# Verify

> Verify a change actually works by running it, not by inspecting it

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

## Install

```sh
agentstack add skill-hartbrook-staghorn-verify
```

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

## About

# Verify

Confirm that **{{target}}** actually works by running it and observing the
result — not by reading the code and assuming. A change is not done until it
has been verified.

Checks to run: **{{checks}}**

## How to Verify

1. **Discover the project's own commands.** Don't guess. Look at the files that
   declare them:
   - `package.json` scripts (`build`, `test`, `lint`), `Makefile` targets,
     `pyproject.toml` / `tox.ini`, `go.mod` (`go build ./...`, `go test ./...`),
     `Cargo.toml`, CI config (`.github/workflows/*`).
   - Read the project's docs where build/test steps are written in prose:
     `README.md`, `CONTRIBUTING.md`, `TESTING.md`, or a `docs/` equivalent.
     A documented command is authoritative — prefer it over one you infer.
   - Prefer the command the project already uses in CI over an ad-hoc one.

2. **Run the relevant checks** for `{{checks}}`:
   - `build` — compile or build the project.
   - `tests` — run the test suite (scope to the affected area when the full
     suite is slow, but say so).
   - `all` / `auto` — run build then tests; `auto` skips a step the project
     doesn't have rather than inventing one.

3. **Observe the actual output.** Read exit codes and the real test/build
   results. Passing means the command reported success — not that the code
   looks correct.

4. **If a check fails**, stop and report the failure with the actual output.
   Do not work around it silently or describe it as a minor issue.

## Reporting

Report only what you observed:

- **What ran** — the exact commands.
- **Result** — pass or fail, with the real output for any failure.
- **Not covered** — anything you could not verify (no test exists, couldn't run
  the app, environment missing), stated plainly.

Never claim a change works without having run something that demonstrates it.
If verification wasn't possible, say exactly what was and wasn't checked rather
than implying confidence you don't have.

## Source & license

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

- **Author:** [HartBrook](https://github.com/HartBrook)
- **Source:** [HartBrook/staghorn](https://github.com/HartBrook/staghorn)
- **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-hartbrook-staghorn-verify
- Seller: https://agentstack.voostack.com/s/hartbrook
- 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%.