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 imagemagickgit 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/imagemagick)<a href="https://agentmods.dev/skills/atomicbot-ai/atomic-agent/imagemagick"><img src="https://agentmods.dev/badge/skills/atomicbot-ai/atomic-agent/imagemagick/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/imagemagick"><img src="https://agentmods.dev/badge/skills/atomicbot-ai/atomic-agent/imagemagick.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 | $0.00041 | $0.00916 |
| Opus 5.5 | $0.00016 | $0.00366 |
| Sonnet 5.5 | $0.00008 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
imagemagick 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 2mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
imagemagick
Transform still images with ImageMagick v7
(magick command). Pairs well with vision.describe — describe an image to
decide what to do, then operate on it here. Always write to a new output file.
ImageMagick v7 uses
magick in.png out.jpg. Legacy v6 usesconvert; if onlyconvertexists, substitute it formagickin the examples below.
Setup health check (run first, every session)
Verify with one solo step:
[{ "tool": "os.shell.run", "args": { "cmd": "magick", "args": ["--version"] } }]
Outcome map:
exit 0+Version: ImageMagick 7…→ ready, proceed.command not found: magick→ tryconvert --version(v6); if also missing → enter Setup playbook → "imagemagick missing".
Setup playbook (when prerequisites are missing)
imagemagick missing
Reply (solo reply step):
"ImageMagick is not installed. I can install it:
brew install imagemagick. Install it?"
On yes:
[{ "tool": "os.shell.run", "args": { "cmd": "brew", "args": ["install", "imagemagick"] } }]
On Linux: apt-get install imagemagick.
When to use
- "Resize / crop / rotate this image", "convert PNG to JPG / WebP".
- "Compress this image", "make a thumbnail", "combine images into a montage".
- "Add a text caption / watermark to this image".
When NOT to use
- Understanding image content — use
vision.describeinstead. - Video frames / animation encoding — use the
ffmpegskill. - Multi-page PDF assembly from images — use the
pdfskill (magickcan make a PDF but page-level control lives inpdf).
Common operations
All examples invoke os.shell.run with cmd: "magick". The approval gate
surfaces each write.
| Goal | args |
|---|---|
| Inspect dimensions/format | ["identify", "in.png"] |
| Convert PNG → JPG | ["in.png", "out.jpg"] |
| Convert → WebP | ["in.png", "-quality", "82", "out.webp"] |
| Resize to 800px wide | ["in.jpg", "-resize", "800x", "out.jpg"] |
| Thumbnail (fit 200x200) | ["in.jpg", "-thumbnail", "200x200", "thumb.jpg"] |
| Crop 300x300 from 10,10 | ["in.png", "-crop", "300x300+10+10", "+repage", "crop.png"] |
| Rotate 90° | ["in.jpg", "-rotate", "90", "rot.jpg"] |
| Compress JPG quality 75 | ["in.jpg", "-quality", "75", "small.jpg"] |
| Montage 2x2 grid | ["montage", "a.png", "b.png", "c.png", "d.png", "-tile", "2x2", "-geometry", "+4+4", "grid.png"] |
| Add caption | ["in.jpg", "-pointsize", "36", "-annotate", "+20+40", "Hello", "out.jpg"] |
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.
- 2mo ago First seen · 87 lines · 41 tokens per session scan A 28f261640e32
imagemagick is a skill published in the GitHub repository AtomicBot-ai/atomic-agent (3,481 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 916 once invoked, about $0.0002 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
harness-init-runner
Initialize a lightweight repo-local Node.js harness (harness/ + .harness/) WITHOUT AIOS dependency. Use ONLY when you need a standalone, portable harness. If AIOS is installed, use aios-harness instead — it has rex Command hosting, ContextDB integration, and checkpoint recovery.
manage-llm-server
Inspect and control the local LLM server(s) via llama-launcher — list profiles, see what's running, switch models, tail logs. Use when the user wants to know what model is loaded, change models, start/stop or restart the server, or troubleshoot a stuck load.
release-llama-launcher
Cuts a llama-launcher release: checks the release gate with go run ./cmd/release status, drafts the notes with release-notes-llama-launcher, proposes the version and has the owner confirm it, makes the two local release commits with prepare, then — after a dry run and one explicit confirmation — runs publish, which…
release-notes-llama-launcher
Builds an evidence-backed inventory of every change since llama-launcher's last published GitHub release — three blind scouts (changelog, commits, user surfaces), a merge, verification of only the contested rows — and renders plain-language release notes from it, trace-checked both ways. Read-only: it describes and…
browse
Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase…
opencli-usage
Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.