ooo

ooo is a skill for Claude Code from SoliEstre/EstreGenesis. It costs 96 tokens per session (1,112 once invoked), scanned A, original, Apache-2.0.

A workflow for continuing independent work when a question comes up during a task. It records unanswered questions on a small scoreboard and resolves or bypasses them where possible.

In plain words
What is it for?
Use it to turn the workflow on or off, view the question scoreboard, or run one task with questions tracked out of order.
Why use it?
It prevents the whole task from stopping while waiting for an answer to a question that does not affect every part of the work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the superscalar plugin — 5 skills shipped together

Good fit Use it to turn the workflow on or off, view the question scoreboard, or run one task with questions tracked out of order.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soliestre/estregenesis/ooo
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.

Any agent
npx skills add SoliEstre/EstreGenesis --skill ooo
Clone the repo
git clone --depth 1 https://github.com/SoliEstre/EstreGenesis

Made for: Claude Code.

Or install superscalar, the plugin that ships this one along with the rest of its 5 skills.

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 ooo

README.md
[![agentmods](https://agentmods.dev/badge/skills/soliestre/estregenesis/ooo.svg)](https://agentmods.dev/skills/soliestre/estregenesis/ooo)
Your own site
<a href="https://agentmods.dev/skills/soliestre/estregenesis/ooo"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/ooo.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,112 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00096 $0.01112
Opus 5 $0.00048 $0.00556
Sonnet 5 $0.00019 $0.00222
Haiku 4.5 $0.00010 $0.00111

Measured 7d ago against content hash e6e08317f8b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ooo 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 7d 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.

plugins/superscalar/skills/ooo/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ooo — question-scoreboard execution (비순차실행)

Superscalar §2 reorders sub-agent lanes around data hazards. The main lane itself still stalls on its most common hazard: a question to the human. Ask-and-wait is an in-order pipeline with one very slow operand — and human response latency is this module's founding bottleneck. /ooo gives the main lane's questions the same treatment the lanes already get: a blocked item waits; the queue does not.

Normative spec: Superscalar.md §5.3. This skill is the procedure.

1. Toggle contract

  • State = one marker file: .agent/ooo.json{"on": true}. Absent ⇒ off. No mirrors (§5.1's state-convergence lesson).
  • /ooo on writes it · /ooo off removes it · /ooo status reads it back and reports the current scoreboard if one is open.
  • Default OFF — the standing posture stays ask-and-wait unless the workspace opts in. ON is standing: every task runs with the scoreboard, no per-task ceremony.
  • A one-shot /ooo invocation on a specific task runs that task under the scoreboard without writing the marker.

2. The scoreboard

When a question arises mid-task, register one line instead of stopping:

Q<n> · <the question, one line> · blocks: <item(s)> · meanwhile: <what proceeds / interim default>

The one-line format is a contract, not a style: if it won't compress to a line, it isn't a question — it's a decision, and it routes through the Hyperbrief trigger rubric (§3.1 interlock) instead. The compression is also what makes answering cheap: the human can answer any subset, in any order, whenever they surface.

Question-inflation guard: a question whose every answer leads to the same next action is not a question. Drop it before it costs anyone a read.

3. Resolution ladder (per question, in order)

  1. Self-resolve by measurement. Read the file, run the check, reproduce the case. Most "questions" are unread files — a question answerable from the workspace never reaches the scoreboard.
  2. Bypass. Reorder: execute every item that doesn't depend on the answer. The blocked item parks; the queue continues. This is the default outcome and the reason the skill exists.
  3. Assumption-run — only where speculation is enabled per §4's gates: proceed under a named default with a revisit marker. A contradicting answer squashes and re-runs the affected slice only, never the whole task.
  4. Park. Irreducible and speculation off → the item waits. Everything independent still proceeds.

Read the full file on GitHub · 58 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. 7d ago First seen · 58 lines · 96 tokens per session scan A e6e08317f8b1

Subscribe to this mod's changes

ooo is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 96 tokens to every session and 1,112 once invoked, about $0.0005 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.