pipeline-spec

pipeline-spec is a command for Claude Code from sponticelli/gamedev-claude-plugins. It costs 13 tokens per session (766 once invoked), scanned A, original, MIT.

A command that writes a specification for a CI/CD pipeline, the automated process that builds, tests, and delivers software. It adapts the plan to the game engine, target platforms, repository setup, team workflow, and chosen CI service.

In plain words
What is it for?
Use it to plan pipelines for pushes, pull requests, releases, nightly runs, and manual deployments, while documenting the current setup, constraints, and build goals.
Why use it?
It turns a project's development and release needs into defined triggers, builds, tests, and deployment steps instead of leaving the process ad hoc.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the devops plugin — 6 commands, 6 agents shipped together

Good fit Use it to plan pipelines for pushes, pull requests, releases, nightly runs, and manual deployments, while documenting the current setup, constraints, and build goals.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sponticelli/gamedev-claude-plugins/pipeline-spec
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/sponticelli/gamedev-claude-plugins

Made for: Claude Code.

Or install devops, the plugin that ships this one along with the rest of its 6 commands, 6 agents.

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 pipeline-spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/sponticelli/gamedev-claude-plugins/pipeline-spec/github.svg)](https://agentmods.dev/commands/sponticelli/gamedev-claude-plugins/pipeline-spec)
Your own site
<a href="https://agentmods.dev/commands/sponticelli/gamedev-claude-plugins/pipeline-spec"><img src="https://agentmods.dev/badge/commands/sponticelli/gamedev-claude-plugins/pipeline-spec/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 pipeline-spec

Your own site · 80×15
<a href="https://agentmods.dev/commands/sponticelli/gamedev-claude-plugins/pipeline-spec"><img src="https://agentmods.dev/badge/commands/sponticelli/gamedev-claude-plugins/pipeline-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 766 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 $0.00013 $0.00766
Opus 5 $0.00006 $0.00383
Sonnet 5 $0.00003 $0.00153
Haiku 4.5 $0.00001 $0.00077

Measured 9d ago against content hash 5e5260024b86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pipeline-spec 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 9d ago.

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.

plugins/devops/commands/pipeline-spec.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI/CD Pipeline Specification Generator

Generate a comprehensive CI/CD pipeline specification tailored to the project's needs.

Context Gathering

Before generating, understand:

Project Context

  • Game engine (Unity/Unreal/Godot/Custom)
  • Target platforms (PC, Console, Mobile, Web)
  • Repository structure (monorepo, multi-repo)
  • Team size and workflow (trunk-based, git flow)

CI Platform

  • GitHub Actions, GitLab CI, Jenkins, Azure DevOps, etc.
  • Runner availability (hosted vs self-hosted)
  • Budget constraints

Current State

  • Existing CI/CD (if any)
  • Pain points to address
  • Build time targets

Output Format

# CI/CD Pipeline Specification: [Project Name]

## Overview
**CI Platform:** [Platform]
**Engine:** [Engine]
**Platforms:** [Target platforms]
**Workflow:** [Branching strategy]

## Pipeline Triggers

| Event | Pipeline | Purpose |
|-------|----------|---------|
| Push to main | Full build + deploy | Production releases |
| Pull request | Quick build + tests | PR validation |
| Tag v*.*.* | Release pipeline | Version releases |
| Schedule (nightly) | Full test suite | Comprehensive testing |
| Manual | Deploy to [env] | On-demand deployment |

## Pipeline Stages

### Stage 1: Validation
**Duration:** ~2-3 minutes
**Runs on:** [Runner type]
```yaml
steps:
  - lint
  - format-check
  - license-check

Stage 2: Build

Duration: ~[X] minutes Runs on: [Runner type]

Platform Matrix
Platform Runner Artifacts
Windows windows-latest game-win64.zip
macOS macos-latest game-osx.dmg
Linux ubuntu-latest game-linux.tar.gz
WebGL ubuntu-latest game-webgl.zip

Stage 3: Test

Duration: ~[X] minutes

parallel:
  - unit-tests
  - integration-tests

Stage 4: Deploy

Environments: [dev, staging, production]

conditions:
  - dev: auto on develop
  - staging: auto on main
  - production: manual approval

Caching Strategy

Cache Key Pattern Size Estimate
Unity Library unity-${{ hashFiles('**/Packages/') }} ~2GB
node_modules npm-${{ hashFiles('**/package-lock.json') }} ~500MB

Secrets Required

Secret Purpose Scope
STEAM_USERNAME Steam deployment deploy jobs
SIGNING_CERT Code signing build jobs

Environment Configuration

Environment URL Protection
Development dev.example.com None
Staging staging.example.com None
Production example.com Required reviewers

Performance Targets

Metric Target
PR feedback < 10 minutes
Full build < 30 minutes
Deploy time < 5 minutes

Estimated Costs

Resource Monthly Estimate
CI minutes $[X]
Storage $[X]
Runners $[X]

Read the full file on GitHub · 132 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. 9d ago First seen · 132 lines · 13 tokens per session scan A 5e5260024b86

Subscribe to this mod's changes

pipeline-spec is a command published in the GitHub repository sponticelli/gamedev-claude-plugins (15 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 766 once invoked, about $0.0001 per session on Opus 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 2026-08-30.