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.
npx agentmods add skills/acquiredl/acu/acu-startnpx skills add Acquiredl/Acu --skill acu-startgit clone --depth 1 https://github.com/Acquiredl/AcuWrote 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.
[](https://agentmods.dev/skills/acquiredl/acu/acu-start)<a href="https://agentmods.dev/skills/acquiredl/acu/acu-start"><img src="https://agentmods.dev/badge/skills/acquiredl/acu/acu-start.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00083 | $0.01436 |
| Opus 5 | $0.00042 | $0.00718 |
| Sonnet 5 | $0.00017 | $0.00287 |
| Haiku 4.5 | $0.00008 | $0.00144 |
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 4d 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.
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:
- If the user specified a pipeline name, look for it under
pipelines/{name}/ - If not specified, check
ROUTES.yamlfor active pipelines and ask the user which one - Verify the pipeline exists and has both
.acu-meta.yamlandtemplates/intake.yaml
Step 2: READ — Load pipeline context
Read these files from the target pipeline:
.acu-meta.yaml— get unit naming (units.name,units.plural,units.directory), stages listtemplates/intake.yaml— understand all fields that need populatingtemplates/status.yaml— understand the status structure
Step 3: AUTO-ID — Determine the next unit ID
- List existing directories under
{pipeline}/{units.directory}/ - Extract numeric IDs from directory names (format:
{NNN}-{name}) - Auto-increment to the next available ID (zero-padded to 3 digits)
- 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):
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.
- 4d ago First seen · 149 lines · 83 tokens per session scan A b0f7e5685607
acu-start is a skill published in the GitHub repository Acquiredl/Acu (2 stars, last pushed 26d ago), licensed MIT. It adds 83 tokens to every session and 1,436 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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.
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…