Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
jgravelle/jcodemunch-mcp
给AI编程助手装个精准取代码的管道,找函数时少读整文件,省九成以上的token开销。A server that lets your AI read just the symbol it needs from GitHub, so code exploration uses far fewer tokens.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
定位代码中的函数与变量
只取相关几行,不读整个文件
自动给项目建立索引
统计一次会话省下的字数
跳过常见框架的初次索引
Search for a symbol by name and get its exact location
Read only the source of a function, not the entire file
Track tokens served and saved per session with a stats report
Configure per-project languages and file size limits
Skip initial indexing with pre-built starter packs for popular toolkit
上手GET STARTED
uv tool install jcodemunch-mcp选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.
静态扫描未发现明显风险,但不代表安全。The static scan found no obvious risk patterns in the documentation, but that does not prove the project is safe. The security level is marked as unknown, and it requires both an API key and a local environment.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+4.8%+4.8%
2.7k → 2.9k stars · 48 个快照2.7k → 2.9k stars · 48 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
1 条外部提及1 external mentions
状态STATUS
持续活跃Active
质量 AQuality A
近7天有38次提交,项目仍在快速迭代。Reported 95%+ token cost reduction on code exploration
HN_STORY · 1 points · 0 comments
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
},
{
"agent": "claude-desktop",
"evidence": "readme: …our MCP clients (Claude Code, Claude Desktop, Cursor, Windsurf, Continue,…"
},
{
"agent": "claude-ai",
"evidence": "readme: …this in managed settings (the claude.ai admin console, an MDM policy,…"
},
{
"agent": "codex",
"evidence": "readme: …*, **Cursor**, **VS Code**, **Codex CLI**, **Windsurf**, **Continue**…"
},
{
"agent": "cursor",
"evidence": "readme: …unch-mcp%22%5D%7D) [, write…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …f, Continue, Codex, opencode, Gemini CLI, Cline, VS Code with Copilot)…"
},
{
"agent": "vscode",
"evidence": "readme: …*Claude Code**, **Cursor**, **VS Code**, **Codex CLI**, **Windsurf*…"
},
{
"agent": "opencode",
"evidence": "readme: …r, Windsurf, Continue, Codex, opencode, Gemini CLI, Cline, VS Code w…"
},
{
"agent": "copilot",
"evidence": "readme: …# For admins Claude Code and GitHub Copilot (the Copilot app, Copilot CLI…"
}
],
"apiKey": "`PYTHONPATH=src python ...`, `GITHUB_TOKEN=\"\" gh ...`, `BR=$(...)`. **Inline env-v",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 3,
"dev-tools": 4,
"indie-web": 0,
"skill-agent": 10,
"productivity": 4
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "treamlit` (`<25`), `inference-gpu` (`~=24.0`). Upgrading breaks three wor",
"skillMdTotal": 11,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "11 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "server.json (MCP registry manifest)",
"weight": 0.85
},
{
"signal": "python dependency on mcp / fastmcp + MCP framing",
"weight": 0.8
},
{
"signal": "skills/ directory with 10 markdown files",
"weight": 0.75
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "README ships an mcpServers config for this server",
"weight": 0.7
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".claude/skills/benchmark-methodology/SKILL.md",
".claude/skills/changelog-format/SKILL.md",
".claude/skills/claude-md-budget/SKILL.md",
".claude/skills/mechanism-not-instance/SKILL.md",
".claude/skills/observatory/SKILL.md",
".claude/skills/pr-description/SKILL.md",
".claude/skills/release/SKILL.md",
".claude/skills/standard-axes/SKILL.md",
".claude/skills/tool-surface-discipline/SKILL.md",
".claude/skills/version-scheme/SKILL.md",
"plugin/jcodemunch/skills/jcodemunch/SKILL.md"
],
"skillMdFetched": 11
}