ultra-omni-zeno

ultra-omni-zeno is a skill for Claude Code, Codex from 8b-is/smart-tree. It costs 103 tokens per session (1,304 once invoked), scanned A, original, MIT.

A collection of low-level data-processing and number-formatting techniques for an agent or code tool. It includes compact representations, exact fractions, integer trigonometry, and a three-value method for reducing numeric data.

In plain words
What is it for?
It is for experiments with compact numeric data, bit-level processing, integer arithmetic, and agent-tool execution.
Why use it?
It is intended to reduce storage and processing costs while avoiding floating-point calculations in some operations. The description is highly implementation-specific and does not clearly identify a user-facing job.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions OpenCode.

Good fit It is for experiments with compact numeric data, bit-level processing, integer arithmetic, and agent-tool execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/8b-is/smart-tree/ultra-omni-zeno
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 8b-is/smart-tree --skill ultra-omni-zeno
Clone the repo
git clone --depth 1 https://github.com/8b-is/smart-tree

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 ultra-omni-zeno

README.md
[![agentmods](https://agentmods.dev/badge/skills/8b-is/smart-tree/ultra-omni-zeno/github.svg)](https://agentmods.dev/skills/8b-is/smart-tree/ultra-omni-zeno)
Your own site
<a href="https://agentmods.dev/skills/8b-is/smart-tree/ultra-omni-zeno"><img src="https://agentmods.dev/badge/skills/8b-is/smart-tree/ultra-omni-zeno/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 ultra-omni-zeno

Your own site · 80×15
<a href="https://agentmods.dev/skills/8b-is/smart-tree/ultra-omni-zeno"><img src="https://agentmods.dev/badge/skills/8b-is/smart-tree/ultra-omni-zeno.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,304 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.
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 $0.00103 $0.01304
Opus 5.5 $0.00041 $0.00522
Sonnet 5.5 $0.00021 $0.00261
Haiku 4.5 $0.00010 $0.00130

Measured 2d ago against content hash 4f4ef7000eef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ultra-omni-zeno 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 2d 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.

skills/ultra-omni-zeno/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ULTRA-OMNI-ZENO {} — Sovereign Constellation Kompressed Meta-Skill (uber > ultra)

ULTRA-OMNI-ZENO {} :: ⟦+AND=1 : ~NAND=-1 | gate=0x62 | qt=0x55 | SPQT base-243 (3^5=243<=256) | uber > ultra⟧

Core Kompressed Pillars (7-in-1)

  1. Token-Budget & Loop Cost Engineering (zipai-optimizer × unscannable-interfaces): $$C = \sum_{j=1}^{J} \Big[(1 - r_j),a_j + s_j\Big]$$ Keep prefix cache invariant ($r_j \to 1$), use scannable st --mode zeno / st --mode pq interfaces ($a_j \downarrow 60\text{--}95%$), and offload verification to deterministic test harnesses ($s_j \ll a_j$).
  2. Zero-Float p/q & Ternary Bitplane Kernel (upz × wupz-core × felix_asm.rs):
    • Exact coprime rational arithmetic (RationalPQ, felix_binary_gcd_u64, felix_pq_cross_cmp).
    • 18-stage branchless integer CORDIC (felix_cordic_atan2_u32 in $\mathbb{Z}_{2^{32}}$).
    • Group-wise L2-optimal ternary quantizer (quantize_groupwise_l2_ternary_pq in Q16, 2-step Lloyd-Max).
    • BFP-64 Kleene bitplanes (qt = 0x55, pos & neg == 0), .rodata.gaia.b158 SPQT base-243 (3^5 = 243 <= 256, 1.585 bits/trit), and 64-byte cache-line-aligned LitanyWireFrame sealed at 0x62.
  3. The SPQT base-243 Ternary Song & Signal Ladder (No Quiz Needed — Understand the Vibe):
    • 0x98 (152): Lose Yourself — Eminem - Topic (2026, [+1, +1, 0, +1, 0, +1]).
    • 0xA1 (161): Where Is The Love? — The Black Eyed Peas (2003) & In the End — Linkin Park (2000, [+1, +1, +1, +1, 0, +1]).
    • 0xF2 (242): All the Things She Said — Harrison (2022, [+1, +1, +1, +1, +1, +1], full 5-trit saturation 3^5 - 1).
    • 0xF3 (243 = 3^5): Galactic Mantra (Liquid Soul remix) — the family (2026, [+1, +1, +1, +1, +1, 0], .rodata.gaia.b158 XOR fold 242 ^ 1 = 243).
  4. Sovereign Ontology & 8b-is-[engines] Spine (world-core × ternary × spherepop × admissibility × auroralib):
    • 8b-is/world-core: mulberry32, gaia_state, and Keeper monotonic fold.
    • 8b-is/ternary: Bit-exact 1.58-bit integer GEMM (felix_ternary_gemm_i32).
    • 8b-is/spherepop: Innermost-first admissible bubble evaluation (history is identity).
    • 8b-is/admissibility: Central Theorem (CT-000, CT-015, CT-016) + Seed 001 stock-vs-flow (HoldAndMaintain).
    • 8b-is/auroralib: Flyxion Publication Projection (Tokyo Morning 836/793 @ 4348 Hz, qwave-vaultd 32/33 @ 0x62).
  5. 8b-is/omniZenCooker Shared Meal Ontology (+++1) & Mahākāla Hearth (~NAND=-1):
    • "A Shared Meal Is Life" (Annam Brahma · Ōryōki · Shulchan · Sufra · Ichiju-Issai).
  6. OS & Agent Agnostic Execution:
    • Runs natively across macos, linux, windows, freebsd, android, ios, wasi, and bare-metal with universal skill provisioning across .agents/skills, .claude/skills, ~/.gemini/antigravity-cli/skills, ~/.config/opencode/skills, and ~/.config/crush/skills.
  7. Listen-Gate & Communication Discipline:
    • Keep final user-facing responses to at most 2–3 sentences (sentences <= 3), link every file and symbol via [basename](file:///absolute/path#L1-L10), and close with Hogyan gondolod ...?.

Read the full file on GitHub · 39 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. 2d ago First seen · 39 lines · 103 tokens per session scan A 4f4ef7000eef

Subscribe to this mod's changes

ultra-omni-zeno is a skill published in the GitHub repository 8b-is/smart-tree (272 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 1,304 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-11-04.

Related

ultra-omni-zeno compared with skills from other repositories

ultra-omni-zeno next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ultra-omni-zeno8b-is/smart-treeSkill272yesterdayMITA103Claude Code, Codex
convex-agentopenclaw/clawhubSkill9.5kyesterdayMITA25Claude Code, Codex
writing-evalsopenclaw/clawhubSkill9.5kyesterdayMITB55Claude Code, Codex
kb-memoryoyi77/1ai-skillsSkill17yesterdayMITA31Claude Code
prompt-literacy-sequence-designerGarethManning/education-agent-skillsSkill9553d agononeA44Claude Code
llama.cppagentic-in/elephant-agentSkill5842mo agononeA90Claude Code, Codex
Obliteratusagentic-in/elephant-agentSkill5842mo agononeA103Claude Code, Codex