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 agentmods add skills/ric03uec/clawrium/clawctlnpx skills add ric03uec/clawrium --skill clawctlgit clone --depth 1 https://github.com/ric03uec/clawriumWrote 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/ric03uec/clawrium/clawctl)<a href="https://agentmods.dev/skills/ric03uec/clawrium/clawctl"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/clawctl.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.04466 |
| Opus 5 | $0.00015 | $0.02233 |
| Sonnet 5 | $0.00006 | $0.00893 |
| Haiku 4.5 | $0.00003 | $0.00447 |
Grade A, and why
clawctl 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 4d 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 — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
clawctl — Fleet Management CLI
Use this skill whenever the user asks to manage their Clawrium fleet: creating or configuring agents, working with hosts, attaching providers or channels, managing skills, secrets, or memory. All fleet operations use clawctl — never clm.
Architecture
Your Machine (clawctl CLI)
│
├── Host A ──> zeroclaw instance
├── Host B ──> openclaw instance
└── Host C ──> nemoclaw instance, zeroclaw instance
- Config root:
~/.config/clawrium/ - Agent state:
~/.config/clawrium/agents/<agent>/ - SSH user on every host:
xclm - Agent types:
hermes,openclaw,zeroclaw,nemoclaw
Top-Level Commands
clawctl version # Show version and exit
clawctl completion # Emit shell-completion script
clawctl tui # Launch interactive TUI dashboard
clawctl gui # Launch local web GUI dashboard
clawctl apply <manifest> # Apply fleet manifest (declarative reconciliation)
clawctl diff <manifest> # Preview changes without applying
clawctl delete <manifest> # Delete resources declared in a manifest
clawctl service … # System-level lifecycle ops
clawctl host … # Manage fleet machines
clawctl agent … # Manage AI assistant instances
clawctl provider … # Inference backend providers
clawctl channel … # Chat surfaces (Discord, Slack)
clawctl integration … # External service integrations
clawctl skill … # Skills catalog and user overlay
clawctl service
System-level lifecycle for the control plane itself.
clawctl service init # Init config dir, check deps (ansible, ssh, python)
clawctl service start # Start Clawrium daemon (placeholder)
clawctl service stop # Stop Clawrium daemon (placeholder)
clawctl service snapshot # Snapshot fleet state (placeholder)
First-time setup:
clawctl service init
clawctl host
Manage fleet machines. Every host must have an xclm SSH user — see docs/host-preparation.md.
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.
- 4d ago First seen · 473 lines · 31 tokens per session scan A 200ef8b0d558
clawctl is a skill published in the GitHub repository ric03uec/clawrium (51 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 4,466 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
load-github-action-thread
Download retained Codex GitHub Action thread artifacts and load their rollout history into the local Codex app. Use when asked to open, load, import, resume, or inspect a Codex automation thread from a GitHub Actions run or a related GitHub issue or pull request.
uv-workflow
Use when a coding agent needs to run Python code, modules, one-liners, tools, tests, or standalone scripts through uv, or create and maintain PEP 723 scripts with uv init/add/remove --script. Avoid direct python/python3 shell entrypoints.
simulate-contracts
Compile the contract set in your head — simulate how the real application would run from the specs, and disprove (or confirm) it works before any source .py is written.
model-data-schema
Author the persistence schema as a binding contract from the captured external shapes and the interview — before any test stub is written.
author-test-stubs
Author test stub files (.pyi) whose signatures express the domain, relationships, and compositions, as the first contract surface.
derive-source-stubs
Derive the source stub files (.pyi) from the reviewed tests — every type the tests reference gets a definition.