# jidra

> jidra — akhilsinghcodes-jidra. Use this tool when you need to optimize LLM agent performance by reducing token usage, and enhance code intelligence for frameworks like Java, Python, and TypeScript. It indexes code into a verified call graph, providing a more efficient interface for agent queries. Ideal for use cases involving large codebases, git version control, and MCP server integration.

Canonical page: https://skillsregistry.net/skills/akhilsinghcodes-jidra  
JSON: https://api.skillsregistry.net/v1/skills/akhilsinghcodes-jidra

## Description

Framework-aware code intelligence for LLM agents. Indexes Java, Python, TypeScript, Go, Scala into a verified call graph via tree-sitter + Rust. MCP server, Haiku sub-agent, and git hooks included. 68–95% agent token reduction.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/akhilsinghcodes/jidra)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "akhilsinghcodes-jidra"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/akhilsinghcodes-jidra` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/akhilsinghcodes-jidra/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt