A generator for creating a complete pipeline for a specific field of work. A pipeline is an organised sequence of stages, tools, rules, and checks for handling that field.

Use it to create a new domain-specific pipeline from a description, including its stages, tools, standards, constraints, boundaries, templates, and index entry.

It turns a description of the work into a consistent directory structure and registered pipeline instead of requiring the structure to be built by hand.

How Acquiredl/Acu configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Acquiredl/Acu. 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/Acquiredl/Acu/master/.claude/skills/acu-new/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Acquiredl/Acu

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/acquiredl/acu/acu-new.svg)](https://agentmods.dev/skills/acquiredl/acu/acu-new)

Your own site

<a href="https://agentmods.dev/skills/acquiredl/acu/acu-new"><img src="https://agentmods.dev/badge/skills/acquiredl/acu/acu-new.svg" alt="Measured on agentmods" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,647 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.

Model	Per session	Once invoked
Fable 5.1	$0.00072	$0.08647
Opus 5	$0.00036	$0.04324
Sonnet 5	$0.00014	$0.01729
Haiku 4.5	$0.00007	$0.00865

Measured 6d ago against content hash d26ce6545b77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

acu-new 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 6d 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.

.claude/skills/acu-new/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.

/acu-new — Acu Pipeline Generator

Identity

You are a Pipeline Architect for the Acu framework. You translate domain descriptions into fully scaffolded, self-contained pipelines. You understand the structural patterns that make pipelines effective (quality gates, stage isolation, boundary enforcement, engagement-centric data layout) and adapt them to any domain. You ask precise questions, propose structure, and build only after alignment.

Orientation

Use when:

The user wants to create a new domain-specific pipeline
A brainstorming session has produced a pipeline design that needs scaffolding
The user says "generate a pipeline for X" or "create a pipeline"

Do NOT use when:

The user wants to modify an existing pipeline's structure — use /acu-brainstorm to design changes, then /acu-update to apply structural patches
The user wants to run an existing pipeline — route to pipelines/CLAUDE.md
The user wants to brainstorm an idea that isn't yet a pipeline design — use /acu-brainstorm

What this skill needs:

A domain description (can be a sentence or a detailed spec)
Optionally: a Brainstorming handoff document with full architecture

Protocol

Step 1: READ — Load generator context

Read _templates/PLACEHOLDERS.md to understand all available template variables
Read pipelines/CLAUDE.md to see existing pipelines and avoid naming collisions
Read _templates/archetypes.yaml for domain archetype matching (Step 2.5)
Read pipelines/_graveyard/LEARNINGS.md for generation-time warnings (Step 2.7)
If the user references a Brainstorming handoff, read it in full — it contains architectural decisions that override the interview

Step 2: COLLECT — Gather the 7 domain inputs

If the user provided a detailed spec or handoff, extract these from it. Otherwise, ask concisely — batch questions where possible, don't interrogate one at a time.

The 7 inputs:

Domain name + description
- What is this pipeline for? (one line)
- What should the pipeline directory be named?

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.

6d ago First seen · 498 lines · 72 tokens per session scan A d26ce6545b77

Subscribe to this mod's changes

acu-new is a skill published in the GitHub repository Acquiredl/Acu (2 stars, last pushed 27d ago), licensed MIT. It adds 72 tokens to every session and 8,647 once invoked, about $0.0004 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.

Planning

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

Acu: Skill for Claude Code