LeeYudok/agents-scaffold

Fork-and-fill bootstrap for AI coding agents (Claude Code first, Codex/Gemini via AGENTS.md) — agents, skills, hooks, tiered rules (P0/P1/P2), and stack presets composed into one enforced pre-commit gate. Korean/English

This repository also configures its own agents. See what agents-scaffold tells them →

36Stars on the repository
29Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

docs-sync

01

LeeYudok/agents-scaffold

Skill Claude Code needs its repo

A documentation review that compares statements in README files and project instructions with the current code, command output, and official documentation. It updates related language versions or files together when needed.

not rated 36 3d ago A SkillSpector: pass 106 tokens original MIT

example-skill

02

LeeYudok/agents-scaffold

Skill Claude Code

A template for creating a project-specific coding-agent skill, with sections for checking conditions, doing the work, and verifying the result. The included text is in Korean.

not rated 36 3d ago A 31 tokens original MIT

grill-me

03

LeeYudok/agents-scaffold

Skill Claude Code

A question-driven review of an idea or feature before coding begins. It repeatedly tests the goal, assumptions, edge cases, security, privacy, operating needs, and what can be left out of the first version.

not rated 36 3d ago A SkillSpector: pass 73 tokens original MIT

memory-factcheck

04

LeeYudok/agents-scaffold

Skill Claude Code

A check that compares the project’s saved agent notes with the current code, database, issue tracker, and files. It identifies notes whose claims are outdated or no longer match reality.

not rated 36 3d ago A SkillSpector: warn 137 tokens original MIT

review

05

LeeYudok/agents-scaffold

Skill Claude Code

A combined code review and security audit for proposed code changes. A code review checks quality and maintainability, while a security audit looks for vulnerabilities such as unsafe input handling or weak encryption.

not rated 36 changed 27d ago A SkillSpector: pass 45 tokens original MIT

search-first

06

LeeYudok/agents-scaffold

Skill Claude Code

A workflow rule for searching for an existing solution before writing new code. It checks the repository, internal mirrors, package registries, connected tools, and GitHub in that order.

not rated 36 changed 18d ago A SkillSpector: pass 117 tokens original MIT

security-precheck

07

LeeYudok/agents-scaffold

Skill Claude Code

A pre-release security check for reviewing code and agent configuration before an external security audit. It scans for issues such as exposed secrets, missing authentication, and personal-data logging, then groups findings by urgency.

not rated 36 changed 27d ago A SkillSpector: warn 99 tokens original MIT

skill-evolve

08

LeeYudok/agents-scaffold

Skill Claude Code

A review process for improving an agent skill after it produces a mistake, omission, or useful new warning. It reads the skill, proposes a focused change, asks for approval, and then tests the improvement.

not rated 36 changed 27d ago A SkillSpector: pass 51 tokens original MIT

status

09

LeeYudok/agents-scaffold

Skill Claude Code

A project-status checklist that gathers repository state, build results, tests, open GitLab issues, branches, and running processes. Git is a system for tracking code changes, and a monorepo is a repository containing multiple projects.

not rated 36 changed 27d ago A SkillSpector: warn 44 tokens original MIT

handoff

10

LeeYudok/agents-scaffold

Skill Claude Code

A handoff skill that records the current work and the exact state needed for another coding session to continue. It writes this state to HANDOFF.md and can also share it through a project issue or collaboration tool.

not rated 36 3d ago A 201 tokens original 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: