 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.
- **Security**: Never include API keys, passwords, or tokens in any workspace file. SOUL.md and MEMORY.md are common targets for prompt injection attacks (see the ClawHavoc campaign). Recommend `chmod 444` on SOUL.md and How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw Agent Architect
Build, configure, and optimize OpenClaw agent workspace files through guided interviews and workspace analysis.
Overview
OpenClaw agents are defined by markdown files in a workspace directory (default: ~/.openclaw/workspace). Each file serves a distinct purpose:
| File | Purpose | Loaded When |
|---|---|---|
| SOUL.md | Behavioral philosophy, personality, values, communication style, boundaries | Every session (system prompt) |
| IDENTITY.md | External presentation — name, emoji, status line | Every session (display layer) |
| AGENTS.md | Operating instructions — memory rules, safety, group chat behavior, workflows | Every session + subagent sessions |
| MEMORY.md | Long-term persistent memory — learned facts, preferences, project context | Normal sessions only (optional) |
| GOALS.md | Active goals, milestones, priorities, progress tracking | Normal sessions (custom addition) |
SOUL.md defines who the agent is. IDENTITY.md defines how it presents. AGENTS.md defines how it operates. MEMORY.md defines what it knows. GOALS.md defines what it's working toward.
Workflow
This skill operates in two modes:
Mode 1: Build from Scratch (Interview → Generate)
When the user wants to create new agent files, conduct a targeted interview before generating anything. Do not dump a generic template — ask questions, listen, then craft files that reflect the user's actual needs.
Interview Protocol
Run the interview in phases. Each phase covers one file. Ask 3-5 focused questions per phase, wait for answers, then generate that file before moving to the next phase. The user can skip phases for files they don't need.
Phase 1: SOUL.md — Who is your agent?
Core questions to ask (adapt based on context):
- What is your agent's primary role? (personal assistant, DevOps bot, research agent, team helper, etc.)
- What personality traits should it have? (direct, warm, sarcastic, formal, casual, opinionated, cautious)
- What are 3-5 core values that should guide its decisions? (e.g., "accuracy over speed", "ask before acting on anything destructive", "be concise")
- What should it NEVER do? (boundaries and anti-patterns)
- What communication style do you want? (length, tone, emoji usage, humor level, language)
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agent-templates/code-reviewer.md 2.2 KB
- references/agent-templates/devops-automator.md 1.2 KB
- references/agent-templates/feedback-synthesizer.md 1.3 KB
- references/agent-templates/index.md 1.6 KB
- references/agent-templates/security-engineer.md 1.9 KB
- references/agent-templates/software-architect.md 2.4 KB
- references/agent-templates/sprint-prioritizer.md 1.3 KB
- references/agent-templates/technical-writer.md 2.0 KB
- references/agent-templates/ux-researcher.md 1.8 KB
- references/templates.md 5.9 KB
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.
- 11d ago First seen · 174 lines · 172 tokens per session scan B 659dbddb82d1
openclaw-agent-architect is a skill published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 172 tokens to every session and 2,288 once invoked, about $0.0009 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.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.