# Context Loading

> Load minimum necessary context into agent context windows. Prevents token bloat, reduces cost, and improves focus. Only load what the current task needs.

- **Type:** Skill
- **Install:** `agentstack add skill-developersglobal-ai-agent-skills-context-loading`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [DevelopersGlobal](https://agentstack.voostack.com/s/developersglobal)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [DevelopersGlobal](https://github.com/DevelopersGlobal)
- **Source:** https://github.com/DevelopersGlobal/ai-agent-skills/tree/main/skills/context-loading
- **Website:** https://developersglobal.github.io/ai-agent-skills/

## Install

```sh
agentstack add skill-developersglobal-ai-agent-skills-context-loading
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Overview

More context is not better context. Irrelevant context dilutes attention, increases cost, and slows inference. This skill enforces disciplined context loading: only the files, docs, and history that the current task requires.

## When to Use

- Before starting any complex agent task
- When designing system prompts for production agents
- When context windows are filling up

## Process

### Step 1: Identify Required Context

1. List the files/docs the agent needs to read to complete THIS specific task.
2. For each item, ask: *"Can the agent complete the task without this?"* If yes, don't include it.
3. Prioritize: system prompt → task definition → directly relevant code → supporting references.

**Verify:** Every item in context is directly necessary for the current task.

### Step 2: Summarize, Don't Dump

4. Long conversation history → summarize to key decisions and current state.
5. Large files → extract only the relevant functions/sections.
6. Entire docs → extract only the relevant sections.
7. Previous agent output → extract only the conclusions and next steps.

**Verify:** No item in context exceeds what's needed from that source.

### Step 3: Set Context Budgets

8. Define token allocation for each context section:
   - System prompt: ≤ 2,000 tokens
   - Task definition: ≤ 500 tokens
   - Code context: ≤ 4,000 tokens
   - Conversation history (summarized): ≤ 1,000 tokens
9. Stay well within model context limits (leave 30% buffer for output).

**Verify:** Total prompt fits within 70% of model context limit.

### Step 4: Refresh Context for New Tasks

10. Don't carry over context from a completed task to a new task.
11. Start each distinct task with a fresh, minimal context.
12. Re-introduce only what the new task genuinely needs.

## Verification

- [ ] Context items limited to task-required items only
- [ ] Long content summarized before inclusion
- [ ] Token budget defined and respected
- [ ] Context window at ≤70% capacity

## References

- [rag-and-memory skill](../rag-and-memory/SKILL.md)
- [multi-agent-orchestration skill](../multi-agent-orchestration/SKILL.md)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [DevelopersGlobal](https://github.com/DevelopersGlobal)
- **Source:** [DevelopersGlobal/ai-agent-skills](https://github.com/DevelopersGlobal/ai-agent-skills)
- **License:** MIT
- **Homepage:** https://developersglobal.github.io/ai-agent-skills/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-developersglobal-ai-agent-skills-context-loading
- Seller: https://agentstack.voostack.com/s/developersglobal
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.