arch-pipeline

arch-pipeline is a skill for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 95 tokens per session (4,024 once invoked), scanned A, original, MIT.

A complete workflow for creating architecture documentation: decisions, research, context gathering, document generation, and audits. It covers Architecture Decision Records, High-Level Designs, and Low-Level Designs, with support for multiple designs per system or subsystem.

In plain words
What is it for?
Use it to run an end-to-end documentation process from a technical topic through ADRs, HLDs, and LLDs, or resume a saved workflow.
Why use it?
It coordinates the stages and preserves progress, so complex architecture work can continue without mixing research and document-writing context.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the architecture-docs plugin — 19 skills shipped together

Good fit Use it to run an end-to-end documentation process from a technical topic through ADRs, HLDs, and LLDs, or resume a saved workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/googilyboogily/googilyboogily-claude-power-tools/arch-pipeline
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.

Any agent
npx skills add GoogilyBoogily/googilyboogily-claude-power-tools --skill arch-pipeline
Clone the repo
git clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install architecture-docs, the plugin that ships this one along with the rest of its 19 skills.

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 arch-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/arch-pipeline/github.svg)](https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/arch-pipeline)
Your own site
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/arch-pipeline"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/arch-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 arch-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/arch-pipeline"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/arch-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,024 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 $0.00095 $0.04024
Opus 5 $0.00048 $0.02012
Sonnet 5 $0.00019 $0.00805
Haiku 4.5 $0.00010 $0.00402

Measured 12d ago against content hash 97ce4328a1d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

arch-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 12d 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/architecture-docs/skills/arch-pipeline/SKILL.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Documentation Pipeline

Run the complete ADR → HLD(s) → LLD(s) pipeline with context isolation, state persistence, quality audits, and context-clearing prompts. Each phase (discuss, research, gather, generate, audit) runs in its own forked context. The orchestrator tracks file paths, decisions, and verdicts — it never reads document content.

One ADR can produce multiple HLDs (one per subsystem), and each HLD can produce multiple LLDs (one per component). Single-document is the default — fan-out is opt-in.

Input

$ARGUMENTS — the decision topic (e.g., "migrate from REST to GraphQL") or --resume to continue from saved state.

Pipeline Overview

Phase 1:   ADR Discuss     → decisions file
Phase 2:   ADR Research    → RESEARCH.md
Phase 3:   ADR Gather      → context file (compiles from 1+2)
Phase 4:   ADR Generate    → ADR document
Phase 5:   ADR Audit       → audit report

CHECKPOINT — HLD Scoping + Context Clear Prompt

FOR EACH HLD [i]:
  Phase 6-i:  HLD Discuss   → decisions file
  Phase 7-i:  HLD Research  → RESEARCH.md
  Phase 8-i:  HLD Gather    → context file
  Phase 9-i:  HLD Generate  → HLD document
  Phase 10-i: HLD Audit     → audit report

  CHECKPOINT — LLD Scoping + Context Clear Prompt

  FOR EACH LLD [j]:
    Phase 11-i-j: LLD Discuss   → decisions file
    Phase 12-i-j: LLD Research  → RESEARCH.md
    Phase 13-i-j: LLD Gather    → context file
    Phase 14-i-j: LLD Generate  → LLD document
    Phase 15-i-j: LLD Audit     → audit report

Pipeline Complete — tree summary + implement option

Every phase skill runs with context: fork — the orchestrator stays lean, tracking only file paths, decisions, and verdicts.

Process

State Tracking

Maintain these variables throughout the pipeline:

ADR (single):

  • $ADR_DECISIONS_PATH — decisions file from discuss
  • $ADR_RESEARCH_PATH — research file
  • $ADR_CONTEXT_PATH — compiled context file
  • $ADR_PATH — generated ADR document
  • $ADR_AUDIT_VERDICT — PASS / PASS WITH WARNINGS / FAIL

Read the full file on GitHub · 498 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. 12d ago First seen · 498 lines · 95 tokens per session scan A 97ce4328a1d9

Subscribe to this mod's changes

arch-pipeline is a skill published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 4,024 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens