forktreeUse the forktree Python CLI to safely create, list, remove, and garbage-collect git worktrees from a shell pipeline, CI job, or unattended coding agent. Wraps `git worktree` with safety pre-flights, TOML configuration, and a strict stdout/stderr contract.
Install via ClawdBot CLI:
clawdbot install bottanicals/forktreeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/BottaniCals/forktreeAudited Sep 29, 2026 · audit v1.0
Generated Sep 29, 2026
A CI pipeline creates ephemeral worktrees per test shard so parallel jobs never collide on the same checkout. Each job captures `forktree create` stdout into a variable, cds into the path, runs its shard, then relies on `gc` to reap stale worktrees by age. Strict exit codes let the pipeline distinguish preflight refusals from git failures without parsing logs.
An autonomous coding agent spins up a fresh worktree before each task so experimental edits never touch the user's main checkout. Because stdout is pure data, the agent captures the worktree path directly and routes diagnostics to a log file. If `create` exits non-zero, the agent reads stderr and abandons the task rather than retrying blindly.
A review bot materializes a worktree per pull request so multiple diffs can be built and tested concurrently on one machine. It uses `list --json` to enumerate active worktrees and `remove --force-if-lossless` to clean up after merges. The TOML config pins base paths and setup scripts for reproducibility.
Developers run `forktree init` once to generate `.forktree.toml`, then `create` a worktree per branch under test without disturbing the primary clone. `list --porcelain` feeds shell completions and status prompts, while `gc --dry-run` previews what would be cleaned before committing. This keeps laptops tidy across many concurrent branches.
A regulated build system uses forktree to carve out short-lived worktrees that are destroyed automatically by the setup hook's teardown-on-failure behavior. Every `create` refusal is logged with the exact `forktree: <subcommand>: <reason>` stderr line for audit trails. Garbage collection ensures no stale source trees persist past their policy window.
The forktree CLI remains free and stdlib-only while a paid control plane manages worktree lifecycles across fleets of agents and CI runners. The hosted layer adds dashboards, audit logs, and policy enforcement for `gc` and setup hooks. Teams adopt the OSS CLI bottom-up, then upgrade when coordination becomes painful.
forktree is packaged inside an agent runtime sold to AI coding startups that need safe, isolated git checkouts out of the box. Licensing is per-organization, with the CLI acting as the wedge into broader sandboxing and environment-management products. The strict stdout/stderr contract makes it trivially embeddable in any pipeline.
Enterprises with sprawling monorepos pay for engagements that wire forktree into Jenkins, GitHub Actions, or internal build systems with custom TOML configs and setup scripts. Deliverables include hardened gc policies, strict-mode configs, and runbooks for exit-code handling. Recurring retainers cover ongoing tuning as repos grow.
💬 Integration Tip
Always capture `forktree create` stdout into a variable and branch on the exit code before cds, since a non-zero exit means the worktree was never created and the variable is empty. Run `forktree doctor` first to confirm wiring, and prefer `gc --dry-run` before any cleanup pass.
Scored Sep 29, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.