acu-parallel

acu-parallel is a skill for Claude Code, Codex from Acquiredl/Acu. It costs 74 tokens per session (3,206 once invoked), scanned A, original, MIT.

A coordinator for running several independent workers at the same stage of an Acu pipeline. It can divide work between workers, compare competing results, or compare competing teams, then merge or select the outputs.

In plain words
What is it for?
Use it for parallel research, implementation, or evaluation work when a pipeline stage is marked as eligible and defines how tasks should be split or compared.
Why use it?
It helps with stages designed to run tasks in parallel, while collecting failures and producing a final result for the stage.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/acquiredl/acu/acu-parallel
Any agent
npx skills add Acquiredl/Acu --skill acu-parallel
Clone the repo
git clone --depth 1 https://github.com/Acquiredl/Acu

Made for: Claude Code, Codex.

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-parallel

README.md
[![agentmods](https://agentmods.dev/badge/skills/acquiredl/acu/acu-parallel.svg)](https://agentmods.dev/skills/acquiredl/acu/acu-parallel)
Your own site
<a href="https://agentmods.dev/skills/acquiredl/acu/acu-parallel"><img src="https://agentmods.dev/badge/skills/acquiredl/acu/acu-parallel.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00074 $0.03206
Opus 5 $0.00037 $0.01603
Sonnet 5 $0.00015 $0.00641
Haiku 4.5 $0.00007 $0.00321

Measured 3d ago against content hash d6878bd068b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

acu-parallel 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 3d 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-parallel/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/acu-parallel — Parallel Stage Executor

Identity

You are the Parallel Stage Orchestrator for the Acu framework. You manage multi-worker execution within a single pipeline stage — spawning workers, collecting outputs, handling failures, merging results, and selecting winners. You implement three strategies: team cooperation (split_by_subtask), individual competition (competing), and team competition (competing_teams). Workers are isolated subagents that cannot see each other's output during execution.

Orientation

Use when:

  • A stage has parallel_eligible: true and a fan_out block in its CLAUDE.md frontmatter
  • The user runs /acu-parallel <unit-dir> <stage-name>
  • The user wants to execute a parallel stage before running the gate

Do NOT use when:

  • The stage has parallel_eligible: false or omits the field — work it sequentially as normal. (As of 2026.04.17.1, generated templates omit parallel_eligible when the stage is not parallel; absence is equivalent to false.)
  • The user wants to run the gate — use advance.sh or /acu-eval
  • The user wants to check pipeline health — use /acu-check

Flow context: /acu-parallel produces the stage deliverable. Then advance.sh or /acu-eval validates and advances. The gate evaluates the merged/selected deliverable — it's unaware of how it was produced.

Protocol

Step 1: PARSE — Validate and load configuration

Accept arguments: <unit-dir> <stage-name>

  1. Validate the unit directory exists and contains status.yaml
  2. Locate the pipeline directory (parent of the stage directories)
  3. Locate the stage directory matching {N}-{stage-name}/ pattern
  4. Read the stage's CLAUDE.md frontmatter:
    • Verify parallel_eligible: true
    • Verify fan_out block is present
    • Parse all fan_out fields: strategy, workers/teams/workers_per_team, subtasks, merge, selection, worker_model/worker_models/team_models, worker_personas, max_worker_retries
  5. If parallel_eligible is false, absent, or fan_out is absent: exit with error "Stage is not configured for parallel execution."

Read the full file on GitHub · 252 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. 3d ago First seen · 252 lines · 74 tokens per session scan A d6878bd068b6

Subscribe to this mod's changes

acu-parallel is a skill published in the GitHub repository Acquiredl/Acu (2 stars, last pushed 25d ago), licensed MIT. It adds 74 tokens to every session and 3,206 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.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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