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/batch)<a href="https://agentmods.dev/commands/coltonbearden/carrel/batch"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/batch/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/batch"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/batch.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 | $0.00037 | $0.00965 |
| Opus 5.5 | $0.00015 | $0.00386 |
| Sonnet 5.5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
batch 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
Run the bulk task the user asked about: $ARGUMENTS
Run the carrel CLI via Bash. Map the request onto the real flags in the --help block below (regenerated from the CLI by scripts/sync_plugins.py; if the installed carrel batch --help differs, trust the installed version — never invent flags):
Usage: carrel batch [OPTIONS] PATHS...
Run --run actions over every file in PATH... (files, or directories walked like `index`).
Exit 0 when every file succeeded, 1 when any failed (its record carries the rc, stdout and
stderr), 5 with --fail-empty when nothing matched. JSON output is {"summary": {total, ran, ok,
failed, skipped, seconds}, "results": [{path, cmd, rc, stdout, stderr, seconds, ok}]} (cmd/rc are
the failing or last action's, stdout/stderr every action's output in order); --json-lines streams
the records instead. --manifest + --resume make a long run restartable.
Options:
--run CMD Shell action per file; repeatable, runs in order, stops at the first
failure. Substituted (shell-quoted): {path}, {name}, {stem}, {ext},
{dir}. [required]
--glob PATTERN Only files whose name matches (e.g. '*.pdf').
--type T1,T2 Only these detected types (pdf, md, eml, code, …).
--recursive / --no-recursive Walk directories (hidden and .gitignored entries skipped).
[default: recursive]
--jobs INTEGER RANGE Files to process in parallel. [default: 1; x>=1]
--dry-run Print the rendered commands without running anything.
--manifest FILE Append one JSON record per file to this file.
--resume Skip files whose last --manifest record succeeded with the same
--run set.
--fail-fast Stop after the first failing file.
--action-timeout SECS Kill an action that runs longer than SECS (rc=124). [default:
300.0; x>0]
--fail-empty Exit 5 when no file matched.
--json-lines Stream one JSON record per file as it completes, then a summary
line.
--json Machine-readable JSON output.
--help Show this message and exit.
- Compose the action with the same placeholders as
watch:--run 'carrel convert {path} --to txt --out-dir OUT'; repeated--runflags run in order per file and stop at the first failure.{path},{name},{stem},{ext}and{dir}are shell-quoted for you. - Dry-run first for anything that writes or deletes (
--dry-runprints every rendered command); narrow with--glob '*.pdf'/--type pdf,docx; parallelise read-only work with--jobs 4. - Long runs:
--manifest run.jsonlrecords every file;--resumeskips what already succeeded, so a run can be restarted after a crash or a fixed binary.--fail-faststops at the first failure;--action-timeoutbounds each action. - Exit 1 means at least one file failed — read its
rc/stderrfrom--jsonand report which files, not just the count. Exit 5 with--fail-emptywhen nothing matched.
Report the summary (ok/failed/skipped) and list failures with their error text. Never rm, overwrite or move in an action without an explicit, confirmed request.
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 · 56 lines · 37 tokens per session scan A 0ca2d4c1a200
batch is a command published in the GitHub repository coltonbearden/carrel (2 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 965 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 2026-09-11.
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.