computer-use

Instructions for controlling one explicitly allowed macOS application through computer-use tools. It uses the app's accessibility information, which describes visible controls and their positions.

In plain words
What is it for?
Use it to inspect an allowed app, click controls, enter text, press keys, and scroll through its interface.
Why use it?
It reduces accidental actions by requiring a fresh observation after every interaction and confirmation before sending, deleting, purchasing, publishing, or changing permissions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/echovic/blade-computer-use/computer-use
Any agent
npx skills add echoVic/blade-computer-use --skill computer-use
Clone the repo
git clone --depth 1 https://github.com/echoVic/blade-computer-use

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00490
Opus 5 $0.00015 $0.00245
Sonnet 5 $0.00006 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured yesterday against content hash 5824413de1f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

computer-use 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 yesterday.

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.

skills/computer-use/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Computer Use

Operate one allowed macOS app at a time. Treat every observation revision as a single-use capability for exactly one action.

Workflow

  1. Call list_apps and identify the target bundle identifier.
  2. Call observe for that app. Use element_index when a suitable AX node exists; use window-relative coordinates only as a fallback.
  3. Confirm immediately before impactful actions such as sending, submitting, purchasing, deleting, publishing, or changing permissions.
  4. Perform one click, type_text, press_key, or scroll with the revision returned by that observation.
  5. Observe after every action. Never reuse a revision or assume the interface remained unchanged.

If an action reports a stale or consumed revision, observe again and reassess the current interface. Do not replay the old action blindly.

Tools

Tool Purpose
list_apps List running GUI apps and bundle identifiers.
observe Return the current AX tree, revision, and optional screenshot.
click Click an AX element or window-relative coordinate.
type_text Type Unicode text into the focused non-secure field.
press_key Press a supported key with optional modifiers.
scroll Scroll at an element, coordinate, or window center.

Safety

  • Stay within the app the user named and the configured CUA_ALLOWED_APPS policy.
  • Explain when Accessibility or Screen Recording permission is missing; do not weaken the policy to bypass it.
  • Never target loginwindow, SecurityAgent, password fields, or other secure input surfaces.
  • Pause when the visible state differs from the user's request or when physical user input changes the target.
  • Prefer a purpose-built API or CLI when it can complete the task with less UI access.

Common Mistakes

  • Reusing a revision: observe again before retrying.
  • Guessing screen coordinates from an old screenshot: use the current AX element index first.
  • Chaining several actions from one observation: one observation permits one action only.
  • Treating a successful input event as task completion: verify the resulting state with observe.

Read the full file on GitHub · 45 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. yesterday First seen · 45 lines · 30 tokens per session scan A 5824413de1f2

Subscribe to this mod's changes

computer-use is a skill published in the GitHub repository echoVic/blade-computer-use (0 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 490 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens