メニュー
Agent-browser is an LLM-driven browser-automation framework (DOM querying, form filling, navigation) that complements lightpanda-headless-browser for heavier semantic interactions.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when: applying Matt Pocock engineering skills for diagnosis, TDD, architecture improvement, issue breakdown, PRD creation, or rigorous TypeScript/codebase analysis.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
Use when: working with OpenAI Codex plugins, plugin marketplaces, plugin manifests, plugin-bundled skills, or the openai/plugins repository. Helps inspect .codex-plugin/plugin.json, .agents/plugins/marketplace.json, and installed Codex plugin cache.
| name | agent-browser |
| description | Agent-browser is an LLM-driven browser-automation framework (DOM querying, form filling, navigation) that complements lightpanda-headless-browser for heavier semantic interactions. |
| source | https://github.com/browser-use/browser-use |
| integration | external-browser |
| status | descriptor-only |
Descriptor-only registration (P12 batch). Companion to the existing lightpanda-headless-browser skill.
| Concern | Tool | Scope |
|---|---|---|
| Liveness / "is the page alive" | lightpanda-headless-browser | ultra-fast Zig/Rust binary, no JS eval heavy-lifting |
| Semantic navigation | agent-browser | LLM drives click/type/select with accessibility-tree awareness |
| Hard assertions | playwright-webui-qa (existing) | deterministic end-to-end verification |
OctoCode's webui-e2e CI job (added in P9) already uses Playwright; agent-browser is a candidate for exploratory flows where the tests are not pre-scripted but discovered by the agent.
agent_browser_visit(url, goal) as a high-risk tool behind RuntimeConfig.integrations.agent_browser.enabled.skills-install (see crates/octocode-cli/src/skills_install.rs), plus a page-size cap.WorkspaceToolExecutor (same path-traversal guardrails as file-writes).password, card, ssn — reject at tool level.event_feed_json entry for operator audit.lightpanda-headless-browser first as a liveness gate before spinning up an LLM-driven session, per verification instructions the workspace already follows (WebUI verification step).