agentmods.dev

Acu: Skill for Claude Code

.claude/skills/acu-new/SKILL.md

acu-new is a skill for Claude Code from Acquiredl/Acu. It costs 72 tokens per session (8,647 once invoked), scanned A, original, MIT.

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.

In plain words
What is it for?
Use it to create a new domain-specific pipeline from a description, including its stages, tools, standards, constraints, boundaries, templates, and index entry.
Why use it?
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.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md.

This is Acquiredl/Acu's own configuration. It tells Claude Code how to work on Acu 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 Acu configures →

not rated 2repo 2mo ago A scan 72 tokens original MIT
View source ↗ Acquiredl/Acu
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.

agentmods badge for acu-new

README.md
[![agentmods](https://agentmods.dev/badge/skills/acquiredl/acu/acu-new/github.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/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 acu-new

Your own site · 80×15
<a href="https://agentmods.dev/skills/acquiredl/acu/acu-new"><img src="https://agentmods.dev/badge/skills/acquiredl/acu/acu-new.svg" alt="Reviewed on agentmods" width="80" 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.08647
Opus 5.5 $0.00029 $0.03459
Sonnet 5.5 $0.00014 $0.01729
Haiku 4.5 $0.00007 $0.00865

Measured 2mo ago against content hash d26ce6545b77, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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

  1. Read _templates/PLACEHOLDERS.md to understand all available template variables
  2. Read pipelines/CLAUDE.md to see existing pipelines and avoid naming collisions
  3. Read _templates/archetypes.yaml for domain archetype matching (Step 2.5)
  4. Read pipelines/_graveyard/LEARNINGS.md for generation-time warnings (Step 2.7)
  5. 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:

  1. 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.

  1. 2mo 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 2mo ago), licensed MIT. It adds 72 tokens to every session and 8,647 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 2026-08-31.

Planning
Related

acu-new compared with skills from other repositories

acu-new next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
acu-newAcquiredl/AcuSkill22mo agoMITA72Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code