Skill Claude CodeCodex
Part of spec-driven-tdd
Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
not rated 10 26d ago A 49 tokens
copy · 86% MIT
10Stars on the repository
19Mods indexed here, across every type
26d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Part of spec-driven-tdd
You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for…
not rated 10 26d ago A 38 tokens
copy · 94% MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
Core principle: Verify tests → Detect environment → Present options → Execute choice → Clean up.
not rated 10 26d ago A 39 tokens
copy · 97% MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
Code review requires technical evaluation, not emotional performance.
not rated 10 26d ago A 50 tokens
copy · 97% MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history.
not rated 10 26d ago A 34 tokens
copy · 98% MIT
simplify
06Skill Claude CodeCodex
Part of spec-driven-tdd
Use after tests pass and before code review - a portable quality pass that simplifies recently changed code while preserving behavior.
not rated 10 26d ago A 24 tokens
original MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
The spec-driven-tdd delivery workflow (orchestrator) - runs the full lifecycle for an OpenSpec change: OpenSpec planning/tracking + Superpowers TDD, simplify, and code review. Invoked by using-spec-driven-tdd; run it once implementation starts.
not rated 10 26d ago A 59 tokens
original MIT
spike
08Skill Claude CodeCodex
Part of spec-driven-tdd
Use before planning a risky change - a throwaway feasibility experiment that answers "is this even possible?" cheaply and ends in a VALIDATED / PARTIAL / INVALIDATED verdict.
not rated 10 26d ago A 37 tokens
original MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end.
not rated 10 26d ago C 29 tokens
copy · 88% MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
not rated 10 26d ago A 33 tokens
copy · 100% MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
Write the test first. Watch it fail. Write minimal code to pass.
not rated 10 26d ago A 29 tokens
copy · 100% MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
Ensure work happens in an isolated workspace. Prefer your platform's native worktree tools. Fall back to manual git worktrees only when no native tool is available.
not rated 10 26d ago A 48 tokens
copy · 98% MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
Entry point for the spec-driven-tdd workflow - invoke at the START of an OpenSpec change to load the delivery discipline and hand off to the spec-driven-tdd orchestrator before writing code.
not rated 10 26d ago A 44 tokens
original MIT
Skill Claude CodeCodex
Part of spec-driven-tdd
Core principle: Evidence before claims, always.
not rated 10 26d ago A 55 tokens
copy · 100% MIT
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: