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/proof)<a href="https://agentmods.dev/commands/coltonbearden/carrel/proof"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/proof/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/proof"><img src="https://agentmods.dev/badge/commands/coltonbearden/carrel/proof.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 | $0.00046 | $0.00647 |
| Opus 5.5 | $0.00018 | $0.00259 |
| Sonnet 5.5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
proof 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
Soft-proof: $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 proof --help differs, trust the installed version — never invent flags):
Usage: carrel proof [OPTIONS] SRC
Soft-proof SRC against an ICC PROFILE (simulate print/display output).
Writes the proofed image and reports the color shift: mean/max per-channel delta and the share of
pixels that moved visibly. With --json, prints the report as one JSON object.
Options:
--profile PROFILE Path to a .icc file, or builtin alias: cmyk, gray, p3, srgb.
[required]
--out FILE Proofed image path [default: <SRC>.proof.png].
--intent [perceptual|relative] Rendering intent. [default: perceptual]
--json Machine-readable JSON output.
--help Show this message and exit.
--profile(required): a.iccpath or a builtin alias —cmyk("how will this print"),gray,p3(wide-gamut displays),srgb.carrel doctor --jsonlists theicc_dirswhere system profiles live if the user names a specific printer profile.--intent perceptual(default; pleasing overall) orrelative(colorimetric; exact in-gamut colors, clipped out-of-gamut).--out FILEdefaults to<SRC>.proof.png; the original is never modified.
Use --json and translate the report for the user: the proofed image path, mean/max per-channel delta, and the share of pixels that moved visibly — "X% of pixels shift noticeably; the largest changes are in " is more useful than raw numbers. Offer carrel diff SRC OUT --mode image --out heatmap.png to show where the shift lands, and carrel color convert --to-profile when the user wants to actually embed the profile rather than preview it. Exit code 4 means the input is not an image or the profile could not be read.
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 · 38 lines · 46 tokens per session scan A a2003485e4f7
proof is a command published in the GitHub repository coltonbearden/carrel (2 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 647 once invoked, about $0.0002 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
verify
Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.
slides
Magazine-quality slide deck as a self-contained HTML page.
stitch-generate
Full Stitch pipeline — author prompts, generate screens via MCP, fetch images and code.
add-skill
Add a new Skill to the current plugin with proper structure.
hello
Greet the user with a friendly, personalized message.
excalidraw
Create or modify an editable Excalidraw diagram.