AI Agent Workflow Collection

Regenerate the Better Auth Convex schema from the auth config with the Better Auth CLI. Read before changing the auth data model — editing plugins/fields in convex/auth.ts or convex/betterAuth/, bumping the better-auth version, or when a Convex push / tsc fails on a missing or renamed auth table (generatedschema.ts has drifted).

Use to verify a feature/story meets all Definition of Done criteria before marking complete.

Documentation check checkpoint for conductor gates. Analyzes code changes to determine if documentation needs updating. Returns structured result with pass/fail status and documentation suggestions.

How to approach a coding task like a senior engineer — classify it (fix / refactor / feature / review / explore / migrate), map blast radius before editing, and self-review both your plan and your diff. Read at the START of any non-trivial task, before you touch code, and whenever you're tempted to make a large or radical change. The biggest quality lever in this repo is deciding well, not typing fast.

Use when you change existing code WITHOUT changing its behaviour — refactor, optimize, simplify, deduplicate, rename, restructure, extract, or pay down tech debt. It keeps you green while you move and locks behaviour with tests first. Load it the moment a task says "clean up", "refactor", "simplify", "make faster", "extract", "consolidate", or "merge", or whenever you're tempted to rewrite working code. Never refactor without it. If the change adds behaviour use implement-feature; if it fixes a defect use fix-bug.

Use when you need to know where something lives in a codebase or what else a change touches — before any code change, when you're new to a repo, when a request names one screen and parallel ones may exist, or when a visible label or error must be traced to code. It owns three jobs: ORIENT (build the mental map from the repo layout and its enforced tooling — the configs are the conventions), FIND (trace a concept from user-visible vocabulary to i18n keys to symbol names to usages — what a thing is called and what it calls), and SWEEP (after changing one site, enumerate every other occurrence of the concept and change or rule out each — the request names one site; the task is the concept). Load it at Gate A of implement-feature, make-improvement, fix-bug, or implement-ui. Never change one copy of a duplicated concept without sweeping the rest. For facts outside the repo use deep-research.

Use when you test a change or prove it works — write tests that exercise real behaviour (happy path + one edge + one error), run them and watch red→green, drive the real app for anything user-visible, and codify the check so it can't silently break. Load it before writing or changing any test, adding an end-to-end spec, deciding what to cover, or whenever asked to "verify", "test", or "confirm it works". Never claim a change is done on a green typecheck alone — observe the real outcome.

Run this as the FINAL review step once you have finished a UI change you can load in a browser — it is the visual-regression gate, run once at the end (not after every edit), and the change is not done until it reports score: 100. It drives a real browser over the page, auto-detects its relevant elements (no selectors), labels each by ARIA role + accessible name, and reports which changed the rendered frame, what each is anchored to (screen/page/ancestor), and what transition defects (layout-shift, flicker, jank, dithering) occurred, with a 0–100 score. Run bun src/analyze-cli.ts for a lean JSON report (--full for the faithful record). Also read before resolving what an element is anchored to, or editing the instrument, analysis, or element auto-detection in this directory.

Use when you edit any non-English file under services//messages/ (e.g. de.json, fr.json), packages/ui/src/i18n/messages/, or any page under docs/ /, add a locale, or touch a glossary term — Tale ships as one narrator written natively per language, never a word-for-word render of the English. Load it before touching any non-English string; never translate by rendering the source words. Per-locale voice doctrine lives in locales/ /AGENTS.md; the loanword buckets in BUCKETS.md, the conventions template in CONVENTIONS.md, the glossary workflow in GLOSSARYGUIDE.md.