computer_use_guide

Guidance for controlling computer applications through browser and native-computer interactions in a local-first AI assistant.

In plain words
What is it for?
It helps capture applications, type or replace text, interact with managed web pages or native apps, handle stale targets, and check the resulting state.
Why use it?
It helps keep actions tied to the correct window or control and verifies whether each requested change actually happened.

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/siddsachar/row-bot/computer_use_guide
Any agent
npx skills add siddsachar/row-bot --skill computer_use_guide
Clone the repo
git clone --depth 1 https://github.com/siddsachar/row-bot

Made for: Claude Code, Codex.

Per session 4 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 $0.00004 $0.00490
Opus 5 $0.00002 $0.00245
Sonnet 5 $0.00001 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 3d ago against content hash 6f95afecb10c, 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_guide 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 3d 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.

tool_guides/computer_use_guide/SKILL.md · 18 lines

What it actually says

COMPUTER USE WORKFLOW

  • Prefer Browser for managed pages and Computer Use for native targets; never switch silently. Issue one Computer Use call at a time. Use one app-scoped capture with an exact current list_apps name, never parallel app/window discovery.
  • target_id and tokens live in the current Computer Use generation. A new user turn starts with discovery or app-scoped capture. Say gone or its lease expired only after a previously returned opaque target produces target_gone.
  • Do not repeat after app_not_running, window_not_found, protected refusal, or non-retryable native capture. Exact-filter ambiguity permits a returned current token without another capture only for the present observation/lease.
  • On stale refusal, capture the exact same target once and retry the same exact action once. If stale repeats, Stop or request Take over. Do not switch action family or delivery engine.
  • Token-bound type rejects disabled, read-only, secure, protected, or structural targets. Tokenless type is literal text insertion; use replace_text for a complete value.
  • Separate action dispatched, native state change, and exact postcondition. Read driver_verdict, degraded, escalation_recommendation, verdict, and next_step literally: done, verify_fresh_state, escalate, or take_over applies only to this action receipt.
  • Start with delivery_mode=auto. Use explicit delivery_mode=foreground only for click, double-click, right-click, type, key, or scroll after fresh exact-target evidence and a prior structured recommendation/refusal. Pre-dispatch background_unavailable or foreground_required permits one same-action foreground rung; a second refusal requires Take over. Never focus first or assume focus persists.
  • Text insertion, accepted or uncertain mutations, timeouts, disconnects, and ended sessions must not be replayed. Never replay them. After one fresh unchanged suspected_noop, a reversible click permits one alternative exact route: recommended foreground, or px from a new screenshot-grounded exact-target capture. page is observable but unsupported; never use SOM, blind coordinates, Browser/CDP/Page, shell, clipboard, or app-specific fallbacks.
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. 3d ago First seen · 18 lines · 4 tokens per session scan A 6f95afecb10c

Subscribe to this mod's changes

computer_use_guide is a skill published in the GitHub repository siddsachar/row-bot (1,479 stars, last pushed 5d ago), licensed Apache-2.0. It adds 4 tokens to every session and 490 once invoked, about $0.0000 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.

Related

Other skills, from other repositories

agent-browser

Браузерная автоматизация для интерактивных веб-задач. Используй, когда нужно открыть сайт, заполнить форму, кликнуть, сделать скриншот, залогиниться, спарсить JS-страницу или протестировать веб-приложение. Триггеры — «зайди на сайт», «заполни форму», «нажми кнопку», «скриншот страницы», «войди в аккаунт», «спарси…

smixs/iva-agent · 114 tokens

test-ui

Test the Wayfinder agent extension UI by starting the dev environment and visually verifying changes via CDP. Covers the new tab page (left sidebar — Home, Scheduled Tasks, Settings, etc.) and the right side panel (chat interface). Use after making UI changes to apps/agent/.

rahulcvwebsitehosting/wayfinder · 60 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

MRWillisT/PullNexus · 35 tokens

add-tavily-tool

Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.

nanocoai/nanoclaw · 41 tokens

agent-browser

Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful, not just when the user explicitly asks.

nanocoai/nanoclaw · 51 tokens

playwright-pom-discovery

Use when building or extending a Page Object Model (POM) for the Opik E2E suite (under testsendtoend/e2e/pom/) and you need to choose stable selectors against the live UI. Walks through seeding required state, exploring the running page with the Playwright MCP (accessibility snapshot + data-testid enumeration)…

comet-ml/opik · 112 tokens