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/coltonbearden/carrelWrote 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/coltonbearden/carrel/completion)<a href="https://agentmods.dev/commands/coltonbearden/carrel/completion"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/completion/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/coltonbearden/carrel/completion"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/completion.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 | $0.00027 | $0.00607 |
| Opus 5.5 | $0.00011 | $0.00243 |
| Sonnet 5.5 | $0.00005 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
completion 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 1mo 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
Set up carrel shell completion for: $ARGUMENTS
Run the carrel CLI via Bash. Map the user's request onto the real flags in the --help block below (regenerated from the CLI by scripts/sync_plugins.py; if the installed carrel completion --help differs, trust the installed version — never invent flags):
Usage: carrel completion [OPTIONS] {bash|zsh|fish}
Print a completion script for SHELL (bash, zsh, or fish).
eval "$(carrel completion bash)" # ~/.bashrc
eval "$(carrel completion zsh)" # ~/.zshrc, after compinit
carrel completion fish > ~/.config/fish/completions/carrel.fish
The script is produced in-process by click; an unknown shell exits 2. With --json, emits {"shell":
..., "script": ...}.
Options:
--install-hint Append, as a comment block, how to enable the script in that shell.
--json Machine-readable JSON output.
--help Show this message and exit.
SHELLis one ofbash,zsh,fish; an unknown shell exits 2. If the user didn't say which, checkecho $SHELLand ask only if it's ambiguous.--install-hintappends, as a comment block, how to enable the script in that shell — run with it once and relay the instructions verbatim.--jsonreturns{shell, script}if you need to inspect the script rather than print it.
Do not modify the user's ~/.bashrc, ~/.zshrc or fish config yourself — this plugin's tools are limited to running carrel. Show the exact one-liner from the help (eval "$(carrel completion bash)" in ~/.bashrc; zsh after compinit; fish writes to ~/.config/fish/completions/carrel.fish) and let the user add it, then tell them to open a new shell (or source the rc file) and try carrel <Tab>.
Requires the carrel CLI on PATH. If carrel is not found, tell the user to install it with uv tool install carrel (see the repo's INSTALL notes), or run it as uv run carrel ... from the carrel repo root.
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.
- 1mo ago First seen · 39 lines · 27 tokens per session scan A b856fc6e6938
completion is a command published in the GitHub repository coltonbearden/carrel (2 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 607 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 2026-09-05.
Other commands, from other repositories
review-resume
Comprehensive PM resume review against 10 best practices — structure, impact metrics, keywords, and actionable feedback.
vs-stop
Gracefully close the Vibe Squad tmux session from inside Chrono.
follow-up
Review and act on pending reminders. Bare invocation shows all reminders as an indexed list; cron-fired invocation (/follow-up due ) surfaces the specific reminder and waits for a response; /follow-up review lists stale project follow-up entries for per-item disposition (extend/close/promote/skip). Transport-aware…
amp-download
Command "amp-download" from agentmessaging/claude-plugin, covering /amp-download, usage, arguments, options and examples.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
add-skill
Add a new Skill to the current plugin with proper structure.