Superplan is a CLI-first execution system that forces AI agents into step-by-step task workflows instead of drift-prone chat-based work.
Skill Claude Code
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to…
Skill Claude CodeCodex
Use when routed repo work still has meaningful ambiguity about behavior, constraints, taste, or acceptance intent, and that ambiguity would make planning or execution unsafe.
Skill Claude CodeCodex
Use when brownfield or long-running repo work lacks durable context about architecture, conventions, or recurring gotchas that future tasks will need again.
Skill Claude CodeCodex
Use when tracked work hits a failing check, flaky result, runtime bug, or unexplained behavior and you need root cause before changing code.
Skill Claude CodeCodex
Use when code, commands, install flow, help text, or user-visible behavior changed and docs or durable context may now be inaccurate.
Skill Claude CodeCodex
Use when a new request might involve repo work, tracked changes, workspace-specific decisions, or durable coordination and you must decide whether Superplan should engage before exploring or implementing.
Skill Claude CodeCodex
Use when tracked work is already shaped and the next move is to execute, verify, block, or request feedback without replanning from scratch.
Skill Claude CodeCodex
Use when a fix or behavior change needs the smallest durable test, check, or proof so the contract will fail loudly if it regresses.
Skill Claude CodeCodex
Use when work is pausing, switching owners, or at risk of context loss and the next agent will need a concise restart point with the current truth.
Skill Claude CodeCodex
Use when the target is understood but the work still needs an execution path, task breakdown, or proof strategy before implementation begins.
Skill Claude CodeCodex
Use when completed or failed work exposed a reusable lesson, recurring trap, or process weakness worth capturing for future tasks.
Skill Claude CodeCodex
Use when someone asks whether the current product slice is ready to ship, publish, or recommend and the answer depends on a disciplined release-quality check.
Skill Claude CodeCodex
Use when a tracked task appears done and you need to decide whether its acceptance criteria are truly satisfied by fresh evidence.
Skill Claude CodeCodex
Use when Superplan may engage and you need to decide whether to stay lightweight, create one tracked task, gather context first, or shape deeper structure before execution begins.
Skill Claude CodeCodex
Use when Superplan has decided to engage and the work still needs plans, specs, proof paths, or multiple tracked tasks shaped before bounded execution can start.
Skill Claude CodeCodex
Use when a feature, bugfix, or behavior change has a testable contract and implementation is about to begin.
Skill Claude CodeCodex
Use when you are about to say work is complete, fixed, passing, or ready and need fresh proof from the real workspace harness first.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: