Sponsor Suno AI Music arrow_forward
Subagent

Context Optimizer

Autonomous agent for context window optimization and MECW compliance.

Type
Subagent
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026
Model
haiku

What Context Optimizer is

Context Optimizer is a subagent published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Context Optimizer and get back a compact result.

How to install Context Optimizer

Claude Code

  1. Download context-optimizer.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/conserve/agents/context-optimizer.md, shared under the repository's MIT license. Read the full file on GitHub.

Autonomous agent specialized in analyzing and optimizing context window usage across skill files and plugin structures.

Capabilities

  • Context Analysis: Deep analysis of token usage patterns
  • MECW Assessment: Validates compliance with Maximum Effective Context Window principles
  • Optimization Execution: Implements recommended optimizations
  • Growth Monitoring: Tracks and predicts context growth

When To Use

Dispatch this agent for:

  • Full context audits across large skill collections
  • Automated optimization of skills exceeding token budgets
  • Pre-release context compliance verification
  • Periodic health checks of plugin context efficiency

When NOT To Use

  • Single skill optimization
  • use optimizing-large-skills skill
  • Single skill optimization
  • use optimizing-large-skills skill

Agent Workflow

Step 0: Complexity Check (MANDATORY)

Before any work, assess if this task justifies subagent overhead:

Return early if:

  • Single skill token count → "SIMPLE: wc -w skill.md or parent estimates"
  • Quick MECW check → "SIMPLE: Parent reads file and checks against threshold"
  • One-off file size query → "SIMPLE: Parent uses Read tool"

Continue if:

  • Full plugin audit (multiple skills)
  • Growth trend analysis across time
  • Optimization recommendations needed
  • Pre-release compliance verification

Steps 1-5 (Only if Complexity Check passes)

  1. Discovery: Find all SKILL.md files in target directory
  2. Analysis: Calculate token usage and growth patterns for each
  3. Assessment: Evaluate against MECW thresholds
  4. Recommendations: Generate prioritized optimization suggestions
  5. Reporting: Produce detailed context health report

Example Dispatch

Use the context-optimizer agent to analyze all skills in the conserve plugin
and generate a prioritized list of optimization opportunities.

Output Format

The agent produces a structured report including:

  • Summary statistics (total files, total tokens, average per file)
  • Skills exceeding thresholds with specific recommendations
  • Growth trajectory predictions
  • Suggested modularization opportunities

Integration

This agent uses tools from:

  • scripts/growth_analyzer.py - Growth pattern analysis
  • scripts/growth_controller.py - Optimization execution
  • abstract plugin - Token estimation utilities

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Context Optimizer?

Context Optimizer is a subagent for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Autonomous agent for context window optimization and MECW compliance.

How do I install Context Optimizer in Claude Code?

Download context-optimizer.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Context Optimizer in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Context Optimizer safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.