GitEasy: Skill for Claude Code

.claude/skills/editorial-stance/SKILL.md

editorial-stance is a skill for Claude Code from greenmtnsun/GitEasy. It costs 103 tokens per session (1,212 once invoked), scanned A, original, MPL-2.0.

A writing policy for documentation generated from PowerShell metadata. It requires the renderer to show honest gaps instead of inventing descriptions or filling in missing information.

In plain words
What is it for?
Use it when changing renderers that produce Markdown or Confluence documentation from PowerShell metadata. It also applies when reviewing proposals to infer or fabricate missing content.
Why use it?
It keeps generated documentation trustworthy when the source data is incomplete. Readers can tell when the original module did not provide help rather than mistaking generated text for fact.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is greenmtnsun/GitEasy's own configuration. It tells Claude Code how to work on GitEasy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything GitEasy configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/editorial-stance/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/greenmtnsun/GitEasy

Made for: Claude Code.

Wrote 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.

agentmods badge for editorial-stance

README.md
[![agentmods](https://agentmods.dev/badge/skills/greenmtnsun/giteasy/editorial-stance/github.svg)](https://agentmods.dev/skills/greenmtnsun/giteasy/editorial-stance)
Your own site
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/editorial-stance"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/editorial-stance/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.

agentmods 80×15 button for editorial-stance

Your own site · 80×15
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/editorial-stance"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/editorial-stance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,212 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.01212
Opus 5.5 $0.00041 $0.00485
Sonnet 5.5 $0.00021 $0.00242
Haiku 4.5 $0.00010 $0.00121

Measured today against content hash f4388ddf6db9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

editorial-stance 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.

.claude/skills/editorial-stance/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

See also: software-creation §10 (vibe content listed in anti-patterns). module-suite for cross-product strategy and the editorial-stance summary line.

Editorial stance — anti-vibe

The Module Suite's renderers feed a public documentation site. Its value rests on one editorial choice: honest gaps over fabricated content. Every other PowerShell-docs site reposts Microsoft Learn or pads gaps with LLM noise. Keith's bet is that a smaller honest reference beats a larger plausible-sounding one.

This rule is machine-verified, not aspirational. ~30 Pester tests in C:\Sysadmin\Scripts\WikiEngine\Confluence\ConfluenceStorage.Tests.ps1 pin the three suppression behaviors below. A regression breaks the build.

The rule applies to harvested third-party content — module metadata Keith doesn't own. It does not constrain Keith's own comment-based help in his own modules; that's first-party content.


The three rules

1. Empty Description → "Note for Users" admonition

When a command's harvested Description is blank, whitespace, or absent, the renderer emits a labeled admonition stating the upstream module shipped without comment-based help. Never AI-author a description.

Markdown form (the working text — exact wording lives in the renderer):

> **Note for Users:** This command's upstream author did not include a description.
> The information shown here is harvested from PowerShell's reflection metadata; no
> hand-written description was available to render.

Confluence storage format: render the same content inside an info macro so the gap is visually distinct from authored prose:

<ac:structured-macro ac:name="info">
  <ac:rich-text-body><p>Note for Users: …</p></ac:rich-text-body>
</ac:structured-macro>

Future renderers (MCP output, second-language renderers) carry the same admonition in whatever form is idiomatic for that target.

2. Synopsis missing or duplicated → suppress the section

If Synopsis is absent, or if it's identical to Description (a common publisher anti-pattern of repeating the description), suppress the Synopsis section entirely. Don't fabricate a shorter version, don't truncate the description.

Read the full file on GitHub · 84 lines

Changes

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.

  1. today First seen · 84 lines · 103 tokens per session scan A f4388ddf6db9

Subscribe to this mod's changes

editorial-stance is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 103 tokens to every session and 1,212 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.

Related

editorial-stance compared with skills from other repositories

editorial-stance next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
editorial-stancegreenmtnsun/GitEasySkill1yesterdayMPL-2.0A103Claude Code
imagegenopenai/codexSkill136ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill101ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill395ktodayMITA36Claude Code
free-llm-apismnfst/awesome-free-llm-apisSkill14ktodayCC0-1.0A113Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill144ktodayMITA95Claude Code