OpenParable
Skip to content
← Back to skills

Turboplan

Productivity
turboplan

Turboplan is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Analyze task complexity and route to a mode by artifact: direct fix for clear-scope changes, plan file when the approach needs to be written down, or spec and shells for multi-session projects. Use when the user asks to "turboplan", "run turboplan", "plan this task", "turbo plan mode", "plan and implement", or "use turboplan instead of plan mode".

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/planning/turboplan-tobihagemann-turbo-2/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/turboplan, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Turboplan

Analyze task complexity and route to an execution mode.

Categorize the user-supplied task along these dimensions using subjective judgment:

  • Scope: single feature / single subsystem vs multi-feature / multi-subsystem
  • Stakes: one-off change vs long-lived project with architectural implications
  • Unknowns: clear approach vs needs exploration and product decisions

Route to one of three modes (or disambiguate when borderline).

Modes are named by what they produce: no plan, a plan file, or a spec plus shells.

ModeCriteriaRoute
DirectClear scope and a known approach, ready to implement. Goes straight to $implement.Read references/direct-mode.md and follow its steps.
PlanThe approach warrants writing down before implementing — to survey patterns, align with the user, or survive a fresh session. Fits a single implementation session and touches one or two related subsystems. Produces a plan file.Read references/plan-mode.md and follow its steps.
SpecSpans multiple subsystems, requires multiple implementation sessions, or has architectural decisions that need a spec-level discussion before planning begins. Produces a spec plus shells.Read references/spec-mode.md and follow its steps.
BorderlineFalls between two modes.Use request_user_input to confirm the route, then proceed as above.

State the chosen route before continuing with the reference file.

Rules

  • Diff size, perceived task simplicity, and context window concerns are not reasons to skip the chosen mode's phases.