# Relay10 Build

> Implement an authorized repository change in small, verifiable slices. Use after scope and acceptance criteria are clear; do not use for diagnosis-only, review-only, or publication-only requests.

- **Type:** Skill
- **Install:** `agentstack add skill-minwoo19930301-relay10-relay10-build`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [minwoo19930301](https://agentstack.voostack.com/s/minwoo19930301)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [minwoo19930301](https://github.com/minwoo19930301)
- **Source:** https://github.com/minwoo19930301/relay10/tree/main/plugins/relay10/skills/relay10-build

## Install

```sh
agentstack add skill-minwoo19930301-relay10-relay10-build
```

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

## About

# DisciplinedRun Build

Apply the approved change while keeping evidence and rollback obvious.

## Before editing

1. Reconfirm the requested outcome, allowed mutations, and acceptance checks.
2. Inspect the worktree and preserve unrelated user changes.
3. Identify the smallest vertical slice that demonstrates progress.
4. Add or update a failing test first when the behavior is testable and the test adds useful protection.

Do not force test-first mechanics for generated artifacts, trivial text edits, or behavior that is better verified by a deterministic validator. Record why when no test is appropriate.

## Implementation loop

1. Make one coherent change.
2. Run the narrowest relevant check.
3. Inspect the diff and unintended file changes.
4. Continue only when the slice is understood.
5. Run the broader regression set in proportion to risk.

Use structured argv and safe APIs rather than shell interpolation for untrusted values. Keep optional adapters and surfaces outside the core when possible.

## Completion evidence

Report:

- files changed and why;
- tests or validators run with actual exit status;
- user-visible result;
- remaining risks or unsupported paths;
- rollback or revert point.

Do not claim completion from code inspection alone when executable verification is available. Do not commit, push, publish, tag, deploy, or send external messages unless the user authorized that action.

## Source & license

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

- **Author:** [minwoo19930301](https://github.com/minwoo19930301)
- **Source:** [minwoo19930301/relay10](https://github.com/minwoo19930301/relay10)
- **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-minwoo19930301-relay10-relay10-build
- Seller: https://agentstack.voostack.com/s/minwoo19930301
- 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%.