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-aside)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-aside"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-aside/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-aside"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-aside.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 | $0.00038 | $0.00857 |
| Opus 5.5 | $0.00015 | $0.00343 |
| Sonnet 5.5 | $0.00008 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
ccc-aside 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.
This is a copy
100% identical to aside — 177 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-aside — side question, then resume
CC Commander · /ccc-aside · a focused answer to one question, then the paused task continues from the same point.
Usage
/ccc-aside <question>
/ccc-aside what does this function actually return?
/ccc-aside is this pattern thread-safe?
/ccc-aside should we worry about the N+1 query we just added?
The question is $ARGUMENTS.
What happens
-
Hold the task state. Note the active task (file, feature or problem), the step in progress, and the next planned step. Do not create, edit or delete any file during the aside.
-
Answer directly. Lead with the answer, keep it short, and cite
path:linewhen the question is about code. If answering needs a file, read it (read-only). -
Use this shape:
ASIDE: <question, restated briefly> <answer> — Back to task: <one line naming the paused work> -
Resume. Continue the paused task from the exact step it stopped at, without asking permission, unless a case below says to wait.
Cases
| Situation | Do this |
|---|---|
| No question given | Reply ASIDE: no question provided, ask what they want to know, and end with the back-to-task line. |
| No active task | Use the same shape and end with — Back to task: no active task to resume. |
| Answer exposes a problem with the current approach | Add ⚠️ Note: this suggests <issue> with the current approach. and ask (below) before resuming. |
The "question" is really a direction change (for example /ccc-aside actually, let's use Redis instead) |
Ask (below); do not assume. |
| Answer implies a code change | Add 📝 Worth fixing: <change>. I'll raise it after the current task. Do not make the change during the aside. |
| A full answer would be long | Give the essential answer and offer a deeper explanation after the current task. |
| Several asides in a row | Answer each in order, then resume once, with the task state intact. |
| Question is ambiguous | Ask one short clarifying question, no more. |
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 · -79 lines · +16 tokens per session 72a9922a1910
- 1mo ago First seen · 165 lines · 22 tokens per session scan A 1330218c3385
ccc-aside is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 857 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to aside, differing in 177 lines, and is treated as a copy.
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.