# 02 Implement

> Execute an implementation plan phase by phase via the implementer agent, iterating until 100% completeness.

- **Type:** Skill
- **Install:** `agentstack add skill-ai-driven-dev-framework-02-implement`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ai-driven-dev](https://agentstack.voostack.com/s/ai-driven-dev)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ai-driven-dev](https://github.com/ai-driven-dev)
- **Source:** https://github.com/ai-driven-dev/framework/tree/main/plugins/aidd-dev/skills/02-implement
- **Website:** https://www.ai-driven-dev.fr/

## Install

```sh
agentstack add skill-ai-driven-dev-framework-02-implement
```

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

## About

# Skill: implement

Run an existing technical plan to write code, validating each phase before moving on.

## Agent delegation

Spawn the `implementer` agent to execute this skill. For tools that do not support `context: fork` frontmatter: invoke the `implementer` agent explicitly with this skill's content as the prompt.

## Actions

```markdown
@actions/01-implement.md
```

## References

- `@references/blocked.md` - conditions that make a plan `blocked` (needs a human). All actions inherit it.

## Source & license

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

- **Author:** [ai-driven-dev](https://github.com/ai-driven-dev)
- **Source:** [ai-driven-dev/framework](https://github.com/ai-driven-dev/framework)
- **License:** MIT
- **Homepage:** https://www.ai-driven-dev.fr/

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-ai-driven-dev-framework-02-implement
- Seller: https://agentstack.voostack.com/s/ai-driven-dev
- 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%.