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/Achitokun14/claude-universalWrote 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/achitokun14/claude-universal/careful)<a href="https://agentmods.dev/commands/achitokun14/claude-universal/careful"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/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/achitokun14/claude-universal/careful"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/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 | $0.00034 | $0.00323 |
| Opus 5 | $0.00017 | $0.00161 |
| Sonnet 5 | $0.00007 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade C, and why
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 8d 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.
description: Warn before destructive commands (rm -rf, DROP TABLE, git push --force, docker prune). Pairs with /freeze and /guard. Inspired by gstack. What it actually says
You are in CAREFUL mode for the next action. Before running any command that could lose data:
- State EXACTLY what the command will do in plain English.
- List the files/paths/services that would be affected.
- Ask for explicit confirmation: "Type 'yes, ' to proceed."
- Never proceed if user types anything other than the exact confirmation string.
Trigger list (require confirmation for any of these):
rm -rf,rmwith wildcards,find … -deleteDROP TABLE,DROP DATABASE,TRUNCATE,DELETE FROM … WHERE 1=1git push --force,git reset --hard,git clean -fd,git rebase -iof pushed commitsdocker system prune,docker volume rm,kubectl delete namespaceterraform destroy,railway destroy,vercel rmnpm publish,cargo publish,gh release create- any
sudooperation - writes to
.env*,*.key,*.pem,.credentials.json
If the user has $ARGUMENTS specified, they're describing a specific action — audit that action against the above, and explain the risk before executing.
CAREFUL mode persists for this session. To turn off: user types "exit careful mode".
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.
- 8d ago First seen · 25 lines · 34 tokens per session scan C bf0cd8289496
careful is a command published in the GitHub repository Achitokun14/claude-universal (2 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 323 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other commands, from other repositories
od-contribute
Open a first-contribution PR (or bug issue) on nexu-io/open-design — works for non-coders too.
task-dispatch
PitWay: Prepare a parallel-eligible task for worktree execution.
task-discard
PitWay: Abandon a dispatched task's worktree without integrating.
ssh-keys
Manage SSH keys across hosts — generate, sync, list status, or delete.
gss
Git Safe Sync (gss) status and help.
ssh-find
Find an SSH host on the local network and update /.ssh/config with its current IP.