XINYUNLL/xycode
基于 claude-code-from-scratch 二次开发的 coding agent(TS):加入自我纠错闭环、本地 embedding 记忆、MCP、SWE-bench 评测 | A coding agent (TS) built on claude-code-from-scratch, adding self-correction, local embedding memory, MCP, and SWE-bench eval
field: AI / ML
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~7.6k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code
$ npx degit XINYUNLL/xycode/.claude ./rig-xycode # inspect, then merge into .claude/ 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 XINYUNLL/xycode/.claude/skills/commit .claude/skills/commit $ npx degit XINYUNLL/xycode/.claude/skills/greet .claude/skills/greet
$ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/XINYUNLL/xycode/main/.claude/agents/reviewer.md 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 *)"
]
}
} MCP servers (3)
| server | source | est. tokens |
|---|---|---|
| test | local / custom | 2.5k |
| github | local / custom | 2.5k |
| memory | local / custom | 2.5k |
Skills (2)
Subagents (1)
| reviewer | Code review specialist — analyzes code quality and suggests improvements |
Similar rigs
Windy3f3f3f3f/claude-code-from-scratch
Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码,读不动?用 ~5000 行 TypeScript / Python 从零复现核心架构,11 章分步教程带你理解 coding agent 精髓
Pragmatist 2.6k tok · · Q0
alex35mil/dotfiles
My dotfiles
Minimalist 1.2k tok · · Q0
simnalamburt/.dotfiles
:memo: My UNIX-like system configuration files
Minimalist 21 tok · · Q15
pmqueiroz/toolbelt
:penguin: automated script to configure my personal environment
Minimalist 547 tok · · Q0