superscalar

superscalar is a skill for Claude Code from SoliEstre/EstreGenesis. It costs 311 tokens per session (2,340 once invoked), scanned A, original, Apache-2.0.

A setting and checklist for deciding how readily a coding agent should split independent work into parallel tasks. Its modes are always, auto, and off, stored in .agent/superscalar.json.

In plain words
What is it for?
It is for controlling and reviewing whether an agent fans out work, including changing the mode or checking the current mode.
Why use it?
It makes parallel task dispatch a deliberate project setting, with checks for when parallel work is suitable and when it should be reduced.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions subagents.

Part of the superscalar plugin — 5 skills shipped together

Good fit It is for controlling and reviewing whether an agent fans out work, including changing the mode or checking the current mode.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/soliestre/estregenesis/superscalar"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/superscalar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 311 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,340 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 $0.00311 $0.02340
Opus 5 $0.00156 $0.01170
Sonnet 5 $0.00062 $0.00468
Haiku 4.5 $0.00031 $0.00234

Measured 5d ago against content hash 013679cf7ba9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

superscalar 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 5d 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/superscalar/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Superscalar — execution-scheduling discipline

Two jobs in one skill. Invoked with an argument (/superscalar always|auto|off|status) it is a mode toggle — see §0. Invoked with no argument, or consulted before a fan-out, it is the dispatch checklist — §1 onward, read through the lens of the current mode.

0. Mode toggle — how eagerly to fan out (always | auto | off)

State = one marker file, .agent/superscalar.json{"mode": "always"|"auto"|"off", "since": "<date>", "note": "<why>"}. Absent ⇒ auto. Read it at dispatch time; never mirror the mode into other settings surfaces.

  • /superscalar always — write the marker with always · /superscalar auto — write auto (or delete the marker) · /superscalar off — write off · /superscalar status — read it back and report the mode plus where it would apply to the work in front of you.
Mode What it changes What it does not change
off No fan-out on your own initiative — independent work runs in declared order. An explicit user request to parallelize is still honored; record it as an override.
auto (default) §2's cost-benefit gate arbitrates, as before.
always Burden of proof inverts: with ≥2 independent lanes, fan out unless a veto below applies. The gate becomes a veto list, not a hurdle. Prefer Workflow/pipeline over serial inline for multi-item work. Every safety invariant. See below.

always vetoes (still serial): not write-disjoint and isolation unavailable (§3, nested-repo case included) · no independent decomposition · deep shared-context work · total work below the inline-wins floor (§2, ~8k) · latency-critical interactive edit · issue_width already saturated.

Unconditional in every modealways never loosens these: §4 irreversibility barrier · §3.1 Hyperbrief interlock on write/deploy/send lanes · §5 in-order retire + consistency gate + completeness critic · §1 issue_width caps (the prior moves, the ceiling does not) · speculation stays a separate, default-off axis.

Read the full file on GitHub · 103 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. 5d ago Changed · +2 lines 013679cf7ba9
  2. 10d ago First seen · 101 lines · 311 tokens per session scan A 53945bec3ab7

Subscribe to this mod's changes

superscalar is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 311 tokens to every session and 2,340 once invoked, about $0.0016 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

update-agent-context

This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…

mostlyharmless-ai/watercooler · 203 tokens

watercooler-onboarding

Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…

mostlyharmless-ai/watercooler · 79 tokens

ppgp

Portable Persistent Goal Protocol for long-running coding-agent work. Use when starting, resuming, handing off, distilling, or closing a substantial software goal across long sessions, context compaction, agent replacement, or other Agent Skills-compatible coding-agent environments.

Fatboy-coder/ppgp · 53 tokens

search-threads

Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.

mostlyharmless-ai/watercooler · 35 tokens

watercooler-health

Check watercooler system health — MCP server, baseline graph (T1), git auth, GitHub rate limit, and daemons. Use when syncs break or anything in the watercooler stack behaves unexpectedly.

mostlyharmless-ai/watercooler · 49 tokens

recall

Recall project context or answer questions about history and decisions. Use before starting work, when investigating unfamiliar code, or asking "What was decided about X?" / "Why did we choose Y?".

mostlyharmless-ai/watercooler · 41 tokens