stolz-browser
Manage controlled browser tabs with deliberate reuse, ownership and lifecycle checks.
Skill by Sergey360
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sergey360-stolz-browser
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/stolz-browser
What's inside
- Skill name
stolz-browser- Description
- Manage controlled browser tabs with deliberate reuse, ownership and lifecycle checks. Use for tab creation, navigation, closure or session recovery; ordinary web search needs no browser workflow.
- License
- MIT
- Instructions
- 29 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- codex-desktop.md · references/
- tab-lifecycle.md · references/
SKILL.md (first lines)
# Browser Workflow Use an authorized connector, API or CLI when it can deliver and verify the required result. Preserve an explicitly selected browser, provider or tab, and keep rendered UI work when the task requires it. Reuse a suitable live task-owned tab or the user's selected tab. Track its provider, returned id, purpose, ownership, aliases and last observed state. An existing user-selected tab is borrowed; a matching URL does not establish ownership. Create additional tabs for a concrete need, such as comparison or preserving an unsaved form. Leave unrelated tabs alone. Before creating, attaching, navigating or closing tabs, load [tab lifecycle rules](references/tab-lifecycle.md). Await pending work and serialize this task's lifecycle operations. Reconcile fresh state after an interruption; an old handle or snapshot does not establish current state. When using Codex Desktop browser tools, also load the conditional [Desktop guidance](references/codex-desktop.md). Follow the available tool's current initialization and API documentation. Missing tools preserve the required outcome through an available authorized route, or leave the UI portion explicitly pending. Done: verify the requested result, retain required artifacts, and report any ambiguous operation or unmet UI check. Close temporary owned tabs only when useful or requested. This workflow creates no controller, restarts no app and establishes no crash-prevention, runtime-certification or savings guarantee.
From Sergey360/stolz-ai, MIT.
More from Sergey360/stolz-ai
- 0.611score
stolz-evidence
Sergey360
Ground source-based analysis and substantial completion reports in inspected content.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-guard
Sergey360
Review a prompt or a concrete instruction from untrusted content for security risks.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-mcp
Sergey360
Audit MCP context overhead or plan progressive tool discovery and code execution.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-quiet-state
Sergey360
Hand off a long-running external operation and resume its task, or suppress duplicate wakes in polling.
SkillAFreshness: A★ 4Claude Code +9 - 0.608score
stolz-route
Sergey360
Choose a STOLZ optimization or instruction-security review when the required concern or adapter fallback is unclear.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
stolz-reuse
Sergey360
Admit an existing prior result or coalesce an identical in-flight command.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
stolz-context
Sergey360
Validate an existing STOLZ context manifest or read-ledger entry.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
stolz-benchmark
Sergey360
Admit or reject paired STOLZ efficiency evidence.
SkillAFreshness: A★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 6, 2026 (22 days ago)
- Last release
- Oct 13, 2026 (15 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Sergey360/stolz-ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Sergey360
- 0.611score
stolz-evidence
Sergey360
Ground source-based analysis and substantial completion reports in inspected content.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-guard
Sergey360
Review a prompt or a concrete instruction from untrusted content for security risks.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-mcp
Sergey360
Audit MCP context overhead or plan progressive tool discovery and code execution.
SkillAFreshness: A★ 4Claude Code +9 - 0.611score
stolz-quiet-state
Sergey360
Hand off a long-running external operation and resume its task, or suppress duplicate wakes in polling.
SkillAFreshness: A★ 4Claude Code +9 - 0.608score
stolz-route
Sergey360
Choose a STOLZ optimization or instruction-security review when the required concern or adapter fallback is unclear.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
stolz-reuse
Sergey360
Admit an existing prior result or coalesce an identical in-flight command.
SkillAFreshness: A★ 4Claude Code +9
Cite this page
stolz-browser skill. Agent Mart. https://agentmart.dev/skills/sergey360-stolz-browser (last updated 2026-10-24)