lean-context

A plugin that condenses long project documentation into shorter context files for coding agents. Context files give an agent background information about a project.

In plain words
What is it for?
Use it to create concise, agent-focused project context from existing documentation.
Why use it?
Large documentation sets can be difficult for an agent to use efficiently and can bury the details needed for a task.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add asarnaout/lean-context
agentmods
npx agentmods add plugins/asarnaout/lean-context/marketplace
Clone the repo
git clone --depth 1 https://github.com/asarnaout/lean-context

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

lean-context scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 20 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "lean-context",
  "owner": {
    "name": "Ahmed Arnaout"
  },
  "plugins": [
    {
      "name": "lean-context",
      "source": "./plugins/lean-context",
      "description": "Distills verbose project documentation into terse, agent-optimized context files.",
      "version": "0.1.2",
      "author": {
        "name": "Ahmed Arnaout"
      },
      "category": "productivity"
    }
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 20 lines scan A 33dd203dcece

Subscribe to this mod's changes

lean-context is a plugin published in the GitHub repository asarnaout/lean-context (5 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other plugins, from other repositories

claude-code-skills

348 production-ready skill packages for Claude AI across 18 domains: engineering advanced (78, incl. v2.9.0 workflow-builder for Claude Code Workflow-tool authoring), engineering core (51), marketing (46 — incl. AEO/Answer Engine Optimization), c-level advisory (66), product (17), regulatory/QMS (18), compliance-os…

alirezarezvani/claude-skills · not measured

swarm-skill

Multi-agent codebase audit skill for Claude Code — spawns parallel subagents (security, performance, tests, architecture, dead-code) and synthesizes their findings into a prioritized action plan.

Zintellix/Claude-Skills · not measured

self-review

Review every code change before the turn ends: fresh-context reviewer agents, a verified finding standard, honest convergence, and a measured token budget — enforced by a Stop hook, graph-aware when you have a code graph, zero-cost when you don't.

HoussemDjeghri/self-review · not measured

claude-skills-marketplace

Plugin marketplace listing 23 plugins: golden-rules, agent-based-development, mvp-readiness, full-security-review, git-workflow.

RealDougEubanks/ClaudeMarketplace · not measured

claudeboss

Delegate tasks to free opencode agents from Claude Code — Team mode (pair review) or Boss mode (manage, approve, deploy).

xWael9/ClaudeBoss · not measured

claudeboss

Delegate tasks to free opencode agents and supervise them from Claude Code — Team mode (pair review) or Boss mode (manage, approve, deploy).

xWael9/ClaudeBoss · not measured