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 skills add SoliEstre/EstreGenesis --skill ooogit clone --depth 1 https://github.com/SoliEstre/EstreGenesisWrote 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/soliestre/estregenesis/ooo)<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>- NVIDIA SkillSpector pass
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 5.1 | $0.00096 | $0.01112 |
| Opus 5 | $0.00048 | $0.00556 |
| Sonnet 5 | $0.00019 | $0.00222 |
| Haiku 4.5 | $0.00010 | $0.00111 |
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.
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 onwrites it ·/ooo offremoves it ·/ooo statusreads 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
/oooinvocation 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)
- 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.
- 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.
- 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.
- Park. Irreducible and speculation off → the item waits. Everything independent still proceeds.
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.
- 7d ago First seen · 58 lines · 96 tokens per session scan A e6e08317f8b1
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.
Other skills, from other repositories
specflo-auto
Use when the user wants an unattended specflo run — "auto mode", "autopilot", "run it on its own", "keep going without me", "don't stop to ask" — map that to specflo auto. It is an explicit, per-invocation opt-in that drives the pipeline across phase boundaries without the ask-first pause. Do NOT use for the normal…
discovery-question-form
Structured clarification form for unresolved material requirements.
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.