GitEasy: Skill for Claude Code

.claude/skills/delivery-pipeline/SKILL.md

delivery-pipeline is a skill for Claude Code from greenmtnsun/GitEasy. It costs 174 tokens per session (3,823 once invoked), scanned A, original, MPL-2.0.

A staged process for taking project work from an initial idea through discovery, design, building, checking, documentation, release, and operation.

In plain words
What is it for?
Use it to scope new work, develop features, verify changes, document them, release them, and monitor what is running.
Why use it?
It prevents important delivery steps from being skipped when work moves quickly. Each stage points to the discipline or review needed for that part of the work.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

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/delivery-pipeline/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 delivery-pipeline

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/delivery-pipeline"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/delivery-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,823 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 $0.00174 $0.03823
Opus 5.5 $0.00070 $0.01529
Sonnet 5.5 $0.00035 $0.00765
Haiku 4.5 $0.00017 $0.00382

Measured today against content hash 38683b26baf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

delivery-pipeline 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.

The scan reads SKILL.md. This mod also ships 1 executable file (tests/run-scenarios.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/delivery-pipeline/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

See also: honest-completion + verify-claims-on-disk for the completion-claim discipline this pipeline assumes throughout. goal-author, dr-author, virtual-uml-architect, virtual-tester, code-review, virtual-security-reviewer, review-loop, ui-design-reviewer, run, release-qa-passes, virtual-compliance, blog-content-pipeline for the phases below — this skill sequences them, it doesn't replace them.

Delivery Pipeline

Keith's standing instruction, 2026-07-28: "this is bigger than my suite, I want it for every project now and future... I want it enforced in a way that new claudes aren't shocked." This skill is the always-visible, cross-project answer — it shows up in every session's skill list the same way software-creation or air-gap-discipline already do, regardless of which repo is open.

The seven phases

Each phase names the skill/tool that actually does the work — this skill's job is sequencing and making sure nothing gets silently skipped, not duplicating anyone's logic.

# Phase What happens Who does it
1 Discovery & Framing Plain description, why, done-means. Feasibility is a well-framed prompt at kickoff, not a formal stage. Compliance/legal is the existing /comp… skills or the legal persona directly — ask, don't formalize. goal-author
2 Design Architecture choices written down before code. Diagrams are the contract. When the project has a UI: mockups for every screen state, then a UI design review loop before Build starts. dr-author, virtual-uml-architect, ui-design-reviewer
3 Build Code, air-gap-clean, provenance-stamped. function-design/swarm-ready (PowerShell) or the stack's own equivalent convention, named explicitly
4 Verify Static analysis, unit, integration, code review loop, security review loop, visual UI walk, UI review loop (when there is a UI), adversarial input, performance/load, accessibility. No selective test strategy — see below. Release-cadence QA passes (test-suite audit per milestone, regression pack per release cut, SFDIPOT per new feature) — each run logs an evidence row in the ledger. compliancesuite, code-review, virtual-security-reviewer, ui-design-reviewer, run, release-qa-passes
5 Document Wikis (honest-gap stance), UML re-sync, blog post once it's real, changelog. wikimint-dogfood, blog-content-pipeline
6 Ship Cloud target, dev deploy, prod deploy — hard gate, see below. —
7 Operate Telemetry/observability, rollback plan, retro. The phase most pipelines forget. —

Read the full file on GitHub · 176 lines

Files

What ships with it

5 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.

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 · 176 lines · 0 tokens per session scan A 38683b26baf3

Subscribe to this mod's changes

delivery-pipeline is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 174 tokens to every session and 3,823 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.

Related

delivery-pipeline compared with skills from other repositories

delivery-pipeline next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
delivery-pipelinegreenmtnsun/GitEasySkill1yesterdayMPL-2.0A174Claude 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