Skill Claude CodeCodex
Reduction-ladder and minimum-diff checks the Pythinker judge subagent applies to every non-trivial diff.
Skill Claude CodeCodex
Reduction-ladder and minimum-diff checks the Pythinker judge subagent applies to every non-trivial diff.
Skill Claude CodeCodex
Over-engineering review checklist the parent runs before declaring non-trivial code changes done.
Skill Claude CodeCodex
Produce a concise reviewer-friendly walkthrough of a PR or diff, including changed areas, behavior, tests, and risks.
Skill Claude CodeCodex
Answer Pythinker CLI usage, configuration, and troubleshooting questions. Use when user asks about Pythinker CLI installation, setup, configuration, slash commands, keyboard shortcuts, MCP integration, providers, environment variables, how something works internally, or any questions about Pythinker CLI itself.
Skill Claude CodeCodex
Reproduce a bug report with evidence-first investigation, bounded variants, and a clear repro/non-repro verdict.
Skill Claude CodeCodex
Resolve git merge/rebase conflicts safely by preserving both sides' intent and validating the result.
Skill Claude CodeCodex
Review a pull request or working-tree diff with severity-scored, evidence-backed findings.
Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Pythinker's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Claude CodeCodex
Implement a feature or fix from product/technical specs while checking the final code against the stated requirements.
Skill Claude CodeCodex
Draft a product spec from a user request, issue, or bug report with goals, non-goals, requirements, and acceptance criteria.
Skill Claude CodeCodex
Draft a technical implementation spec from product requirements and codebase evidence.
Plugin Claude Code
CLI coding-agent orchestration for Claude through Codex, OpenCode, Pi, and Pythinker Code, with a commitment-boundary advisor.
Plugin Claude Code
Verified coding-agent delegation for Claude Code with isolated Producers, frozen candidate artifacts, independent review, and human-controlled integration.
Settings file Claude Code
Agent settings declaring 3 allowed tools.
MCP server Claude CodeCodexCursor +2
MCP server "runtime" as configured in PyModel/claude-architect. Runs ${CLAUDE_PLUGIN_ROOT}/runtime/bootstrap.mjs with node.
Instructions file CodexOpenCode
Instructions for PyModel/claude-architect, covering agent guide, project purpose, sources of truth, mandatory operating rules and code discovery.
Instructions file
Instructions for PyModel/claude-architect, a project described as: Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a human approves.
Agent
Strictly non-mutating commitment-boundary advisor. Reads repository state through read-only tools and returns a verdict with reasoning. Never edits.
Agent
Second-opinion advisor running Claude's most capable model (Fable 5). Consult at commitment boundaries — before architectural decisions, data migrations, big refactors, or API designs, and whenever the same problem has resisted two attempts. Pass it the decision, the constraints, and the options considered; it returns…
Agent
Runs ONE claude-architect delegation lane (produce + verify only) so it surfaces as a native subagent. Input is a laneId, checkoutPath, protocolVersion, and a complete Delegation Spec; output is the structured lane report. Never reviews, decides, or integrates.
Skill Claude CodeCodex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
Skill Claude CodeCodex
Let Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the Candidate Artifact, record a decision, and integrate only accepted bytes. Use for implementation delegation, Producer selection, or commitment-boundary review.
Skill Claude CodeCodex
Execute an implementation plan with the Superpowers subagent-driven-development loop while every task is implemented by a verified Claude Architect Producer — isolated worktree, frozen Candidate Artifact, independent verification, fresh-context review, runtime-gated acceptance. Use when executing a multi-task plan…
Skill Claude CodeCodex
React feature-based architecture guidelines for scalable applications (formerly feature-architecture). This skill should be used when writing, reviewing, or refactoring React code to ensure proper feature organization. Triggers on tasks involving project structure, feature organization, module boundaries…