Use when implementing any feature or bugfix where tests can be written first — write the test, see it fail, make it pass, refactor
1
AI 94
systematic-debugging
thesyntaxninja3/4/2026
Use when encountering any bug, test failure, unexpected behavior, or error message — before proposing any fix
1
AI 93
story-decomposition
thesyntaxninja3/4/2026
Use when a large task needs to be broken into independent, verifiable stories with pass/fail acceptance criteria
1
AI 93
writing-plans
thesyntaxninja3/4/2026
Use when a task requires multiple steps and benefits from a structured plan before implementation begins
1
AI 92
executing-plans
thesyntaxninja3/4/2026
Use when an approved plan exists and implementation should begin — executes steps sequentially with verification checkpoints
1
AI 91
finishing-a-development-branch
thesyntaxninja3/4/2026
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — merge, PR, or cleanup
1
AI 88
dispatching-parallel-agents
thesyntaxninja3/4/2026
Use when facing 2+ independent tasks that can be researched or implemented by agents without shared state or sequential dependencies
1
AI 88
verification-before-completion
thesyntaxninja3/4/2026
Use when about to claim work is complete, fixed, or passing — requires running verification commands and confirming output before making any success claims
1
AI 85
requesting-code-review
thesyntaxninja3/4/2026
Use when implementation is complete and a comprehensive code review is needed — dispatches parallel review agents and merges findings
1
AI 72
using-git-worktrees
thesyntaxninja3/4/2026
Use when starting feature work that needs isolation from the current workspace or before executing plans that could leave the branch in a broken state
1
AI 65
subagent-driven-development
thesyntaxninja3/4/2026
Use when executing an implementation plan with independent tasks that can be delegated to subagents within the current session
1
self-review
thesyntaxninja3/4/2026
Use when implementation is complete and verification has passed — dispatches the sensei agent for fresh-context quality review
