AI dev infrastructure framework for Claude Code. /dotclaude:bootstrap authors CLAUDE.md + docs/ + .claude/ tuned to your project. Per-domain: design (showpiece), coding, planning, testing, data, ai-workflow.
Agent
Database integrity auditor — queries the persistent store for incomplete enrichment, orphaned references, stuck state-machine rows, cross-tenant leaks, and invariant violations. Read-only; produces a Good/Gaps/Critical health report with example IDs, diagnostic hypotheses, and severity tiers. Run after pipeline…
Agent
Post-implementation review — blast-radius, parallel-path drift, trust-boundary no-ops, and consistency gaps that per-file linters miss. Read-only; produces an S/A/B/C/D/F graded report. Run after a multi-file or boundary-crossing change, before committing. NOT a style checker.
Agent
Pre-implementation validation — maps integration points, parallel paths, and cross-boundary risks BEFORE any code is written. Read-only; produces a Clear-for-Takeoff / Caution / Abort verdict with a risk matrix and an implementation plan. Run before starting a non-trivial or boundary-crossing change. NOT a code…
Agent
Product-vision guardian — audits work against the project's stated direction, detects drift (feature creep / architecture / priority), asks A/B/C clarifying questions, keeps vision docs current, and recommends which other agents to run. NOT a code reviewer; a direction validator. Run at the start of major features…
Agent
Meta-audit that detects drift between documentation and code — verifies every file-path / function / type / table / constant / flow claim in skills, agent docs, rules, and architecture docs against the actual codebase. Read-only; produces stale-references / missing-docs / verified-OK report with exact suggested edits.…
Agent
Test-coverage architect — audits gaps weighted by risk, designs suites, and IMPLEMENTS tests in the project's runner, then runs them. Tests behavior, not implementation. Use after a feature, to systematically grow coverage, or to audit what's untested. Classifies code by testability tier so it tests the right thing…
Agent
Accessibility audit of an implemented UI surface — assistive-tech labels, hit-target size, contrast ratios, text scaling, reduced-motion. Read-only; produces an S/A/B/C/D/F per-dimension report where a missing label or sub-threshold hit target blocks ship regardless of visual grade. Run after a screen is…
Agent
Token-discipline sweep — greps source for raw color literals (hex / rgba / rgb / hsl, inline-style color props, Tailwind arbitrary color values) that bypass the design system, classifies each by severity (S0 chrome / S1 content / S2 internal / Exempt), and proposes the closest semantic token. Cheap, periodic…
Agent
Multi-screen arc audit — grades CONTINUITY in a multi-screen user-flow journey (onboarding, checkout, setup, sign-up→first-use, deletion) via two input modes — (a) walks a live flow end-to-end and grades eight gap classes that single-screen reviewers structurally miss, writing a canonical flow doc plus a dated…
Agent
Semantic chrome-vs-handler integrity audit of a single screen — builds a per-element affordance-vs-behavior table (what the chrome PROMISES vs what the handler DOES), then flags dead chrome, redundant affordances, and optical-group disconnects. Read-only; produces an S/A/B/C/D/F report. Run after a screen is…
Agent
Cross-section consistency auditor — compares the project's primary multi-section surface (tab bar / dashboard sections / top-level views) side-by-side to find consistency drift no single-screen review catches: header pattern, section-title typography, card/row pattern, empty state, CTA hit-size, surface treatment.…
Agent
Senior-IC product designer for information-architecture / user-flow / multi-screen work — the gateway between brainstorm and implementation. Produces a spec doc (IA + flow + per-screen state inventory + considered-and-rejected + engine asks) for new features and redesigns; the spec IS the deliverable, not a mockup.…
Agent
Single-screen visual-polish audit — grades a captured screen against the project's own quality bar (or platform-native conventions if none), names a chrome reference and a domain reference, and scans five composition pitfalls. Read-only; produces an S/A/B/C/D/F report anchored to named references plus one highest-ROI…