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/index)<a href="https://agentmods.dev/commands/coltonbearden/carrel/index"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/index/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/index"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/index.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 | $0.00000 | $0.00938 |
| Opus 5 | $0.00000 | $0.00469 |
| Sonnet 5 | $0.00000 | $0.00188 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
index 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 2d 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
Index for the desk: $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 index --help differs, trust the installed version — never invent flags):
Usage: carrel index [OPTIONS] [PATHS]...
Index PATH... (default: the desk root) into .carrel/carrel.db.
Walks directories for the supported file types plus plain-text source and config files (.py, .rs,
.toml, .yaml, ... — indexed as type `code`, use --no-source to skip them), honoring .gitignore and
skipping hidden entries (.carrel, .git, dotfiles). Files unchanged since the last run (same size +
mtime) are skipped. Text comes from core.textextract; images are registered but only get
searchable text with --ocr. Progress goes to stderr; the JSON summary is {"indexed", "skipped",
"pruned", "errors"}. `--status` prints the `carrel catalog status` report instead.
Options:
--ocr OCR images and scanned PDFs (needs tesseract / ocrmypdf).
--prune Remove index rows whose files no longer exist on disk.
--update Treat PATH... as individual files to (re)index — no directory walking; unsupported
or missing files are silently skipped.
--if-indexed Exit 0 silently when no desk db exists yet under --root (for hooks: only refresh
an index someone already created).
--no-source Skip plain-text source and config files (.py, .rs, .toml, .yaml, ...); index only
the document types.
--no-gitignore Do not honor .gitignore files while walking.
--status Report index health instead of indexing (alias of `carrel catalog status`); other
options are ignored. Exit 4 when no desk db exists under --root.
--json Machine-readable JSON output.
--help Show this message and exit.
Note: --json and --root are global flags and go before index (carrel --json --root DIR index). The desk root is where .carrel/carrel.db lives — default cwd; use --root when the user's collection is elsewhere.
- No PATHS: index the whole desk root. Directories are walked for supported types; hidden entries (
.carrel,.git, dotfiles) are skipped. Unchanged files (same size + mtime) are skipped, so re-running is always cheap and safe. --ocr: also make images/scanned PDFs searchable (needs tesseract/ocrmypdf) — only when the user wants scan text found.--prune: drop index rows for files that no longer exist.--update FILE...: (re)index just those files, no walking.--if-indexed: hook mode — silently exit 0 when no desk exists yet (never creates one).--status: report index health (schema_version, row counts,stale.changed/missing/unindexed) instead of indexing — the same report ascarrel catalog status.
Interpret {indexed, skipped, pruned, errors} for the user; if --status shows stale entries, offer a plain carrel index (and --prune for missing files). Exit code 3 means an OCR binary is missing — relay the install hint from stderr. Exit code 4 with --status means there is no desk db yet.
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.
- 2d ago Changed · +4 lines a7814f26482c
- 7d ago First seen · 49 lines · 0 tokens per session scan A 46e844b3b010
index is a command published in the GitHub repository coltonbearden/carrel (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 938 tokens. 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
receipt
Upload and process receipt images or PDF invoices, extract line items, and match to bank transactions.
sheet-report
Analyze a Numbers or Excel file and generate a report with charts.
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.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.