Atomic Agent is a local-first AI agent that runs its control loop and state on a user's machine while using local or cloud models. It drives browsers, edits files, runs approved commands, remembers context, schedules follow-ups, and connects to external tools, with the catalogue providing skills for its use.
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 AtomicBot-ai/atomic-agent --skill apple-remindersgit clone --depth 1 https://github.com/AtomicBot-ai/atomic-agentWrote 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/atomicbot-ai/atomic-agent/apple-reminders)<a href="https://agentmods.dev/skills/atomicbot-ai/atomic-agent/apple-reminders"><img src="https://agentmods.dev/badge/skills/atomicbot-ai/atomic-agent/apple-reminders/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/atomicbot-ai/atomic-agent/apple-reminders"><img src="https://agentmods.dev/badge/skills/atomicbot-ai/atomic-agent/apple-reminders.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.01419 |
| Opus 5.5 | $0.00012 | $0.00568 |
| Sonnet 5.5 | $0.00006 | $0.00284 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
apple-reminders 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apple-reminders
Drive Apple Reminders from the terminal via remindctl. Reminders sync across Apple devices through iCloud.
Setup check (lazy — do NOT probe every turn)
Do not run a remindctl status probe before each request. Just run the
remindctl command the user asked for directly. Only when a command
fails map the error to a Setup playbook branch:
- stderr contains
command not found: remindctl→ Setup playbook → "remindctl is not installed". - output says permission
denied/not determined/restricted→ Setup playbook → "Reminders permission missing". - macOS not detected → reply that this skill is macOS-only and stop. Do NOT try to install anything.
If unsure which branch applies, capture stderr and ask the user before proceeding.
Setup playbook (when prerequisites are missing)
When a check fails, the agent's job is to OFFER concrete help and EXECUTE the fix itself — not to dump install instructions on the user. Use this dialogue shape:
- State plainly what is missing (one short reply).
- Offer the most direct remediation the agent can perform via tools.
- Wait for the user's yes/no reply.
- On yes, execute the fix (the runtime approval gate will surface the command for confirmation).
- Retry the original request; only then proceed.
remindctl is not installed
Reply (solo reply step):
"The
remindctlutility is not installed. I can install it via Homebrew (brew install steipete/tap/remindctl) — it needs your confirmation and takes about 20 seconds. Install it?"
On yes:
[{ "tool": "os.shell.run", "args": { "cmd": "brew", "args": ["install", "steipete/tap/remindctl"] } }]
After install, retry the original command.
If brew itself is missing, do NOT attempt to bootstrap Homebrew — reply: "You don't have Homebrew installed. Install it manually from https://brew.sh/, then I'll continue."
Reminders permission missing
Unlike Notes Automation, remindctl has its own CLI command to request the permission — the agent CAN do it directly. Offer + execute:
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 · 143 lines · 31 tokens per session scan A abf5915ad96f
apple-reminders is a skill published in the GitHub repository AtomicBot-ai/atomic-agent (3,394 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 1,419 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
amq-spec
Use two agents to research a design independently and converge on one specification through AMQ. Trigger for collaborative design or messages labeled workflow:spec; use amq-cli for ordinary coordination.
scheduling
Scheduling across time zones: confirm times in the attendee's own zone, use IANA zone names, mind DST edges, buffers and calendar etiquette. Use when booking meetings or calls with people in other zones.
agent-desktop
Use the built-in Computer sub-agent with agent-desktop for macOS desktop automation. Apply when a task needs application launching, accessibility snapshots, stable element refs, window focusing, semantic clicks/typing, or visual confirmation outside the browser sandbox.
neosh
Run and manage long-lived coding agents in a neosh workspace from the command line — start conversations in any directory or git worktree, fan work out across many at once, watch and steer them while they run, read what they produced, and clean up. Use whenever the user asks to delegate work to neosh, run something…