# vanenshi

> Open-source publisher. Listings imported from github.com/vanenshi — credited to the original author with their license.

- **Listings:** 3
- **Total installs:** 0
- **Profile:** https://agentstack.voostack.com/s/vanenshi
- **Website:** https://github.com/vanenshi

## Published listings

- [Plan Draft](https://agentstack.voostack.com/l/skill-vanenshi-skills-plan-draft) — Skill · Free · security-reviewed — `agentstack add skill-vanenshi-skills-plan-draft`
  Build a reviewed, execution-ready plan (no code) for a change, using Opus. Manually invoked with /plan-draft; writes one self-contained artifact under .claude/plans/ and delegates a cold review to the plan-critic agent (or the plan-review skill).
- [Plan Execute](https://agentstack.voostack.com/l/skill-vanenshi-skills-plan-execute) — Skill · Free · security-reviewed — `agentstack add skill-vanenshi-skills-plan-execute`
  Execute an approved plan from .claude/plans, openspec apply-loop style, with verification. Uses Sonnet.
- [Plan Review](https://agentstack.voostack.com/l/skill-vanenshi-skills-plan-review) — Skill · Free · security-reviewed — `agentstack add skill-vanenshi-skills-plan-review`
  Cold-review an implementation plan written by /plan-draft. Reads a plan file under .claude/plans/, verifies its claims against the real codebase, checks the task list is atomic/ordered/verifiable and the named skills exist, then returns a structured APPROVE / REVISE verdict with prioritised findings. Read-only — never edits the plan or any source file.

---
Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add <slug>`.