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/compliance-checklist/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/compliance-checklist)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/compliance-checklist"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/compliance-checklist/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/compliance-checklist"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/compliance-checklist.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 | $0.00108 | $0.01692 |
| Opus 5.5 | $0.00043 | $0.00677 |
| Sonnet 5.5 | $0.00022 | $0.00338 |
| Haiku 4.5 | $0.00011 | $0.00169 |
Grade A, and why
compliance-checklist 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
feedback_suite_security_barmemory for the why + three-phase adoption plan.function-designfor the parameter/pipeline/output contract.software-creation§4 for the structured-result-with-CategoryInfo+TargetObject rule.virtual-security-reviewerfor adversarial review when the cmdlet handles untrusted input or credentials.
Compliance Checklist — operator-side PR gate
The canonical content lives in C:\Users\keith\.claude\cross-project-artifacts\SUITE-PR-GATE.md. This skill is the operational layer that surfaces the right sections at the right time, in plain English, when a cmdlet is being authored or modified.
When this skill triggers
- A new function is being created in any
Public/folder underC:\Sysadmin\Scripts\. - An existing public cmdlet is being modified in a way that changes parameters, error paths, or credential handling.
- Keith says "PR-gate this", "compliance-check", "is this ready to merge", "walk the checklist".
- Before declaring a Phase transition in any project (per
phase-gateskill) — the closing phase's cmdlets get walked.
How to use it
The skill walks the checklist by section relevance, not by reading the whole doc. For each cmdlet under review, pick the sections that apply:
| Section | Applies when | Cmdlets where this bites |
|---|---|---|
| A. Input handling | Any cmdlet with parameters | All |
| B. T-SQL composition | Cmdlet builds T-SQL | SqlBackupValidation, SqlSpnManager, eventual IDKSqlServer2025 only |
| C. Credential handling | Cmdlet accepts or produces secrets | Set-Token, Set-Ssh, Set-Vault (GitEasy); any cmdlet returning a connection |
| D. Transport security | Cmdlet opens network connections | Get-Updates, Save-Work (GitEasy); WikiEngine REST; PesterForge Anthropic calls |
| E. Process / shell invocation | Cmdlet runs external commands | Invoke-GEGit (GitEasy); ClusterValidator's CIM/WMI shellouts; PhotoOrganizer Python bridge |
| F. Privilege | Cmdlet performs surprising or privileged actions | All Set- / New- / Remove- |
| G. Error handling and info disclosure | All cmdlets | All |
| H. Idempotency and state | Set-/Enable-/Disable-/New-/anything that writes |
All write-side cmdlets |
| I. Resource bounds | Cmdlet opens a connection, makes an HTTP call, or polls | All network-touching cmdlets |
| J. Audit | State-changing cmdlet | All Set-/New-/Remove-/Enable-/Disable- |
| K. Tests | All | All |
| L. Documentation | All public cmdlets | All public |
| M. Untrusted JSON/XML deserialization (CWE-502 gap section) | Cmdlet calls ConvertFrom-Json / Import-Clixml on input that came from a network, file, or another process |
PesterForge (Anthropic responses), WikiEngine (Confluence REST), any cmdlet reading user-supplied JSON config |
| N. Internal-network URL targets (CWE-918 gap section) | Cmdlet accepts a URL parameter and fetches it | Any cmdlet that takes a -Url / -Endpoint / -Uri and calls Invoke-RestMethod / Invoke-WebRequest |
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 · 89 lines · 108 tokens per session scan A 78e9b449c19d
compliance-checklist is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 108 tokens to every session and 1,692 once invoked, about $0.0004 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.
compliance-checklist compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compliance-checklistgreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 108 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.6k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 961 | today | MIT | A | 84 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.5k | 3d ago | MIT | A | 51 | Claude Code, Codex |
| explore-unknownsdzhng/skills | Skill | 1.5k | 5d ago | MIT | A | 162 | Claude Code, Codex |
| asplos-writing-stylebrycewang-stanford/Awesome-Journal-Skills | Skill | 1.4k | 1mo ago | MIT | A | 65 | Claude Code |