a-tokyo

39 mods across 3 repositories, 44 stars between them.

production-grade

25

a-tokyo/agent-skills

Skill Claude CodeCodex

Principle-engineering posture for production-grade code: reads the repo first, plans before code, matches conventions, pulls latest docs over training recall, and ships the simplest correct change that holds the bar — proper algorithms and data structures, idempotent writes, schema+queries+indexes as one artefact…

15 26d ago B 170 tokens copy · 100% MIT

a-tokyo/agent-skills

Skill Claude CodeCodex

Migrate a project from Tailwind CSS v3 to v4 safely and completely. Runs the official @tailwindcss/upgrade codemod, then drives the judgment it can't: reconciling dependencies and PostCSS/Vite/CLI plumbing, porting JS config to CSS-first @theme (or keeping it via @config), auditing the v4 changed-defaults that…

15 26d ago A 271 tokens original MIT

tribunal

27

a-tokyo/agent-skills

Skill Claude CodeCodex

Runs a doer -> verifier-panel -> consensus loop to verify a deliverable before it ships. An orchestrator freezes acceptance criteria before implementation, dispatches a doer, then convenes a context-walled panel of independent verifiers - including an adversary with an explicit must-oppose mandate - for…

15 26d ago A 207 tokens original MIT

autoresearch

28

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement…

10 26d ago A 116 tokens original MIT

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Factory skill that creates production-grade, benchmarked, autonomously improved, and verified agent skills. Orchestrates a 5-phase pipeline: interview the user to discover purpose and gold standards, research domain materials with parallel subagents, draft the skill with a design-first approach, invoke autoresearch to…

10 26d ago A 118 tokens copy · 100% MIT

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

10 26d ago A 61 tokens copy · 100% MIT

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.

10 26d ago A 39 tokens copy · 100% MIT

handoff

32

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Compact the current conversation into a handoff document for another agent to pick up.

10 26d ago A 19 tokens copy · 78% MIT

llm-council

33

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs…

10 26d ago A 80 tokens original MIT

premortem

34

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Identify failure modes before they occur using structured risk analysis.

10 26d ago A 14 tokens copy · 100% MIT

production-grade

35

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Principle-engineering posture for production-grade code: reads the repo first, plans before code, matches conventions, pulls latest docs over training recall, and ships the simplest correct change that holds the bar — proper algorithms and data structures, idempotent writes, schema+queries+indexes as one artefact…

10 26d ago B 170 tokens copy · 100% MIT

tribunal

36

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Runs a doer -> verifier-panel -> consensus loop to verify a deliverable before it ships. An orchestrator freezes acceptance criteria before implementation, dispatches a doer, then convenes a context-walled panel of independent verifiers - including an adversary with an explicit must-oppose mandate - for…

10 26d ago A 207 tokens copy · 100% MIT

a-tokyo/agent-skills-harness

Skill Claude CodeCodex

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

10 26d ago A 24 tokens copy · 100% MIT

a-tokyo/agent-skills-harness

Instructions file

Instructions for a-tokyo/agent-skills-harness, a project described as: A factory for building production-grade agent skills — benchmarked against gold standards, autonomously improved via an autoresearch loop, and verified by independent multi-agent consensus.

10 26d ago A 3 tokens copy · 100% MIT