pokayokay
01Plugin Claude Code
AI-assisted development orchestration with task tracking and skill-based routing.
Plugin Claude Code
AI-assisted development orchestration with task tracking and skill-based routing.
Instructions file CodexOpenCode
Instructions for srstomp/pokayokay, covering agents.md, project overview, development commands, plugin from it (run from repo root) and run specific shell tests.
Instructions file
Instructions for srstomp/pokayokay, covering claude.md, project overview, development commands, local development - load plugin from directory and validate plugin manifest.
Plugin Claude Code
AI-powered development workflows with task tracking, skill-based routing, and guaranteed execution hooks.
MCP server Claude CodeCodexCursor +2
MCP server for ohno task management. Runs locally from the @stevestomp/ohno-mcp npm package.
Agent
Completeness auditor for L0-L5 feature verification. Use proactively after story/epic completion, when auditing features, or when validating that implemented features are user-accessible.
Agent
Refines ambiguous task requirements through structured exploration. Produces clear acceptance criteria and implementation approach. Runs before implementation for under-specified tasks.
Agent
Use only when dispatched by a pokayokay coordinator after UI changes with task and dev-server details; not for ad-hoc browsing. Verifies UI changes in a real browser. Checks visual elements, interactions, and console errors. Returns PASS, ISSUE, or SKIP with evidence.
Agent
Use only when dispatched by a pokayokay coordinator with a filled design-review-prompt template before implementation begins; not for ad-hoc design questions. Reviews task requirements against codebase patterns and produces a validated implementation approach before coding begins. Read-only pre-implementation design…
Agent
Fast codebase exploration for understanding structure, patterns, and architecture. Use proactively for research tasks, planning phases, or when you need to understand how something works before implementing.
Agent
Use only when dispatched by a pokayokay coordinator on test failures with the failing test output; not for ad-hoc debugging. Lightweight test failure fixer. Parses test output, makes targeted edits to fix failures, re-runs tests. Attempt limit set by coordinator (default 3).
Agent
Use only when dispatched by a pokayokay coordinator (/work, /fix, /hotfix) with a filled implementer-prompt template; not for ad-hoc edits. Implements a single task with AC-first TDD and fresh context. Receives full task details from coordinator, implements, self-reviews, commits, and reports back.
Agent
Use only when dispatched by the /plan coordinator with a filled planner-prompt template and a PRD document; not for ad-hoc planning questions. Analyzes PRD documents and produces structured implementation plans with epic/story/task breakdowns, skill routing, and dependency mapping. Returns a structured plan for the…
Agent
Use only when dispatched by a pokayokay coordinator with a filled quality-review-prompt template after spec review passes; not for ad-hoc code review. Reviews implementation for code quality, tests, edge cases, and conventions. Returns PASS or FAIL with specific issues.
Agent
Code review specialist. Analyzes code quality, security, and best practices. Use proactively after code changes, before commits, or when reviewing pull requests.
Agent
Security audit specialist. Scans for vulnerabilities, OWASP issues, and security misconfigurations. Use proactively for security reviews, before deployments, or when auditing authentication/authorization.
Agent
Use only when dispatched by a pokayokay coordinator with a filled spec-review-prompt template after implementation completes; not for ad-hoc code review. Reviews implementation against task specification with adversarial framing. Checks all acceptance criteria met, no missing requirements, no scope creep. Returns PASS…
Agent
Time-boxed technical investigation with structured output. Use for feasibility studies, architecture exploration, integration assessment, or when you need to answer a bounded technical question.
Agent
Test execution specialist. Runs test suites and reports failures concisely. Use after implementation changes, before commits, or when verifying fixes.
Command
Design RESTful APIs with consistent patterns.
Command
Review architecture and plan refactoring.
Command
Audit feature completeness and identify gaps.
Command
Create, debug, or optimize CI/CD pipelines.
Command
Design database schemas and migrations.