phobologic

phobologic/claude_code_helpers

Agent Claude Code

Verifies that an implementation satisfies its ticket's acceptance criteria. Reads the ticket, reads the diff, and returns PASS or FAIL with specifics. Does not evaluate code quality, style, or anything beyond whether the AC are met.

phobologic/claude_code_helpers

Agent Claude Code

Adversarial code reviewer. Assumes the code has problems and finds evidence. Covers logic, security, performance, and reliability in a single pass with a discriminator mindset.

phobologic/claude_code_helpers

Agent Claude Code

Reviews code for logical errors, best practices, and architecture issues.

phobologic/claude_code_helpers

Agent Claude Code

Reviews code for performance issues, efficiency, and resource usage.

phobologic/claude_code_helpers

Agent Claude Code

Reviews code for structural problems — duplication, dead code, broken abstractions, and consistency violations.

phobologic/claude_code_helpers

Agent Claude Code

Creative UI/UX designer on a design sprint team. Produces design proposals across three rounds of increasing concreteness — mood/direction in Round 1, system in Round 2, spec-ready values in Round 3. Three instances of this agent run in parallel; the team lead supplies each with its designer number and the app context…

phobologic/claude_code_helpers

Agent Claude Code

Persistent evaluator on a design sprint team. Scores three designer proposals across three rounds against weighted criteria, issues shared briefs between rounds, and writes the final design specification synthesis after Round 3.

phobologic/claude_code_helpers

Agent Claude Code

Implements a single tk ticket. Reads the ticket, gathers context, writes code, writes tests, ensures tests pass, and commits. Does not self-review or verify its own acceptance criteria.

phobologic/claude_code_helpers

Agent Claude Code

Adversarial code reviewer on an agent team. Reviews changes that have already passed AC verification. Focuses on correctness, security, reliability, and performance. Creates tk tickets for findings.

phobologic/claude_code_helpers

Agent Claude Code

Aggregates and organizes code review findings from multiple reviewers.

phobologic/claude_code_helpers

Agent Claude Code

Reviews code for security vulnerabilities, risks, and defensive coding practices.

phobologic/claude_code_helpers

Agent Claude Code

Adversarial reviewer for implementation plans and specs. Evaluates whether a plan will actually work when handed to independent implementer agents. Focuses on testability of ACs, gaps between tickets, dependency correctness, self-containment, and product decisions the plan settles without the user's answer.

phobologic/claude_code_helpers

Plugin Claude Code

Bundles 1 hook

Go language support: goimports auto-formatting on file edits, Go coding conventions.

phobologic/claude_code_helpers

Skill Claude Code

Run a multi-agent GAN-style design sprint to produce a frontend design specification. Three designer agents (sonnet) propose independently across three rounds of increasing concreteness; a persistent evaluator (opus) scores each round and issues a shared brief; the team lead writes the final spec. Use when the user…

phobologic/claude_code_helpers

Skill Claude Code

Show a tree of epics with open/closed ticket counts. Use when the user asks to see an epic tree, visualize epic hierarchy, or show ticket counts by epic.

phobologic/claude_code_helpers

Skill Claude Code

Implement a set of tk tickets in parallel using a DAG-driven agent team with continuous dispatching. Spawns a pool of up to 4 implementers and up to 2 quality reviewers at startup (sized to the input ticket count, so a single-ticket run gets 1 + 1); dispatches tickets as they unblock without wave boundaries. Quality…

phobologic/claude_code_helpers

Skill Claude Code

Implement a set of tk tickets in parallel using an agent team. Analyzes tickets for file-level conflicts, groups into minimum-wave batches, and runs each wave with parallel implementers validated by a quality reviewer. Designed for multi-review fix batches where tickets don't have formal acceptance criteria. Use when…

phobologic/claude_code_helpers

Skill Claude Code

Implement one or more tk tickets. Use when the user says "implement ticket X", "work on ticket", "do ticket.

phobologic/claude_code_helpers

Skill Claude CodeCodex

Wire a shared opt-in rule from /.claude/optionalrules/ into the current project's .claude/rules/ as a symlink. Use when the user says "load the shared rule", "set up shared rule X for this project", "opt in to the skeletons rule", or similar. Takes one argument — the rule name (e.g. skeletons).

phobologic/claude_code_helpers

Skill Claude Code

Perform a comprehensive code review using multiple specialized sub-agents in parallel. Covers logical correctness, performance, readability, and security. Creates tk tickets if tk is available, otherwise writes a report to .code-review/final-report.md.

phobologic/claude_code_helpers

Skill Claude Code

Spawn a team of Playwright-driven agents to explore a running web app as simulated users. Supports ad-hoc exploration (routes discovered from source code) and catalog mode (predefined scenarios loaded by name). Uses wave-based execution with agent recycling to prevent context exhaustion. Findings become tk tickets.…

phobologic/claude_code_helpers

Skill Claude CodeCodex

Quick code review using an adversarial sub-agent. Surfaces Critical and High issues first. Creates tk tickets for Critical/High/Medium findings if tk is available.

phobologic/claude_code_helpers

Skill Claude Code

Execute a tk epic using a DAG-driven agent team with continuous dispatching. Spawns a pool of up to 4 implementers, up to 2 quality reviewers, and 1 AC verifier at startup (sized to the open ticket count, so a single-ticket epic gets 1 + 1 + 1); dispatches tickets as they unblock without wave boundaries. Use when the…

phobologic/claude_code_helpers

Skill Claude Code

Execute a tk epic using an agent team. Creates implementer, AC verifier, and quality reviewer teammates, dispatches unblocked tickets for parallel implementation, and manages the validation loop. Use when the user says "run epic", "execute epic", "start working on the epic", or similar.