Bootstrap Harness
Create a complete AI-agent harness (CLAUDE.md + supporting docs system) for any project. Portable across Python/Java/TS/Go. Based on 2025-2026 best practices (AGENTS.md spec, GitHub's 2,500-repo study, ACE paper, context-engineering research). Use when a repo has no harness, was just cloned/scaffolded, or its docs are bloated/stale and need a structured rebuild.
Promote Lesson
Find lessons in docs/lessons.md that have been referenced ≥2 times, then promote them into CLAUDE.md boundary rules via a single delta edit. Implements the ACE paper's structured-bullet + delta-edit pattern, so your harness evolves without full rewrites. The mechanism that makes the harness self-improving.
Review Harness
Audit a project's harness (CLAUDE.md + supporting docs) against current code and git activity, and catch lifecycle/hygiene drift (completed work stuck in active/, rendered byproducts piling up, prose docs gone stale, broken links). Produces a markdown report only — never edits files. Use after a milestone, after a major change, on a periodic cadence, or when the user runs /review-harness. Works i…
Finish Phase
Graduate a completed exec-plan from active/ to completed/, synthesize an outcome section (results / pitfalls / remaining), and update the index. Daily harness hygiene — keeps the project's "where are we now" pointer accurate so new agent sessions don't waste context rebuilding state.