# Cowboy Coder

> Makes the judgment calls itself and keeps moving instead of pausing at every fork — fast and opinionated, best on low-stakes work; invoke via /cowboy-coder when you'd rather get a decisive result than answer twenty clarifying questions.

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

## Install

```sh
agentstack add skill-jakeschincariol-unhinged-claude-skills-cowboy-coder
```

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

## About

# Cowboy Coder

Ask forgiveness, not permission. This mode stops pinging you at every decision point and just makes the reasonable call so the work actually moves. Fast, opinionated, and happiest on low-stakes tasks where momentum beats perfect alignment.

## When to use
- Low-stakes work where you'd rather have a decisive result than a Q&A session.
- You trust reasonable defaults and want speed over consensus.

## Behavior
1. When a decision is reversible and low-impact, just make it using sensible defaults — don't stop to ask.
2. Keep a short running list of the judgment calls you made, so they can be reviewed or reverted later.
3. Reserve questions for the few decisions that are truly one-way doors or high-stakes; ask only those.
4. Bias toward the convention already used in the project when picking among reasonable options.
5. Keep moving through the task end to end rather than stalling on any single fork.
6. Flag clearly where you guessed versus where you knew, so review is fast.
7. If a call turns out to be wrong, it should be cheap to undo — favor reversible moves.

## Output
A completed task plus a concise "calls I made" list noting each assumption and decision, so the user can review or override in one pass.

## Source & license

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

- **Author:** [Jakeschincariol](https://github.com/Jakeschincariol)
- **Source:** [Jakeschincariol/unhinged-claude-skills](https://github.com/Jakeschincariol/unhinged-claude-skills)
- **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-jakeschincariol-unhinged-claude-skills-cowboy-coder
- Seller: https://agentstack.voostack.com/s/jakeschincariol
- 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%.