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.
git 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-caveman)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-caveman"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-caveman/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/commands/kevinzai/commander/ccc-caveman"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-caveman.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 | $0.00033 | $0.00345 |
| Opus 5.5 | $0.00013 | $0.00138 |
| Sonnet 5.5 | $0.00007 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
ccc-caveman 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 5d 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.
What it actually says
/ccc-caveman — terse output mode
CC Commander · /ccc-caveman · compressed responses for fast iteration; code, commands and error text stay exact.
Arguments
$ARGUMENTS: lite, full or ultra (default full); off deactivates.
What happens
- Read the grammar rules and intensity definitions from the caveman skill:
skills/caveman/SKILL.mdin this repository, or~/.claude/skills/caveman/SKILL.mdwhen installed. If neither exists, say the skill is not installed and stop. - Activate the requested intensity and confirm in one line:
- lite:
Caveman lite active. Fluff gone, grammar stays. - full:
Caveman mode. Few words. Full brain. - ultra:
Ultra. Max compress. Go.
- lite:
- Apply the caveman rules to every response until deactivated.
- Deactivate on
/ccc-caveman off, "stop caveman" or "normal mode", and confirm withNormal mode.
Done when
The confirmation line for the chosen level (or Normal mode.) has been sent.
Guardrails
- Never compress code blocks, commands, file paths or quoted error messages.
- Safety warnings and confirmation questions stay in full sentences.
See also
/ccc-context-budget · /ccc-cost
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.
- 5d ago Changed · +15 lines · +7 tokens per session 9806bdb39808
- 1mo ago First seen · 20 lines · 26 tokens per session scan A 5171fcb228a6
ccc-caveman is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 345 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
on
Prevent the machine from sleeping (optionally for a fixed duration).
busy
Inhibit sleep only while Claude is actively processing.
context-stats
Display context window usage and token statistics.
cancel-ralph
Cancel active Ralph Wiggum loop.
scout-work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.