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-careful)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-careful"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-careful/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-careful"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-careful.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 | $0.00377 |
| Opus 5.5 | $0.00015 | $0.00151 |
| Sonnet 5.5 | $0.00008 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade C, and why
ccc-careful scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Refuse destructive commands** and explain why: `rm -rf`, `DROP TABLE` / `DROP DATABASE`, `git push --force`, `kubectl delete`, `docker system prune`, `pm2 delete all`, and equivalents. What it actually says
/ccc-careful — careful mode for this session
CC Commander · /ccc-careful · session-long safety constraints the assistant follows until you turn them off.
Arguments
$ARGUMENTS: empty or on activates; off deactivates.
What happens
- Reply
Careful mode is on.and apply these rules to every remaining turn:- Refuse destructive commands and explain why:
rm -rf,DROP TABLE/DROP DATABASE,git push --force,kubectl delete,docker system prune,pm2 delete all, and equivalents. - Confirm before mutations: file deletion, database writes, production deploys, configuration changes. Ask with AskUserQuestion (plain-text question where unavailable): 🟢 Cancel · Proceed with this exact command (shows it).
- Show the diff before writing any file.
- Log commands: keep a running list of every shell command run this session and print it on request or when careful mode ends.
- Refuse destructive commands and explain why:
- On
/ccc-careful off, replyCareful mode is off.and print the command log.
Done when
The activation or deactivation line has been sent; while on, every mutation in the session has a recorded user choice.
Guardrails
- These rules are instructions the assistant follows, not enforcement. For hook-level blocking, use the
guardorfreezeskills. - Careful mode never weakens a stricter rule already in force.
See also
/ccc-checkpoint · /ccc-verify
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 · +19 lines · +22 tokens per session e45b1e729a43
- 1mo ago First seen · 15 lines · 16 tokens per session scan C 0f37f94c89f6
ccc-careful 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 377 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
loop
Autonomous execution loop. Runs the TDD cycle repeatedly until all tasks in an epic are complete, with circuit breaker protection and PR workflow.
phase
Orchestrate a full roadmap phase. Designs features, imports to tracker, creates issues, then executes.
status
Show current execution status with progress, dependencies, file ownership, and parallelization opportunities.
justone-publish
Publish a completed JustOne build — create a public GitHub repo, push, and register on the gallery.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.