agentic-engineering-patterns

Run the compound engineering step — a short retrospective after a piece of work that folds what was learned back into CLAUDE.md, the skills, or the hoard. Use at the end of every significant task.

Sort out git messes and perform history surgery — undo/rewrite commits, resolve conflicted merges and rebases, recover lost code via reflog, find regressions with git bisect.

Save a newly-figured-out trick as a minimal working example in hoard/, so future sessions can reuse or recombine it. Use after solving something non-obvious for the first time.

Build a self-contained interactive or animated HTML page that explains how an algorithm or piece of code works. Use to pay down cognitive debt when a written explanation isn't enough.

Manually exercise code beyond the automated tests — python -c for libraries, curl for APIs, browser automation with screenshots for web UIs — and document the results. Use after tests pass, before declaring work done.

Pre-pull-request checklist — verify the code works, the diff is reviewable, and the PR carries context and evidence of testing. Run before opening any pull request.

Proofread a document before publication — spelling, grammar, repetition, logical and factual errors, weak arguments, placeholder links. Reports issues; never rewrites the author's voice.

Implement a feature or bug fix using red/green test-driven development — write failing tests first, confirm they fail, then implement until green. Use for any new behavior or bug fix.

Build a linear walkthrough document explaining how a codebase or subsystem works, using Showboat with real command output for every code snippet. Use to get up to speed on unfamiliar or vibe-coded code.