Verify
Verify a change actually works by running it, not by inspecting it
Install
$ agentstack add skill-hartbrook-staghorn-verify ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-hartbrook-staghorn-verify) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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
- Discover the project's own commands. Don't guess. Look at the files that
declare them:
package.jsonscripts (build,test,lint),Makefiletargets,
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.
- 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;autoskips a step the project
doesn't have rather than inventing one.
- 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.
- 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
- Source: HartBrook/staghorn
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.