Skill Claude CodeCodex
Single-task execution loop with structured context handoff. Enforces the discipline of plan → execute → simplify → review → close. Uses Beads (bd) for task tracking so context survives across sessions without artifact clutter. A new session runs bd ready and picks up exactly where the last one left off. Supports…
Skill Claude CodeCodex
Competitive Problem Decomposition. Spawns N independent agents, each proposing a DIFFERENT decomposition of a problem into subproblems using a distinct structural lens. One decomposes by user journey, another by data flow, another by failure domain, another by team boundary, another by deployment unit. Synthesizes…
Skill Claude CodeCodex
Evaluate an MCP tool's agentic usability via parallel test scenarios plus a meta-reflection pass, producing a scored improvement report.
Skill Claude CodeCodex
Parallel Strategy for System Transitions. Spawns N independent agents in isolated worktrees, each implementing a DIFFERENT migration strategy for the same old-system-to-new-system transition. The path is the variable, not the destination — all agents implement the same end state but via different transition paths.…
Skill Claude CodeCodex
Cancel or pause a PRD build run.
Skill Claude CodeCodex
Resume a paused or interrupted PRD build run.
Skill Claude CodeCodex
Show PRD build orchestration status.
Skill Claude CodeCodex
Decompose a PRD into parallel work units and build them with independent agents.
Skill Claude CodeCodex
Run /prd-build over multiple PRDs with full worktree lifecycle (create, dispatch, FF-merge, cleanup). Single-command dispatch from one session — sequential or parallel.
Skill Claude CodeCodex
Prospective Failure Narratives. Spawns N independent agents, each writing a narrative from the future where the project FAILED for a different root cause. No agent sees others' failure stories. A lead agent then synthesizes all failure narratives into a structured risk registry with severity ratings and mitigations.
Skill Claude CodeCodex
Independent Verification by Reimplementation. Spawns N agents in isolated worktrees to implement the SAME specification independently, with no knowledge of each other's code. Compares outputs to produce a convergence/divergence map that reveals where the spec is clear, where it is ambiguous, and what it fails to…
Skill Claude CodeCodex
Run diverge → converge → premortem pipeline to produce a risk-annotated PRD.
Skill Claude CodeCodex
Build-order planning via competing sequencing strategies. Takes a chosen design (from /diverge-prototype or any architecture decision) and spawns N independent agents, each proposing a different build-order strategy. Each agent produces a sequenced implementation plan with milestones, dependencies, and risk…
Skill Claude CodeCodex
Review changed code for reuse, quality, and efficiency, then fix any issues found.
Skill Claude CodeCodex
Parallel Adversarial Attack Surface Analysis. Spawns N independent agents, each tasked with BREAKING a system from a different attack angle. No agent sees others' findings. Synthesizes into a vulnerability map with severity ratings.
sjarmak/coding-agent-workflows
Instructions file CodexOpenCode
Instructions for sjarmak/coding-agent-workflows, covering agentic coding practices, principles, agent roles, skills and workflows.
sjarmak/coding-agent-workflows
Agent
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
sjarmak/coding-agent-workflows
Agent
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
sjarmak/coding-agent-workflows
Agent
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
sjarmak/coding-agent-workflows
Agent
Simplify and clean up code after generation. Use proactively after writing or modifying code.
sjarmak/coding-agent-workflows
Agent
PostgreSQL specialist for query performance, schema design, security/RLS, and migration safety. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance.
sjarmak/coding-agent-workflows
Agent
End-to-end testing specialist. Generates, maintains, and runs E2E tests for critical user journeys; quarantines flaky tests; captures artifacts (screenshots, videos, traces). Prefers Agent Browser with a Playwright fallback.
sjarmak/coding-agent-workflows
Agent
Go build, vet, and compilation error resolution specialist. Fixes build errors, go vet issues, and linter warnings with minimal changes. Use when Go builds fail.
sjarmak/coding-agent-workflows
Agent
Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects.