Lean Ctx logo

Lean Ctx

CommunityPopular
yvgude
lean-ctx

Pick the right lean-ctx tool for reading, searching, understanding and running code with fewer tokens and fewer round trips. Use when lean-ctx MCP tools (ctx_*) are available or when a command output, file read or search would be large.

Overview

Publisheryvgude
Repositorylean-ctx
Skill namelean-ctx
Stars
3.9K
Forks
351
Bundled files
11
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 11 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by yvgude on GitHub. Read the source before you install it.

Installation

Install the Lean Ctx AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yvgude/lean-ctx/tree/main/rust/src/templates
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yvgude/lean-ctx.git /tmp/lean-ctx
mkdir -p .claude/skills
cp -r /tmp/lean-ctx/rust/src/templates .claude/skills/lean-ctx
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lean Ctx in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lean Ctx on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lean Ctx is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

LeanCTX — Context Gateway for AI Systems

Control what your AI can see. LeanCTX Engine provides local context selection, supported access and content controls, and evidence of observed context operations for existing agents: Select → Control → Prove. Recovery depends on source or archive availability and access permissions. LeanCTX SDK is the separate integration surface for applications.

lean-ctx shapes context before it reaches you: cached reads, compressed shell output, focused search, recovery to exact source. Two rules beat every detail:

  1. Fewer round trips beat smaller outputs. One call that answers the question is cheaper than three small ones. Never add a call just to save a few hundred tokens.
  2. Never wait by polling. Do not loop sleep + status checks (see below).

Intent → tool

You want to…Call
Understand how something works (unknown location)ctx_compose(task) — ranked files + source in one call; use it FIRST instead of search→read→read
Find the exact definition of a symbolctx_search(action="symbol", name=…)
Find code by meaningctx_search(action="semantic", query=…)
Find a text/regex patternctx_search(pattern=…, path=…)
Who calls X / what calls X makes`ctx_callgraph(action="callers"
Read a file you will editctx_read(path, mode="anchored") → edit with ctx_patch, or the host's native edit tool
Read a file only for context`ctx_read(path, mode="signatures"
Re-check a file after editingctx_read(path, mode="diff")
Run a command (build, test, git, …)ctx_shell(command) — output is compressed
List files / directory shapectx_glob(pattern) / ctx_tree(path, depth)
Remember across sessions`ctx_session(action="finding"

Do not read or search through ctx_shell (cat, sed -n, grep, rg): that bypasses the read cache and symbol index. Use ctx_read / ctx_search.

Deferred tools (ToolSearch)

If the host lists lean-ctx tools by name only, load what the task needs in one call, e.g. select:mcp__lean-ctx__ctx_compose,mcp__lean-ctx__ctx_search,mcp__lean-ctx__ctx_read. Do not fall back to ctx_shell for everything because it happens to be loaded. A tool named here that your tool list lacks (the default profile shows a small core) is still callable: ctx_call(name="ctx_knowledge", arguments={…}). ctx_call(name="ctx_discover_tools", arguments={"query": "…"}) lists all of them.

Long-running commands

  • Prefer the host's own background execution that notifies on completion (Claude Code: Bash with run_in_background, or Monitor). Start it, then continue other work or end the turn — you will be told when it finishes.
  • ctx_shell(run_in_background=true) jobs do not notify by themselves. Check a job at most once when you actually need its result; never sleep in a loop.

Truncated output

Compressed or archived output ends with a recovery handle. Fetch only the slice you need: ctx_expand(id, search=… | head=N | json_path=…), or ctx_read(path, raw=true) for exact bytes. Do not re-run the command.

Without MCP (CLI)

bash
lean-ctx read <file> -m signatures    # or map | diff | lines:N-M
lean-ctx grep <pattern> [path]
lean-ctx -c "<command>"               # only where the shell is not already wrapped
lean-ctx raw "<command>"              # exact, uncompressed output

Setup

bash
which lean-ctx || curl -fsSL https://raw.githubusercontent.com/yvgude/lean-ctx/main/skills/lean-ctx/scripts/install.sh | bash
lean-ctx setup        # editor wiring, hooks, rules, this skill
lean-ctx doctor       # verify

Docs: https://leanctx.com/docs

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lean Ctx AI skill do?

Pick the right lean-ctx tool for reading, searching, understanding and running code with fewer tokens and fewer round trips. Use when lean-ctx MCP tools (ctx_*) are available or when a command output, file read or search would be large.

Why use Lean Ctx on TypingMind?

Because you install it once and use it with any model. Lean Ctx is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lean Ctx in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yvgude/lean-ctx/tree/main/rust/src/templates. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lean Ctx?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lean Ctx?

As many as you like. As long as a model supports skills, you can use Lean Ctx with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lean Ctx AI skill free?

Yes. It is published on GitHub by yvgude under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