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/esaruoho/apple/overlaygit clone --depth 1 https://github.com/esaruoho/appleWhat 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 | $0.00106 | $0.00498 |
| Opus 5 | $0.00053 | $0.00249 |
| Sonnet 5 | $0.00021 | $0.00100 |
| Haiku 4.5 | $0.00011 | $0.00050 |
Grade A, and why
overlay 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 2d 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
Run the apple-skill overlay helper on $ARGUMENTS.
Use Bash to execute (one call, then stop):
/Users/esaruoho/work/apple/bin/overlay $ARGUMENTS
Modes:
/overlay— status: running? how many marks, by which actor?/overlay open— launch Overlay.app (menu-bar only; ⌃⌥⌘D draws, esc leaves)/overlay kinds— the object vocabulary an agent can post/overlay post box --rel 0.1,0.2,0.3,0.1 --actor agent:fm --ttl ephemeral/overlay post callout --rel 0.5,0.5,0.1,0.1 --text "this is the stuck process"/overlay post spotlight --rel 0.3,0.3,0.4,0.3— dim everything else/overlay post --stdin— read one object, or an array, as JSON/overlay clear --actor agent:fm— remove one agent's marks, leave the human's ink/overlay dump --json— the marks currently mirrored to disk
--rel is 0…1 of the screen (preferred: an agent needs to know nothing about pixel
sizes); --rect X,Y,W,H and --at X,Y take absolute AppKit coordinates, origin
bottom-left. Posted objects default to ttl: session so an agent cannot litter the
desktop permanently.
Posting never enters draw mode — the overlay stays click-through while marks are up.
After the command completes, report only the lines it printed. Do not summarize.
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.
- 2d ago First seen · 34 lines · 0 tokens per session scan A 3b276d0a4329
overlay is a command published in the GitHub repository esaruoho/apple (11 stars, last pushed 5d ago), licensed MIT. It adds 106 tokens to every session and 498 once invoked, about $0.0005 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 commands, from other repositories
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
buildable-design
Create a UI/UX design brief from a prompt or the current Buildable app spec.
ui-wizard
Launch the Dev-Suite Configurator dashboard for the current project.
mockup-analyze
Extract design specifications from HTML mockups using AI vision.