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/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/verify)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/verify"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/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/verify"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/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 | $0.00165 | $0.01818 |
| Opus 5.5 | $0.00066 | $0.00727 |
| Sonnet 5.5 | $0.00033 | $0.00364 |
| Haiku 4.5 | $0.00016 | $0.00182 |
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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
honest-completionfor the closeout a reply must carry,verify-claims-on-diskfor checking another session's claims,release-qa-passesfor release-cadence passes,review-loopfor the review that runs after verification. The built-inrunskill is the fallback launcher when a repo has no verify skill yet.
Verify
Verification means running the change, not reading it. Keith adopted the Claude Code team's
practice on 2026-11-17: every repo carries a verify skill that boots the product, drives one real
flow and inspects the result; Claude runs it before every commit; the commit says how it was checked.
With that in place the human's job moves from reading every diff to defining what done looks like and
reading the evidence.
Where it lives
| What | Where |
|---|---|
| The contract (this file) | C:\Users\keith\.claude\skills\verify\SKILL.md |
| The template for a repo's own skill | C:\Users\keith\.claude\skills\verify\TEMPLATE-verify-SKILL.md |
| The diff-triggered checklist | C:\Users\keith\.claude\skills\verify\Get-DiffTriggeredChecks.ps1 |
| A repo's own verify skill | <repo>\.claude\skills\verify\SKILL.md, as close to the code as it can be |
| The commit gate | C:\Users\keith\.claude\hooks\commit-verify-gate.ps1, mode in commit-verify-gate.mode |
The procedure, every time
- Find the repo's verify skill. Read
<repo>\.claude\skills\verify\SKILL.md. If there is none, author one now from the template, in the same commit as the work. A missing harness is a work item, not a reason to skip (CLAUDE.md section 14). Until it exists, the built-inrunskill launches the app. - Cheap checks first. Static analysis, build, unit tests, in that order, from the directory the repo's skill names. Stop at the first failure and fix it before anything slower runs.
- Run the repo's smoke test. Boot the product the way the skill says, drive the one real flow it
names, inspect what it says to inspect. For a PowerShell module that is import, run
Tools\Invoke-*Pester.ps1, then run one public command against a real target. For a UI it is the UI gate with a screenshot. For a service it is a real request to the real path with the status code shown. - Run the diff-triggered checklist. From the repo root:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 117 lines · 0 tokens per session scan A e0cdb75a958d
verify is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 165 tokens to every session and 1,818 once invoked, about $0.0007 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 | 165 | 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 |