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 commands/sifxprime/kodelyth-ecc/clawgit clone --depth 1 https://github.com/sifxprime/kodelyth-eccWrote 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/commands/sifxprime/kodelyth-ecc/claw)<a href="https://agentmods.dev/commands/sifxprime/kodelyth-ecc/claw"><img src="https://agentmods.dev/badge/commands/sifxprime/kodelyth-ecc/claw.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 | $0.00018 | $0.00214 |
| Opus 5 | $0.00009 | $0.00107 |
| Sonnet 5 | $0.00004 | $0.00043 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade A, and why
claw 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 yesterday.
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.
What it actually says
Claw Command (Legacy Shim)
Use this only if you still reach for /claw from muscle memory. The maintained implementation lives in skills/nanoclaw-repl/SKILL.md.
Canonical Surface
- Prefer the
nanoclaw-replskill directly. - Keep this file only as a compatibility entry point while command-first usage is retired.
Arguments
$ARGUMENTS
Delegation
Apply the nanoclaw-repl skill and keep the response focused on operating or extending scripts/claw.js.
- If the user wants to run it, use
node scripts/claw.jsornpm run claw. - If the user wants to extend it, preserve the zero-dependency and markdown-backed session model.
- If the request is really about long-running orchestration rather than NanoClaw itself, redirect to
dmux-workflowsorautonomous-agent-harness.
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.
- yesterday First seen · 24 lines · 18 tokens per session scan A d19e4c1b61bb
claw is a command published in the GitHub repository sifxprime/kodelyth-ecc (11 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 214 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
toh-help
Display all Toh Framework commands and quick usage guide.
research
Delegate a thorough research investigation to the agy:runner subagent.
kimi-setup
Run node "$HOME/.kimi-plugin/kimi-companion.mjs" setup, then report installation and authentication status.
Obad
Search for given words or phrases in the book of Obadiah in one or multiple bibles.
strategy-cfo
商业战略与财商融合决策专家 — 商业模式 / 资本结构 / 投资决策 / 资源配置 / 估值视角.
learn
Analyze the current session and extract any patterns worth saving as skills.