JiniBean/harness-for-K-legacy
한국형 SI 레거시용 에이전트 하네스. 에이전트가 알기 힘든 국내 SI 관례에 맞춰 하네스 환경을 구축합니다.
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/JiniBean/harness-for-K-legacy MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit JiniBean/harness-for-K-legacy/modules/comment-gen/skills/comment-gen .claude/skills/comment-gen $ npx degit JiniBean/harness-for-K-legacy/modules/garbage-collector/skills/garbage-collector .claude/skills/garbage-collector $ npx degit JiniBean/harness-for-K-legacy/modules/issue-flow/skills/issue-flow .claude/skills/issue-flow $ npx degit JiniBean/harness-for-K-legacy/modules/log-debug/skills/log-debug .claude/skills/log-debug $ npx degit JiniBean/harness-for-K-legacy/modules/memory-tidy/skills/memory-tidy .claude/skills/memory-tidy $ npx degit JiniBean/harness-for-K-legacy/modules/nexacro/skills/generate .claude/skills/generate $ npx degit JiniBean/harness-for-K-legacy/modules/ponytail/skills/ponytail-audit .claude/skills/ponytail-audit $ npx degit JiniBean/harness-for-K-legacy/modules/ponytail/skills/ponytail-gain .claude/skills/ponytail-gain $ npx degit JiniBean/harness-for-K-legacy/modules/ponytail/skills/ponytail-help .claude/skills/ponytail-help $ npx degit JiniBean/harness-for-K-legacy/modules/ponytail/skills/ponytail-review .claude/skills/ponytail-review $ npx degit JiniBean/harness-for-K-legacy/modules/ponytail/skills/ponytail .claude/skills/ponytail $ npx degit JiniBean/harness-for-K-legacy/modules/response/skills/response .claude/skills/response $ npx degit JiniBean/harness-for-K-legacy/modules/verify/skills/verify .claude/skills/verify
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (13)
Similar rigs
JiniBean/harness-kit
웹 프로젝트용 에이전트 하네스. 프로젝트를 읽어 규칙·훅·스킬을 맞춰 하네스 환경을 구축합니다.
Skill Collector 1.7k tok · · Q0
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok · · Q0
saqie803/ponytail
Ship production-ready code with one line of AI-generated output, built for 20 agents and zero ceremony.
Pragmatist 714 tok · · Q0
acememe7/Orgbot
Local multi-agent coding rooms for Ubuntu Linux. Coordinate Claude, Codex, Grok, DeepSeek and Ollama Cloud in isolated workspaces with conflict review and shared context. No relay account required.
Pragmatist 66 tok · · Q0