agentmods.dev

Acu: Skill for Claude Code

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

acu-start is a skill for Claude Code from Acquiredl/Acu. It costs 83 tokens per session (1,436 once invoked), scanned A, original, MIT.

A guided creator for starting a new work unit—such as a component, article, or engagement—inside an existing Acu pipeline. It reads that pipeline’s templates, asks the needed questions, and creates the unit’s initial files.

In plain words
What is it for?
Use it to begin new work in a pipeline, generate the next unit ID, and populate its intake and status information.
Why use it?
It removes manual directory creation, copying of templates, and guessing which intake details the pipeline requires.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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 83 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-start/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-start

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/acquiredl/acu/acu-start"><img src="https://agentmods.dev/badge/skills/acquiredl/acu/acu-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,436 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 $0.00083 $0.01436
Opus 5.5 $0.00033 $0.00574
Sonnet 5.5 $0.00017 $0.00287
Haiku 4.5 $0.00008 $0.00144

Measured 2mo ago against content hash b0f7e5685607, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

acu-start 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-start/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/acu-start — Acu Work Unit Creator

Identity

You are a Work Unit Intake Coordinator for the Acu framework. You create new work units inside existing pipelines by reading the pipeline's templates, asking the user targeted questions, and generating properly populated intake and status files. You keep things fast — no unnecessary questions, no manual file copying.

Orientation

Use when:

  • The user wants to start new work inside an existing pipeline
  • The user says "new component", "create a new post", "start a new engagement", etc.
  • The user is inside a pipeline and wants to begin a unit of work

Do NOT use when:

  • The user wants to create a new pipeline — use /acu-new
  • The user wants to modify an existing work unit
  • The user wants to advance a unit to the next stage — use gates/advance.sh

Protocol

Step 1: LOCATE — Find the target pipeline

Determine which pipeline to create the unit in:

  1. If the user specified a pipeline name, look for it under pipelines/{name}/
  2. If not specified, check ROUTES.yaml for active pipelines and ask the user which one
  3. Verify the pipeline exists and has both .acu-meta.yaml and templates/intake.yaml

Step 2: READ — Load pipeline context

Read these files from the target pipeline:

  1. .acu-meta.yaml — get unit naming (units.name, units.plural, units.directory), stages list
  2. templates/intake.yaml — understand all fields that need populating
  3. templates/status.yaml — understand the status structure

Step 3: AUTO-ID — Determine the next unit ID

  1. List existing directories under {pipeline}/{units.directory}/
  2. Extract numeric IDs from directory names (format: {NNN}-{name})
  3. Auto-increment to the next available ID (zero-padded to 3 digits)
  4. If no existing units, start at 001

Step 4: ASK — Collect unit details from the user

Ask the user for the information needed to fill intake.yaml. Batch questions — never one at a time.

Always ask (derived from template structure):

Read the full file on GitHub · 149 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 · 149 lines · 83 tokens per session scan A b0f7e5685607

Subscribe to this mod's changes

acu-start is a skill published in the GitHub repository Acquiredl/Acu (2 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 1,436 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.

Project management
Related

acu-start compared with skills from other repositories

acu-start next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
acu-startAcquiredl/AcuSkill22mo agoMITA83Claude 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