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/hbkdad/arc/acr-dashboardgit clone --depth 1 https://github.com/hbkdad/arcWrote 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/hbkdad/arc/acr-dashboard)<a href="https://agentmods.dev/commands/hbkdad/arc/acr-dashboard"><img src="https://agentmods.dev/badge/commands/hbkdad/arc/acr-dashboard.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 | $0.00021 | $0.00340 |
| Opus 5 | $0.00010 | $0.00170 |
| Sonnet 5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
acr-dashboard 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 4d 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
ACR has no background service -- the dashboard is a local web server (acr dashboard serve) that only exists once something starts it, and blocks its terminal like any dev server. This command is that one step.
If the Browser pane tools are available in this session:
- Call
preview_startwith{"name": "acr-dashboard"}--.claude/launch.jsonalready defines this entry (uv run acr dashboard serve, port 8765). It reuses an already-running instance rather than starting a duplicate. - Report the URL back to the user.
- Do a quick real check that it's actually serving live data, not just that the process started:
read_console_messagesfor errors, thenget_page_texton the Overview page and confirm it shows something other than an error page. Don't fabricate what it shows -- report what's actually there (including "no tasks recorded yet" if that's genuinely the state).
If Browser pane tools are not available in this session (a plain terminal-only context), tell the user to run this themselves and report the URL once they confirm it's up:
uv run acr dashboard serve --open-browser
--open-browser opens their default browser automatically once the server is ready; omit it if they'd rather navigate to http://127.0.0.1:8765 manually. This blocks the terminal it runs in by design (no daemon mode) -- either give it its own terminal, or background it themselves (... &, or a separate shell).
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.
- 4d ago First seen · 20 lines · 21 tokens per session scan A 16cd51671aed
acr-dashboard is a command published in the GitHub repository hbkdad/arc (4 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 340 once invoked, about $0.0001 per session on Opus 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
ship-and-babysit
Commit, push to origin (fork), open PR to tinyhumansai/openhuman:main, then poll every 5min for CodeRabbit comments and CI failures, resolve them, and exit when clean.
rp-build-cli
Build with rp-cli context builder → chat → implement.
start-feature
Command "start-feature" from melagiri/code-insights, covering /start-feature — auto-setup feature development team, step 1: create git worktree, example (adapt the slug from $arguments), step 2: create named team and step 3: spawn pm agent.
forkmind
Start ForkMind or branch/inspect/regression-test an LLM call.
models
Search Ryu's model catalog and optionally activate a local model.
workflow
List Ryu workflows and run one by id.