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/kevinzai/commander/ccc-clawgit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/ccc-claw)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-claw"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-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 | $0.00034 | $0.00336 |
| Opus 5 | $0.00017 | $0.00168 |
| Sonnet 5 | $0.00007 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
ccc-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
Start an interactive AI agent session with persistent markdown history and operational controls.
Usage
node scripts/claw.js
Or via npm:
npm run claw
Environment Variables
| Variable | Default | Description |
|---|---|---|
CLAW_SESSION |
default |
Session name (alphanumeric + hyphens) |
CLAW_SKILLS |
(empty) | Comma-separated skills loaded at startup |
CLAW_MODEL |
sonnet |
Default model for the session |
REPL Commands
/help Show help
/clear Clear current session history
/history Print full conversation history
/sessions List saved sessions
/model [name] Show/set model
/load <skill-name> Hot-load a skill into context
/branch <session-name> Branch current session
/search <query> Search query across sessions
/compact Compact old turns, keep recent context
/export <md|json|txt> [path] Export session
/metrics Show session metrics
exit Quit
Notes
- NanoClaw remains zero-dependency.
- Sessions are stored at
~/.claude/claw/<session>.md. - Compaction keeps the most recent turns and writes a compaction header.
- Export supports markdown, JSON turns, and plain text.
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 · 52 lines · 34 tokens per session scan A d241e07e72ff
ccc-claw is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 336 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 2026-09-03.
Other commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
review
Run a Codex code review of your working tree or a branch (read-only).
adv-codex
Send a prompt to Codex CLI and return the response.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
planning-triage
Quick-score an enhancement, bug, or feedback item using the impact-first triage framework. Creates an issue if approved.
add-hook
Add a new hook to .claude/settings.json. Quick operation, no full interview needed. Trigger phrases: "add hook", "auto-format on save", "run tests after edit", "lint on write", "run [command] after [tool]".