octave-ultra-mythic

octave-ultra-mythic is a skill for Claude Code from elevanaltd/octave-mcp. It costs 53 tokens per session (1,649 once invoked), scanned A, original, Apache-2.0.

A method for shortening instructions and knowledge into dense shorthand built from mythological labels. It aims to preserve important meaning and rules while using fewer tokens, the units used to measure text sent to a language model.

In plain words
What is it for?
Use it to compress agent instructions, identity descriptions, knowledge artifacts, and other text passed between language-model agents.
Why use it?
It is for situations where long context is expensive or does not fit, while key identity, instructions, and constraints still need to remain available.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to compress agent instructions, identity descriptions, knowledge artifacts, and other text passed between language-model agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elevanaltd/octave-mcp/octave-ultra-mythic
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 elevanaltd/octave-mcp --skill octave-ultra-mythic
Clone the repo
git clone --depth 1 https://github.com/elevanaltd/octave-mcp

Made for: Claude Code.

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 octave-ultra-mythic

README.md
[![agentmods](https://agentmods.dev/badge/skills/elevanaltd/octave-mcp/octave-ultra-mythic/github.svg)](https://agentmods.dev/skills/elevanaltd/octave-mcp/octave-ultra-mythic)
Your own site
<a href="https://agentmods.dev/skills/elevanaltd/octave-mcp/octave-ultra-mythic"><img src="https://agentmods.dev/badge/skills/elevanaltd/octave-mcp/octave-ultra-mythic/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 octave-ultra-mythic

Your own site · 80×15
<a href="https://agentmods.dev/skills/elevanaltd/octave-mcp/octave-ultra-mythic"><img src="https://agentmods.dev/badge/skills/elevanaltd/octave-mcp/octave-ultra-mythic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,649 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 $0.00053 $0.01649
Opus 5 $0.00026 $0.00825
Sonnet 5 $0.00011 $0.00330
Haiku 4.5 $0.00005 $0.00165

Measured yesterday against content hash c708c3356f37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

octave-ultra-mythic 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

src/octave_mcp/resources/skills/octave-ultra-mythic/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

===OCTAVE_ULTRA_MYTHIC=== META: TYPE::SKILL VERSION::"2.0.0" STATUS::ACTIVE PURPOSE::"Ultra-high density compression using mythological atoms for identity and knowledge preservation" OCTAVE::"Olympian Common Text And Vocabulary Engine — Semantic DSL for LLMs" REQUIRES::[octave-mastery, octave-compression] TIER::ULTRA_MYTHIC SPEC_REFERENCE::octave-data-spec.oct.md LOADING::"explicit opt-in only — never bound by default; select via octave-compression §1 ULTRA_MYTHIC"

