# Mega Context Manager

> Manages large context windows via chunking, summarization, and retrieval. Use for: manage context, too much context, chunk document, context budget.

- Skill: `stijnman/mega-context-manager` (Agent Skill)
- Install (CLI): `npx skillmds@latest add stijnman/mega-context-manager`
- Raw SKILL.md: https://api.skillmd.com/api/skills/stijnman/mega-context-manager/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Finance & Business
- License: MIT
- Author: Stijnman (https://skillmd.com/u/stijnman)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/stijnman/mega-context-manager

---

# Mega Context Manager
## When to Use

- User says **manage context** or task matches this capability
- User says **too much context** or task matches this capability
- User says **chunk document** or task matches this capability
- User says **context budget** or task matches this capability

## Workflow

1. Measure token estimate of inputs.
2. If over budget: chunk, summarize chunks, index.
3. Retrieve relevant chunks per subtask only.
4. Drop stale chunks after task completion.

## Integrations

- `semantic-memory-manager`
- `predictive-cache-manager`
- `persistent-memory-bridge`

## Error Handling

| Failure | Response |
|---------|----------|
| Retrieval miss | Expand query; include adjacent chunks. |

## Gotchas

- Summaries lose detail; keep raw chunks for citation.

## Example

**Input:** User request matching triggers above.
**Output:** Structured result per workflow with integrations invoked as needed.