Plugin Claude Code
Two Claude Code plugins: engineering workflow discipline (dotclaude — worktree, pre-flight, guard hooks, code review, testing) and design/UX audits (dotclaude-design). Consumed as-is; each adapts to your project at runtime. Install either or both.
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…
Skill Claude CodeCodex
Set up LLM workflow discipline for projects that use AI / LLM calls in production or eval suites. Authors an eval-cost-watcher agent that projects token cost BEFORE regression evals run, plus an AI-workflow-discipline rule covering mock-mode placement, fixture freshness, and multi-stage cost accumulation. Optionally a…
Skill Claude CodeCodex
Set up database / persistent-state discipline for a project with a DB. Authors a data-auditor agent (5 categories of integrity check), a migration-create skill, query-discipline rule (CLI > MCP DB tool for reads), and edit-time regen hook — all derived from the project's actual schema, migration framework, and…
Skill Claude CodeCodex
Author a database schema migration safely — one atomic change per migration, classified by risk with an explicit confirmation gate on destructive changes, access policies composed in the same migration as any new table, generated artifacts regenerated after, and a smoke test before declaring done. Discovers the…
Plugin Claude Code
Code review, pre-flight, worktree isolation, guard hooks, and risk-weighted test coverage for Claude Code. Consumed as-is; /dotclaude:coding and /dotclaude:testing elicit your project's bar.
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…
Hook
Runs before the agent uses a tool for Bash, Write, Edit and NotebookEdit tool calls, executing check-git-safety.sh, check-bash-safety.sh and check-main-checkout-edit.sh via bash (3 commands). From vindm/dotclaude.
Hook
Runs after a tool call finishes for Write, Edit and Bash tool calls, executing check-secret-leak.sh, check-file-size.sh and check-main-checkout-bash-write.sh via bash (3 commands). From vindm/dotclaude.
Hook
Runs when the agent finishes a response, executing check-delivery-claim.sh via bash. From vindm/dotclaude.
Hook
Runs when a session starts, executing git-context-sessionstart.sh via bash. From vindm/dotclaude.
Hook
Runs when a session ends, executing warn-uncommitted-on-clear.sh via bash. From vindm/dotclaude.
Skill Claude CodeCodex
Set up a project's AI dev infrastructure the consume-direct way — enable the dotclaude plugin (which provides the universal base: operating-discipline, the auditor agents, the universal guard hooks) and author ONLY the un-shareable project-specific layer (identity, architecture, quality-bar benchmarks, knowledge…
Skill Claude CodeCodex
Elicit coding hygiene intent for a project and write it to a thin artifact — .claude/dotclaude/code-anti-patterns.md plus a few dotclaude.yml keys — derived from the project's actual file-size distribution and the bug classes visible in git history. No agent, rule, or hook is authored: the consumed code-review agent…
Skill Claude CodeCodex
Decompose a file that has grown over the size ceiling into focused sibling files — extracting at cognitive seams (hooks, sub-components, pure helpers, types), in the right order, behind a user-approved plan, with post-extraction verification. Invoke when a file-size check warns or a file has become too large to…
Skill Claude CodeCodex
The authority order across a project's three knowledge layers — guidance (.claude/), code (truth), and docs/ (reflection + transient intent) — with code as the tiebreak when a doc and the code disagree. Load when reading or trusting a doc to make a code decision, when authoring rules or skills that reference docs, or…
Skill Claude CodeCodex
Core operating discipline for any non-trivial task — understand before building, reason to the right solution, execute completely and verified, stay lean, and avoid the parallel-path and subagent-dispatch traps. Load this on any substantive coding, design, planning, debugging, refactor, or review work (skip only for…
Skill Claude CodeCodex
Elicit test-coverage risk priorities for a project and write them to a thin artifact — .claude/dotclaude/test-risk-model.md plus a dotclaude.yml key — derived from the project's actual test/source ratio, its most-edited untested files, and the user's own sense of what scares them most. No agent, rule, or hook is…
Skill Claude CodeCodex
Set up worktree-per-feature discipline for a project where several AI sessions (or humans + agents) work concurrently and collide in one checkout. Writes a thin worktree: config block that the plugin's CONSUMED main-checkout hook reads (no rendered per-project hook copy), plus a project-specific worktree lifecycle…
Plugin Claude Code
A design/UX audit layer for Claude Code. /dotclaude:design elicits your design north-star; ux, flow, pages, a11y, interaction, and design-token audits grade every screen against it, plus a product-designer IA/flow spec.