Jragmunch CLI — AI skill for Claude Code
Maximal token-efficient RAG for headless Claude.
How to install Jragmunch CLI
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open jgravelle/jragmunch-cli and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Jragmunch CLI does
Maximal token-efficient RAG for headless Claude. Auth-agnostic; slice-level retrieval.
Alternatives in AI
- Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
- Rb Setup — First-time setup 1.3k ★
- Clawcodex — Token efficient Claude Code full Python rebuild 875 ★
README
jragmunch-cli
[](https://pypi.org/project/jragmunch/) [](https://pypistats.org/packages/jragmunch) [](https://pypi.org/project/jragmunch/) [](https://github.com/jgravelle/jragmunch-cli/blob/master/LICENSE) [](https://github.com/jgravelle/jragmunch-cli/stargazers)
**Maximal token-efficient RAG for headless Claude.** Uses your existing `claude` CLI; auth-agnostic; slice-level retrieval powered by [jcodemunch-mcp](https://github.com/jgravelle/jcodemunch-mcp).
Billing: SDK credit by default, API on opt-in
**Starting June 15, 2026**, Anthropic's Pro and Max subscriptions include a **monthly Agent SDK credit** that scales with subscription tier (**$20** Pro, **$100** Max 5x, **$200** Max 20x) covering `claude -p` and SDK-based tools like jragmunch. By default, jragmunch strips `ANTHROPIC_API_KEY` and `ANTHROPIC_AUTH_TOKEN` from the subprocess environment before spawning `claude`, so the CLI uses your Claude OAuth login and runs against that SDK credit. ([Anthropic announcement](https://support.claude.com/en/articles/15036540-use-the-claude-agent-sdk-with-your-claude-plan))
- Inside your monthly SDK credit: $0 actual dollars.
- Past the credit: Anthropic's "extra usage" kicks in if you've
enabled it (opt-in, manually toggleable in Anthropic's billing
settings); otherwise the call fails. Heavy users will want to either
enable extra usage or pass
--use-api. - Your subscription session limits are not touched. Those stay
reserved for interactive use of Claude Code and chat. (Pre-June-15
behavior was the opposite: programmatic
claude -pconsumed session quota. The Agent SDK credit replaces that arrangement.)
If
Related Skills
Browser39
A headless browser for AI agents that fetches modern web pages, runs JavaScript, manages sessions, and returns
Sqlite Graph Memory
Graph RAG on SQLite for AI agents: vector retrieval + hand-curated wikilink graph + cross-encoder rerank, with
Claude Light
claude_light.py is an interactive CLI chat tool for querying and editing a codebase using Claude. By combining
Nab
Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin
Pbi CLI
Power BI CLI - semantic models (.NET TOM) and PBIR reports for token-efficient AI agent usage, built for Claud
Atlassian Skills
Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassi
Related Agents
Backend RAG Specialist
Use for isolated server-side API, retrieval, and knowledge-base work in server/, especially route behavior, se
Pi Implementer
Implementation lane driven by the pi CLI (a local multi-provider coding agent, distinct from omp). Model-agnos
RAG Specialist
GAIA RAG and agentic-retrieval specialist. Use PROACTIVELY for RAG pipeline work, document indexing, embedding