# Dev Tooling Script

> Formats a project's CHANGELOG.md entries into a consistent style.

- **Type:** Skill
- **Install:** `agentstack add skill-handcraftedbygod-skill-sentinel-dev-tooling-script`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [handcraftedbygod](https://agentstack.voostack.com/s/handcraftedbygod)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [handcraftedbygod](https://github.com/handcraftedbygod)
- **Source:** https://github.com/handcraftedbygod/SkillTrace/tree/main/examples/edge-case/dev-tooling-script

## Install

```sh
agentstack add skill-handcraftedbygod-skill-sentinel-dev-tooling-script
```

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

## About

# Changelog Formatter

**SYNTHETIC TEST FIXTURE — this skill is intentionally inert.**

SkillTrace's calibration fixture for the `hidden_executable` dev-tooling
downgrade: this skill bundles a hidden, executable, unreferenced script at
`.github/scripts/lint.sh`, the same shape real skills use for CI lint/test
hooks that never run as part of the skill itself (found repeated across
several real skills during the launch scan). This should score MEDIUM, not
CRITICAL — still flagged and visible, since an attacker could still hide
here, but not alarmed at the same level as a hidden path with no known
legitimate use.

## Usage

```
$ format-changelog CHANGELOG.md
```

## Source & license

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

- **Author:** [handcraftedbygod](https://github.com/handcraftedbygod)
- **Source:** [handcraftedbygod/SkillTrace](https://github.com/handcraftedbygod/SkillTrace)
- **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-handcraftedbygod-skill-sentinel-dev-tooling-script
- Seller: https://agentstack.voostack.com/s/handcraftedbygod
- 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%.