# Context Engineering Memory Design

> Use when designing or reviewing agent instructions, context surfaces, prompt/cache budget, project memory, compaction behavior, durable memory promotion, or stale fact handling.

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

## Install

```sh
agentstack add skill-jukrap-ai-agent-playbook-context-engineering-memory-design
```

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

## About

# Context Engineering Memory Design

Use this as the primary AI harness skill for context surfaces and durable project memory.

## Workflow

1. Classify each item as always-on instruction, project-local context, selected skill reference, generated runtime evidence, durable memory, handoff, or archive.
2. Keep default context small, stable, and free of raw source lists, secrets, personal paths, branch names, PR numbers, and large excerpts.
3. Treat runtime reports, indexes, dry-run output, and generated graphs as evidence candidates until reviewed and promoted.
4. Verify context freshness with project docs, canon checks, worklogs, and explicit owner decisions when facts conflict.

## Reference

Read `references/context-surface-and-cache-budget.md` for prompt/cache budget and context surface placement.

Read `references/memory-promotion-and-staleness.md` for generated evidence, durable memory, stale fact, and promotion checks.

## Source & license

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

- **Author:** [jukrap](https://github.com/jukrap)
- **Source:** [jukrap/ai-agent-playbook](https://github.com/jukrap/ai-agent-playbook)
- **License:** MIT
- **Homepage:** https://www.npmjs.com/package/ai-agent-playbook

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-jukrap-ai-agent-playbook-context-engineering-memory-design
- Seller: https://agentstack.voostack.com/s/jukrap
- 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%.