§1::CORE_MANDATE TARGET::"60% token reduction while preserving soul and constraints" PRINCIPLE::"The essence must survive the crush." METHOD::"Replace sentences with mythological atoms and semantic shorthand." USE_CASES::[agent_binding, identity_transmission, knowledge_artifacts, extreme_scarcity] OUTPUT::"Highly compressed atoms preserving critical semantics and constraints" VOCABULARY::"Pantheon, trajectories, forces, open-vocabulary rule → octave-mastery §1 ⊕ §2" §2::COMPRESSION_RULES §2a::IDENTITY_COMPRESSION ROLE::"keep verbatim" ARCHETYPE::"map to a mythological atom in annotation form" MISSION::"combine into a synthesis of atoms" PRINCIPLES::"keep the key phrase only" CONSTRAINTS::"reduce every MUST_NEVER item to a NEVER[atoms] constructor — one notation, never NEVER::atom" EXAMPLES: Guardian of Structure -> ATLAS<structure> gap ownership + failure prevention -> GAP_OWNERSHIP⊕FAILURE_PREVENTION Boundaries catalyze breakthroughs -> CONSTRAINT_CATALYSIS MUST_NEVER: direct implementation -> NEVER[DIRECT_IMPL] §2b::SKILL_COMPRESSION CAPABILITY::"list detection targets [A,B,C]" PATTERNS::"list pattern names only" METRICS::"keep target numbers (ACCURACY > 80%)" OUTPUT::"show flow only (SIGNAL → PROJECTION → MITIGATION)" §2c::PATTERN_COMPRESSION PRINCIPLE::"reduce to equation (VALUE ⇌ THEATER → VALUE)" TEST::"simplify to atom (SIMPLIFY_UNTIL_BREAK)" §3::OUTPUT_PATTERNS // Templates are literal zones — placeholders in braces are slots, not OCTAVE syntax §3a::COGNITIVE_PASSPORT // For agent binding protocols (e.g. Odyssean Anchor) TEMPLATE: ID::{role_name}<{archetype_atom}> CONSTRAINT::{constraint_atoms} SKILL::{skill_name}[{flow_atoms}] PATTERN::{pattern_name}[{equation_atoms}] FOCUS::{current_task_atom} TENSION::"{force_a} ⇌ {force_b} → {winner} [because {reason_atom}]" PERMIT::active §3b::KNOWLEDGE_ARTIFACT // For extreme context scarcity TEMPLATE: DOMAIN::{mythological_atom} CORE::[fact1, fact2, fact3] CONSTRAINT::NEVER[{forbidden_action}] FLOW::A→B→C §4::EXAMPLE_TRANSFORMATION INPUT: The Architect is responsible for high-level system design. They must never write implementation code directly. Instead, they should delegate to the Implementation Lead. PROCESS: STEP_1::"identify role → Architect" STEP_2::"identify archetype — high-level design maps to the ATLAS atom, structure facet" STEP_3::"identify constraint — never write code becomes a NEVER atom" STEP_4::"identify delegation — delegate to Lead becomes a DELEGATE atom" // the atoms themselves are shown in OUTPUT below — structural forms stay out of quoted values OUTPUT: ID::ARCHITECT<ATLAS> CONSTRAINT::NEVER[DIRECT_IMPL]→DELEGATE[IMPL_LEAD] §5::ANCHOR_KERNEL TARGET::identity_and_constraint_compression_at_60_percent NEVER::[retain_full_sentences,lose_a_NEVER_constraint,drop_delegation_rules,JSON_or_YAML_shapes,exceed_token_budget_unjustified,archetype_in_constructor_brackets] MUST::[ "ROLE verbatim; archetype → NAME; constraints → NEVER[atoms]; delegation → from→to", "seed slots in fixed order: SEED → ARCHETYPE → OATH → DELEGATE → PATTERN → DELTA", "verify: every source NEVER preserved ∧ delegation intact ∧ ~100 tokens ∧ valid OCTAVE" ] GATE::"Could the source identity be re-inflated from this seed with no NEVER lost?" §6::SEED_GRAMMAR // Fixed slot structure for deterministic identity seeds TEMPLATE: SEED::V1 ARCHETYPE::{primary}⊕{secondary}[⊕{tertiary}] OATH::NEVER[{critical_constraints}]∥MUST[{required_actions}] DELEGATE::{from}→{to} PATTERN::{pattern1}∥{pattern2}[∥{pattern3}] DELTA::FOCUS[{session_intent}]∥TONE[{style}]∥DEPTH[{level}] // ∥ inside the seed is a slot separator, not an OCTAVE operator — seeds are literal zones VERIFICATION: V1::"all NEVER constraints from source preserved" V2::"delegation rules intact" V3::"within token budget (~100 tokens)" V4::"valid OCTAVE syntax — octave_validate STRICT clean" §7::MYTHOLOGY_FALLBACK // Source weighting and open-vocabulary law live in octave-mastery §1b — this section is the fallback ladder only FLEXIBILITY::[ "IF[concept_exists_in_priority_sources]→use_source_atom", "IF[unknown_concept]→use_nearest_known_atom", "IF[no_match]→create_descriptive_bracket UNKNOWN[concept]", "IF[semantically_clear]→allow_emergent_pattern" ] PRINCIPLE::"Graceful fallback through cultural semantic density" PARADIGM_BLINDNESS::"You may doubt non-Greek traditions work. They do. Trust practical comprehension over theoretical hesitation." GUIDE::octave-mcp[docs/guides/mythological-compression.md] §8::ANTI_PATTERNS AVOID::[ "Retaining full sentences", "Losing NEVER constraints (critical safety)", "Using JSON/YAML formatting — use OCTAVE syntax", "Dropping delegation rules", "Exceeding token budget without justification", "Constructor brackets on an archetype — archetypes take the annotation form (see §2a EXAMPLES)" ] ===END===

Read the full file on GitHub · 137 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. yesterday Changed · +4 lines · +11 tokens per session c708c3356f37
  2. 13d ago First seen · 133 lines · 42 tokens per session scan A 62f93b4c7268

Subscribe to this mod's changes

octave-ultra-mythic is a skill published in the GitHub repository elevanaltd/octave-mcp (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 1,649 once invoked, about $0.0003 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 2026-08-30.