GitEasy: Skill for Claude Code

.claude/skills/dr-author/SKILL.md

dr-author is a skill for Claude Code from greenmtnsun/GitEasy. It costs 81 tokens per session (852 once invoked), scanned A, original, MPL-2.0.

A method for recording a significant design choice before coding it. A Decision Record explains the options, the chosen approach, and the reason for choosing it.

In plain words
What is it for?
Use it for non-trivial PowerShell design decisions with several reasonable options or long-term consequences. It supports open, decided, and changed decisions across project phases.
Why use it?
It preserves the reasoning behind choices that may be difficult to reverse. Future developers can understand the original intent instead of guessing from the code.

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/dr-author/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 dr-author

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/dr-author"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/dr-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 852 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 $0.00081 $0.00852
Opus 5.5 $0.00032 $0.00341
Sonnet 5.5 $0.00016 $0.00170
Haiku 4.5 $0.00008 $0.00085

Measured today against content hash 360cebbd2db7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dr-author 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/dr-author/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

See also: software-creation §7 for the canonical DR format and Drift discipline. phase-gate for what happens to DRs at phase transitions.

Decision Record authoring

A Decision Record (DR) captures a non-trivial design choice in plain English so future Keith (and future Claude) can see the intent, the options weighed, and the choice made.

When to write a DR

Lean toward writing one when:

  • The choice has more than one defensible answer
  • The choice will be hard or expensive to reverse later
  • Future code will depend on the assumption being recorded
  • A reader looking at the code in 6 months would ask "why is this like this?"

Skip a DR when:

  • The choice is obvious from existing convention
  • The change is trivial / stylistic
  • The work is exploration / spike (write a DR after the spike if the path stays)

Before or after code?

Before, except when the choice only becomes clear after a small spike. The DR's value is forcing the design conversation; that conversation matters most when there's still time to take a different option.

Template

# Decision Record NNN — <Title>

## Status
OPEN | DECIDED (YYYY-MM-DD) | DECIDED · drift | OPEN · note

## Question
<one sentence>

## Context
<2–4 paragraphs: what's the situation, what's at stake>

## Options
**Option A — <name>**
- pros / cons
**Option B — <name>**
- pros / cons

## Decision
**<chosen option>.**
Rationale: <plain-English why>

## Blocks / Depends On
- <list>

## Owner
Keith Ramsey

## Phase
<project-defined — e.g. 0, 1, 2 or a feature-name; the phase model is the
project's own bookkeeping, not a global enumeration>

File location

  • One file per phase: Docs/DECISIONS_PHASE<N>.md
  • Big standalone decisions can have their own dedicated file
  • Index everything in Docs/DECISION_REGISTER.md with a status table + dependency graph

Status conventions

  • OPEN — under discussion, code not yet written
  • DECIDED (YYYY-MM-DD) — chosen; code can proceed
  • DECIDED · drift — code violates the contract; add a Drift Notice (see software-creation §7) and a recommended fix path
  • OPEN · note — partial implementation; add an Implementation Note explaining what ships today and what's missing
  • SUPERSEDED — replaced by a later DR; link to the replacement

Read the full file on GitHub · 96 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 · 96 lines · 81 tokens per session scan A 360cebbd2db7

Subscribe to this mod's changes

dr-author is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 81 tokens to every session and 852 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.

Related

dr-author compared with skills from other repositories

dr-author next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dr-authorgreenmtnsun/GitEasySkill1yesterdayMPL-2.0A81Claude 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