Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leionion/ClawForgenpx agentmods add skills/leionion/clawforge/openclaw-skillWrote 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/leionion/clawforge/openclaw-skill)<a href="https://agentmods.dev/skills/leionion/clawforge/openclaw-skill"><img src="https://agentmods.dev/badge/skills/leionion/clawforge/openclaw-skill/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/leionion/clawforge/openclaw-skill"><img src="https://agentmods.dev/badge/skills/leionion/clawforge/openclaw-skill.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 | $0.00040 | $0.00638 |
| Opus 5.5 | $0.00016 | $0.00255 |
| Sonnet 5.5 | $0.00008 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
metaskillbase 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw Skill Forge — Demand Decomposition for OpenClaw
When a user describes what they want in natural language, use OpenClaw Skill Forge to decompose the demand into atomic meta skills, then execute or hand off.
When to Use
- User says: "backup my chat memory", "run a backtest on my data", "organize my files"
- Multi-step or ambiguous demands that need skill mapping
- Before executing—decompose first to route correctly
How It Works
- Decompose: Call OpenClaw Skill Forge Cutter with the user's demand.
- Skills returned: e.g.
memory_backup,strategy_backtest,file_copy, etc. - Runnable standalone:
memory_backup,strategy_backtestrun viametaskillCLI. - Needs OpenClaw: Mac HCI, device, other skills—use OpenClaw's native skills.
Usage
CLI (recommended)
# Install: pip install -e /path/to/ClawForge
metaskill "backup my chat memory"
metaskill "run backtest on trading data" --decompose-only
metaskill --list
Python API
from core.cutter import CutterEngine
result = CutterEngine().process("backup my chat memory")
# result["decomposed"] → [{"skill": "memory_backup", "confidence": 0.8, ...}]
LLM Decomposition (optional)
Set CHUTES_API_KEY in .env and use --model chutes for smarter decomposition.
Cutter Keywords
| Demand phrase | Skill |
|---|---|
| backup my, chat memory, memory backup | memory_backup |
| backtest, trading strategy, quantitative | strategy_backtest |
| file copy, move, delete | file_copy, file_move, file_delete |
| open app, close app | open_app, close_app |
| screenshot, brightness, volume | screenshot, brightness, volume |
| ... see Skill-Index.md |
Installation
cd ClawForge
pip install -e .
# Install into OpenClaw workspace (or run ./scripts/setup_openclaw.sh)
cp -r openclaw-skill ~/.openclaw/workspace/skills/metaskillbase
Permissions
- filesystem: For memory_backup, strategy_backtest (read/write CSVs, backups)
- network: Optional for strategy_backtest (data fetch), GPT decomposition
- shell: Run metaskill CLI from OpenClaw
What ships with it
1 file 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.
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.
- 1mo ago First seen · 76 lines · 40 tokens per session scan A a543db88cfc5
metaskillbase is a skill published in the GitHub repository leionion/ClawForge (89 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 638 once invoked, about $0.0002 per session on Opus 5.5. 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
tmux
Use when a CLI task needs an interactive terminal or control of a tmux session.
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
add-resend
Add Resend (email) channel integration via Chat SDK.
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
communication
Use before sending @mentions, deciding whether to reply, TASKCOMPLETED, BLOCKED, QUESTION, direct answers, loop prevention, or suppressing low-information acknowledgements.