Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/verify/TEMPLATE-verify-SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/greenmtnsun/giteasy/template-verify)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/template-verify"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/template-verify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/template-verify"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/template-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.00563 |
| Opus 5.5 | $0.00026 | $0.00225 |
| Sonnet 5.5 | $0.00013 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Verify
Copy this file to <repo>\.claude\skills\verify\SKILL.md, replace every <angle-bracket> field, and
delete this paragraph. Every section stays, even when its answer is "none".
Where to run from
Run everything below from <repo root, absolute path>. If the shell is anywhere else, say so and
move first (CLAUDE.md section 9).
Cheap checks first
In this order. Stop at the first failure.
- Static analysis:
<command>. Success looks like:<for example: 0 warnings, 0 errors>. - Build:
<command, or "none: PowerShell module">. Success looks like:<text>. - Unit tests:
<command, for example Tools\Invoke-<Prefix>Pester.ps1>. Success looks like:<for example: Passed: N Failed: 0>.
Boot
<How the product starts for a check. For a module: Import-Module .\<Name>.psd1 -Force. For a service: the local run command and the port. For a UI: the launcher and what window appears.>
Success looks like: <text>.
Drive one real flow
The flow a user would recognise, end to end:
<step><step><step>
Success looks like: <the observable result: output text, a status code, a file that now exists, a screenshot that shows X>.
Inspect
<what to read afterwards: a log path, a result object, a database row, a screenshot><what a regression would look like here>
Known slow or fragile parts
<Anything that takes more than a minute or needs a live environment, and what to do instead when it is not available. "None" is a valid answer.>
What this harness does not prove
<The honest limits. For example: PS 5.1 compatibility (only runs on 7), behaviour against a real AD, the installed-from-PSGallery path. These go in the Not verified block of the closeout.>
Trailer shape for this repo
Verified: <runner> N/N; verify: <flow name> on <target> saw <result>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 63 lines · 64 tokens per session scan A 97886ff6f294
verify is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 64 tokens to every session and 563 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-18.
verify compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| verifygreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 64 | Claude Code |
| create-verification-skillYeachan-Heo/oh-my-claudecode | Skill | 41k | today | MIT | A | 45 | Claude Code |
| verify-omnigentomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 100 | Claude Code, Codex |
| test-masterJeffallan/claude-skills | Skill | 12k | 2d ago | MIT | A | 104 | Claude Code |
| eval-dataset-designbojieli/ai-agent-book | Skill | 59k | 1mo ago | Apache-2.0 | A | 138 | Claude Code, Codex |
| dogfoodcallstack/agent-device | Skill | 5.4k | today | MIT | A | 55 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |