Command Claude Code
Run a budget-aware exploration loop that externalizes every finding into the harness state files.
Command Claude Code
Run a budget-aware exploration loop that externalizes every finding into the harness state files.
Command Claude Code
Initialize externalized harness state (budget, candidates, curated set, evidence, verification, observations) for the active feature.
Command Claude Code
Synthesize curated evidence and verification records into the feature's research.md with a coverage table.
Command Claude Code
Render a compact, budget-aware slice of the harness state with a recommended next action.
Command Claude Code
Adversarially verify claims in spec/plan artifacts against primary sources and record verdicts.
Command Claude Code
All five commands are prompt files in commands/, registered in extension.yml. Each resolves HARNESSDIR the same way: config file → SPECKITHARNESS env vars → arguments; feature directory from the current git branch (e.g. branch 003-user-auth → specs/003-user-auth/), else the most recently modified directory under…
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: