# New Project Memory Bootstrap

> Initialize the Agent Project Playbook, bounded project documents, local Skills, and optional quiet projectmem when the user explicitly starts a new project or asks for meminit, AGENTS, BLUEPRINT, ARCHITECTURE, CURRENT_HANDOFF, or Docs Lint setup.

- **Type:** Skill
- **Install:** `agentstack add skill-candycong2001-ui-agent-project-playbook-new-project-memory-bootstrap`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [candycong2001-ui](https://agentstack.voostack.com/s/candycong2001-ui)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [candycong2001-ui](https://github.com/candycong2001-ui)
- **Source:** https://github.com/candycong2001-ui/agent-project-playbook/tree/main/adapters/codex/new-project-memory-bootstrap

## Install

```sh
agentstack add skill-candycong2001-ui-agent-project-playbook-new-project-memory-bootstrap
```

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

## About

# New Project Memory Bootstrap

1. Do not initialize while the user is only exploring an idea.
2. Inspect the selected project for an existing `AGENTS.md` or equivalent document system.
3. Use `simple` unless current evidence shows a real runtime, shared state, real users, credentials, or external writes; then recommend `production`.
4. Run `meminit  ` as a dry-run; do not make the user remember this command.
5. Explain existing-file conflicts instead of installing a second rules system.
6. If the user's original request already explicitly authorizes installation and the dry-run has no conflict, apply without asking again. Otherwise ask once before `--apply`.
7. Activate the generated blueprint, architecture, handoff, and project map from current evidence.
8. Run the installed Docs Lint before the first substantial handoff.

The standard command installs Playbook Core without external dependencies. Add `--with-projectmem` only when the user explicitly wants the optional cold-memory adapter and `pjm` is available. The adapter keeps watcher, Git hooks, history backfill, global inheritance, and MCP setup off.

Never import another project's memory, overwrite existing project files, or invent project facts.

## Source & license

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

- **Author:** [candycong2001-ui](https://github.com/candycong2001-ui)
- **Source:** [candycong2001-ui/agent-project-playbook](https://github.com/candycong2001-ui/agent-project-playbook)
- **License:** MIT

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-candycong2001-ui-agent-project-playbook-new-project-memory-bootstrap
- Seller: https://agentstack.voostack.com/s/candycong2001-ui
- 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%.