dennisonbertram

dennisonbertram/lgrep

Instructions file CodexOpenCode

Instructions for dennisonbertram/lgrep, covering project configuration, worktree bootstrap, lgrep - local semantic code search, hard rule and when to use.

dennisonbertram/lgrep

Instructions file

Instructions for dennisonbertram/lgrep, covering project configuration, worktree bootstrap, lgrep - semantic code search, core workflow and storage-aware guidance.

dennisonbertram/claude-coordinator

Plugin Claude Code

A structured orchestration system for Claude Code that plans, delegates, reviews, and learns. Includes coordinator, worker, and reviewer agents.

dennisonbertram/claude-coordinator

Agent

Context reader and situational analyst. Reads files and returns structured briefings for the coordinator. Fast, thorough, and interpretive.

dennisonbertram/claude-coordinator

Agent

Pure-delegation coordinator. Agent-only control plane — delegates ALL I/O to specialized subagents (briefer, planner, worker variants, reviewer, scribe, testers, validators, learning-extractor).

dennisonbertram/claude-coordinator

Agent

Validates that completed work actually satisfies the user's original intent — not just the task instructions, but what the user truly wanted. Runs foreground so it can ask the user directly.

dennisonbertram/claude-coordinator

Agent

Analyzes session work — task outputs, reviewer findings, intent-validator output, AND sub-agent JSONL transcripts — to surface learnings. Captures both successful patterns and process struggles (retries, dead ends, scope drift, confusion) so future sessions improve.

dennisonbertram/claude-coordinator

Agent

Architecture and task planning agent. Analyzes requirements and codebase to produce task breakdowns with dependencies, file boundaries, and contracts.

dennisonbertram/claude-coordinator

Agent

Read-only code reviewer that identifies bugs, regressions, missing tests, and security/concurrency hazards.

dennisonbertram/claude-coordinator

Agent

Lightweight state writer for .coord/ and docs/ files. Cheap, fast, precise. Handles all file writes the coordinator needs.

dennisonbertram/claude-coordinator

Agent

Integration and system-level tester. Runs full test suites, checks regression coverage, validates component integration, and identifies untested code paths.

dennisonbertram/claude-coordinator

Agent

Visual quality tester. Inspects the running UI for layout issues, broken elements, overlapping components, responsiveness, and modern design standards. Uses browser automation.

dennisonbertram/claude-coordinator

Agent

Usability and experience tester. Evaluates whether the app works in a way that makes sense to a human — navigation logic, information architecture, progressive disclosure, and overall intuitiveness.

dennisonbertram/claude-coordinator

Agent

Read-only research worker. Performs root-cause analysis, codebase exploration, dependency mapping, and feasibility checks. Returns structured findings. Makes no code changes and produces no commits.

dennisonbertram/claude-coordinator

Agent

Behavior-preserving refactor worker. No new tests required, but the existing relevant test suite MUST pass before and after the refactor. Single commit per task with before/after test evidence.

dennisonbertram/claude-coordinator

Agent

Adds tests to existing untested code. Not TDD (code already exists), but tests must be meaningful — they would fail under mutation. Two-commit audit trail per task (tests + verification).

dennisonbertram/claude-coordinator

Agent

Strict TDD implementation worker for feature and bugfix tasks. Produces an auditable commit trail (red → green → regression) so the test-first practice is provable from git history.

dennisonbertram/ux-toolkit

Plugin Claude Code

UX testing toolkit for Claude Code — generate user journey stories, walk them through a real browser, and implement the issues found.

dennisonbertram/ux-toolkit

Skill Claude CodeCodex

Generate exhaustive user journey stories by analyzing the codebase. Creates realistic UX paths (short feature exercises and long end-to-end flows) using a swarm of parallel sub-agents. Use when asked to 'create stories', 'walk the app', 'map user journeys', 'generate ux paths', 'create user flows', 'map the app'…

dennisonbertram/ux-toolkit

Skill Claude CodeCodex

Walk UX story catalog through a real browser, testing each journey for correctness, visual quality, and UX excellence. Auto-fixes small issues, files GitHub issues for larger ones.

dennisonbertram/ux-toolkit

Skill Claude CodeCodex

This skill should be used when the user asks to "walk the issues", "work through github issues", "groom and implement issues", "tackle the issue backlog", "start the issue loop", "go through tickets", "work all open issues", "clear the backlog", "process all tickets", or "close out open issues". Orchestrates an…

dennisonbertram/mcp-hats

MCP server Claude CodeCodexCursor +2

MCP server "hats-protocol-server" as configured in dennisonbertram/mcp-hats. Runs locally from the @mcp/hats-protocol-server npm package.

dennisonbertram/website-to-cli

Skill Claude CodeCodex

Turn any website into a fast, beautiful command-line client. Use when the user wants a CLI that replicates a site's features by capturing its network traffic (HAR), recovering the private/undocumented API behind it, and generating a typed terminal client that calls those endpoints directly instead of driving a browser…

dennisonbertram/codex-agent

Plugin Claude Code

Delegate coding tasks to OpenAI Codex CLI as a fast build agent.