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.
npx agentmods add commands/hainrixz/open-carrusel/startgit clone --depth 1 https://github.com/Hainrixz/open-carruselWrote 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/hainrixz/open-carrusel/start)<a href="https://agentmods.dev/commands/hainrixz/open-carrusel/start"><img src="https://agentmods.dev/badge/commands/hainrixz/open-carrusel/start.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00853 |
| Opus 5 | $0.00008 | $0.00426 |
| Sonnet 5 | $0.00003 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
start scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(node *), Bash(uname *), Bash(test *), Bash(lsof *), Bash(kill *), Bash(curl *), Bash(open *), Bash(xdg-open *), Bash(cmd.exe *), Bash(npm *), Bash(tail *), AskUserQuestion How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are bootstrapping Open Carrusel for the user. Be terse — short status updates only, no preamble.
Snapshot (these run before you see this prompt)
- Node: !
node --version 2>/dev/null || echo MISSING - Platform: !
uname -s 2>/dev/null || echo Windows - Port 3000 in use: !
lsof -ti :3000 2>/dev/null && echo YES || echo NO - node_modules: !
test -d node_modules && echo YES || echo NO - Data seeded: !
test -f data/carousels.json && echo YES || echo NO
User-supplied port (optional): $ARGUMENTS
Steps
-
Verify Node ≥ 20. Parse the version above. If MISSING or major version < 20, tell the user to install Node 20+ from https://nodejs.org and stop.
-
Pick port. Use
$ARGUMENTSif non-empty, else 3000. Call this<port>. -
Run setup if needed. If
node_modulesis NO orData seededis NO:- Tell the user: "Running setup (first time installs ~300MB Chromium for export — takes 1–2 minutes)..."
- Run
OC_SETUP_NO_DEV=1 npm run setupwith a 600s timeout. The env var tells the setup script to skip its own dev-server start (/startmanages the server itself in step 5). On Windows PowerShell use$env:OC_SETUP_NO_DEV=1; npm run setup; on cmd.exe useset OC_SETUP_NO_DEV=1 && npm run setup. - On failure, surface the error and stop.
-
Handle port collision. If
<port>is in use and the listening process is not the dev server you just started, ask via AskUserQuestion: "Port<port>is in use. Kill the existing process or pick a different port?" Options: Kill / Different port / Cancel.- Kill →
lsof -ti :<port> | xargs killthen proceed to step 5. - Different port → ask for new number, set
<port>, re-check, then step 5. - Cancel → stop.
- Kill →
-
Launch dev server in background (only if not already running on
<port>):PORT=<port> npm run dev > /tmp/open-carrusel-dev.log 2>&1 &via Bash withrun_in_background: true. -
Wait until ready. Poll
curl -sf http://localhost:<port>every 1s until 200 (60s cap). On timeout, runtail -30 /tmp/open-carrusel-dev.log, share the output, and stop.
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.
- 6d ago First seen · 50 lines · 15 tokens per session scan A d4d658c37cd2
start is a command published in the GitHub repository Hainrixz/open-carrusel (446 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 853 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
fieldtheory
Explain and drive the Field Theory CLI — bookmark-sourced seeds, repo-aware possibility runs that score ideas onto a 2x2 grid, and the interconnected .md files they leave behind. Trigger when the user asks about ft, bookmarks, seeds, ft possible (or the older name ft ideas), grids, dots/nodes, or how to turn saved…
iai-directive
Record a standing order the user typed themselves, as an explicit memory directive.
memory
What px0 knows about you, as opposed to what you have read.
rp-build-cli
Build with rp-cli context builder → chat → implement.
tma1-peer
List recent sessions on this project by agent — peers (Codex, OpenClaw, Copilot CLI) or your own.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.