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/tag)<a href="https://agentmods.dev/commands/coltonbearden/carrel/tag"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/tag/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/tag"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/tag.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 | $0.00019 | $0.00733 |
| Opus 5.5 | $0.00008 | $0.00293 |
| Sonnet 5.5 | $0.00004 | $0.00147 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
tag 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
Handle this tagging request: $ARGUMENTS
Run the carrel CLI via Bash. carrel tag is a group; map the user's request onto the real subcommands and flags in the --help blocks below (regenerated from the CLI by scripts/sync_plugins.py; if the installed carrel tag --help differs, trust the installed version — never invent flags). Tags live in the desk db (.carrel/carrel.db under the global --root, default cwd):
Usage: carrel tag [OPTIONS] COMMAND [ARGS]...
Tag files in the desk db (.carrel/carrel.db under --root).
Options:
--json Machine-readable JSON output.
--help Show this message and exit.
Commands:
add Add TAG...
find List files carrying ALL of TAG...
ls List tags of PATH, or (without PATH) every tag with its file count.
rm Remove TAG...
Usage: carrel tag add [OPTIONS] PATH TAGS...
Add TAG... to PATH (registers the file in the desk db if needed).
Options:
--json Machine-readable JSON output.
--help Show this message and exit.
Usage: carrel tag find [OPTIONS] TAGS...
List files carrying ALL of TAG... (paths relative to the desk root).
Options:
--json Machine-readable JSON output.
--help Show this message and exit.
Usage: carrel tag ls [OPTIONS] [PATH]
List tags of PATH, or (without PATH) every tag with its file count.
Options:
--json Machine-readable JSON output.
--help Show this message and exit.
Usage: carrel tag rm [OPTIONS] PATH TAGS...
Remove TAG... from PATH (unknown tags/files are a quiet no-op).
Options:
--json Machine-readable JSON output.
--help Show this message and exit.
- Choose the subcommand from intent: "tag X as invoice" →
add, "what's tagged urgent" →find, "untag" →rm, "what tags exist" →ls. addregisters the file in the desk db if needed;rmon unknown tags/files is a quiet no-op.findreturns paths relative to the desk root; ANDs multiple tags.- If the user's desk is elsewhere, put
--root DIRbeforetag(carrel --root DIR tag add ...).
Report what changed (or list the results) conversationally. Tags combine well with /carrel-inspect:search --tag for filtered full-text search, and /carrel-agent:catalog exports/imports them — mention that when relevant.
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 Changed · +53 lines 708df3b2f12b
- 1mo ago Changed 38bfd78387e2
- 1mo ago First seen · 25 lines · 19 tokens per session scan A 7cc1e44842ac
tag is a command published in the GitHub repository coltonbearden/carrel (2 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 733 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 2026-08-31.
Other commands, from other repositories
review-resume
Comprehensive PM resume review against 10 best practices — structure, impact metrics, keywords, and actionable feedback.
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…
stop
Gracefully close the Vibe Squad tmux session from inside Chrono.
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.
maestro-companion
Quick execution for small tasks — minimal run lifecycle (start + done) with evidence recording. Full LLM capability, scoped to mechanically clear tasks.