a-tokyo/agent-skills-harness

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.

This repository also configures its own agents. See what agent-skills-harness tells them →

10Stars on the repository
12Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

autoresearch

01

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…

not rated 10 1mo 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…

not rated 10 1mo 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.

not rated 10 1mo 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.

not rated 10 1mo ago A 39 tokens copy · 100% MIT

handoff

05

a-tokyo/agent-skills-harness

Skill Claude Code

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

not rated 10 1mo ago A 19 tokens copy · 78% MIT

llm-council

06

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…

not rated 10 1mo ago A 80 tokens original MIT

premortem

07

a-tokyo/agent-skills-harness

Skill Claude Code

Identify failure modes before they occur using structured risk analysis.

not rated 10 1mo ago A 14 tokens copy · 100% MIT

production-grade

08

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…

not rated 10 1mo ago B 170 tokens copy · 100% MIT

tribunal

09

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…

not rated 10 1mo ago A 207 tokens copy · 100% MIT

a-tokyo/agent-skills-harness

Skill Claude Code

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

not rated 10 1mo ago A 24 tokens copy · 100% MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: