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 skills add band-app/band --skill band-loopgit clone --depth 1 https://github.com/band-app/bandWrote 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/skills/band-app/band/band-loop)<a href="https://agentmods.dev/skills/band-app/band/band-loop"><img src="https://agentmods.dev/badge/skills/band-app/band/band-loop/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/skills/band-app/band/band-loop"><img src="https://agentmods.dev/badge/skills/band-app/band/band-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 96 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00172 | $0.03191 |
| Opus 5.5 | $0.00069 | $0.01276 |
| Sonnet 5.5 | $0.00034 | $0.00638 |
| Haiku 4.5 | $0.00017 | $0.00319 |
Grade A, and why
band-loop 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Band Loop
Recurring agent tasks via band cronjobs. The agent fires on a cron schedule against a target worktree — dispatching each iteration to the worktree's chat pane (default) or the agent's terminal CLI (--via terminal) — optionally checks a stop condition each iteration, and deletes its own cronjob when the condition is met.
This is the native answer for users who reach for Claude Code's built-in /loop: that command is gated behind scheduledTasksEnabled, which is always false in SDK / Band sessions. band cronjobs runs server-side and survives session restarts.
This skill is focused on the scheduled-loop pattern. For broader operations see the sibling skills:
band— worktrees, repos, tunnel, settings (also documentsband cronjobsfor general CRUD).band-start— create a new worktree and kick off the first agent task.band-chat— chat panes inside a worktree (the loop's prompt is dispatched to a chat).
Prerequisites
- The Band server must be running (started by the Band dashboard app).
- A target worktree must exist (use
band-startto create one first if needed).
JSON Output
All commands support --output json (or BAND_OUTPUT=json env var) for structured output.
- Success: JSON object to stdout, exit code 0
- Error:
{"error": "message"}to stderr, exit code 1
Workflow
1. Resolve the loop target
Every cronjob belongs to one worktree (the repo's default-branch worktree or any other), so the prompt fires into the same chat over and over:
# Auto-detect the worktree ID from cwd
ws_id=$(band worktrees list --output json \
| jq -r --arg cwd "$PWD" '.worktrees[] | select(.path == $cwd) | .id' \
| head -1)
If the user is outside a worktree cwd, ask them which worktree to target (or run band worktrees list and pick one).
2. Parse the interval into a cron expression
Accept human durations (5m, 10m, 1h, 6h, 1d). Default is 10m. Map to a standard 5-field cron expression in the server's local timezone:
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.
- 13d ago Changed · -1 lines 2695c0eaddb9
- 25d ago Changed · +1 tokens per session f8c906a1cc2f
- 2mo ago First seen · 261 lines · 171 tokens per session scan A 0f9352253193
band-loop is a skill published in the GitHub repository band-app/band (5 stars, last pushed today), licensed MIT. It adds 172 tokens to every session and 3,191 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.