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 agentmods add skills/atomicbot-ai/atomic-agent/apple-calendarnpx skills add AtomicBot-ai/atomic-agent --skill apple-calendargit 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-calendar)<a href="https://agentmods.dev/skills/atomicbot-ai/atomic-agent/apple-calendar"><img src="https://agentmods.dev/badge/skills/atomicbot-ai/atomic-agent/apple-calendar.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 | $0.00045 | $0.01363 |
| Opus 5 | $0.00023 | $0.00681 |
| Sonnet 5 | $0.00009 | $0.00273 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
apple-calendar 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 5d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apple-calendar
Read Apple Calendar from the terminal via icalBuddy
(read-only) and create events through osascript AppleScript against Calendar.app.
Calendars sync across Apple devices through iCloud.
Setup check (lazy — do NOT probe every turn)
Do not run a --version probe before each request. Just run the
calendar command the user asked for (e.g. icalBuddy eventsToday) directly.
Only when a command fails map the error to a Setup playbook branch:
- stderr mentions
command not found: icalBuddy→ Setup playbook → "icalBuddy is not installed". - a read returns nothing and stderr mentions calendar access / not authorized → Setup playbook → "Calendar permission missing".
- macOS not detected (e.g.
unamereturnsLinux) → 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, OFFER concrete help and EXECUTE the fix yourself — do not dump install instructions on the user.
icalBuddy is not installed
Reply (solo reply step):
"The
icalBuddyutility is not installed. I can install it via Homebrew (brew install ical-buddy) — it needs your confirmation and takes ~20 seconds. Install it?"
On yes:
[{ "tool": "os.shell.run", "args": { "cmd": "brew", "args": ["install", "ical-buddy"] } }]
After install, retry the original command.
If brew itself is missing, do NOT bootstrap Homebrew automatically — reply:
"You don't have Homebrew installed. Install it manually from https://brew.sh/, then I'll continue."
Calendar permission missing
icalBuddy reads Calendar via EventKit; macOS guards this behind Privacy &
Security → Calendars. The agent cannot toggle that switch programmatically.
Open the panel to help the user:
[{ "tool": "os.shell.run", "args": { "cmd": "open", "args": ["x-apple.systempreferences:com.apple.preference.security?Privacy_Calendars"] } }]
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.
- 5d ago First seen · 126 lines · 45 tokens per session scan A 6d597985b499
apple-calendar is a skill published in the GitHub repository AtomicBot-ai/atomic-agent (2,466 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,363 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
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.
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
workspace-digest
Summarize the files saved in this assistant's shared workspace. Use when the user asks what is in their workspace, for a file inventory, or a digest of saved work.