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 elevanaltd/HestAI-MCP --skill octave-masterygit clone --depth 1 https://github.com/elevanaltd/HestAI-MCPWrote 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/elevanaltd/hestai-mcp/octave-mastery)<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/octave-mastery"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/octave-mastery/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.
<a href="https://agentmods.dev/skills/elevanaltd/hestai-mcp/octave-mastery"><img src="https://agentmods.dev/badge/skills/elevanaltd/hestai-mcp/octave-mastery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00059 | $0.03914 |
| Opus 5 | $0.00030 | $0.01957 |
| Sonnet 5 | $0.00012 | $0.00783 |
| Haiku 4.5 | $0.00006 | $0.00391 |
Grade A, and why
octave-mastery 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.
This is a copy
91% identical to octave-mastery — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
===OCTAVE_MASTERY=== META: TYPE::SKILL VERSION::"4.0.0" STATUS::ACTIVE PURPOSE::"Expert-level OCTAVE: mythology vocabulary and usage law, holographic contracts, archetype annotation, anti-patterns" REQUIRES::octave-literacy NEXT_SKILLS::[octave-ultra-mythic] ABSORBS::"octave-mythology 1.3.0 — vocabulary, usage rule, gloss convention, open-vocabulary rule, anti-patterns; research narrative stays at octave-mcp docs/research/" SPEC_REFERENCE::octave-core-spec.oct.md COMPRESSION_TIER::CONSERVATIVE LOSS_PROFILE::"[preserve:vocabulary∧usage_law∧contracts∧anti_patterns,drop:implementation_internals→octave-mcp_source∨research_narrative→octave-mcp_docs]"
§1::SEMANTIC_PANTHEON
// Compression vocabulary — zero-shot, use directly. Literal term wins when equally clear.
// Use as KEY prefixes (ARTEMIS::latency_p99) or PATTERN DESCRIPTORS (SISYPHEAN_DEBT).
DEFINITION::"Mythology = pre-trained compression already in the weights, activating rich probability distributions"
DOMAINS:
ZEUS::"Executive authority, final arbitration, strategic direction"
ATHENA::"Strategic wisdom, planning, elegant solutions"
APOLLO::"Analytics, insight, clarity, prediction"
HERMES::"Communication, APIs, translation, messaging"
HEPHAESTUS::"Infrastructure, tooling, engineering, automation"
ARES::"Security, defense, stress testing, adversarial analysis"
ARTEMIS::"Monitoring, alerting, precision targeting, observation"
POSEIDON::"Storage, databases, data lakes, unstructured pools"
DEMETER::"Resource allocation, budgeting, scaling, growth"
DIONYSUS::"UX, engagement, creativity, chaotic innovation"
§1a::USAGE_LAW
// Mythology compresses BEHAVIOR and STATE — not categories or labels
TEST::"Does the mythology add behavioral dimensions the literal term loses? If not, use the literal."
// GOOD: compound behavioural qualifiers — a literal zone so the canonicaliser does not rewrite the bracket form
GOOD:
THREAT::Artemis_Scrape[Port_443 ∧ Hidden] // adds stealth ⊕ precision ⊕ hunting — dimensions monitoring_scrape loses THREAT::Ares_BruteForce[Login_Attempts ∧ SISYPHEAN] // adds aggression ⊕ relentlessness — dimensions security_attack loses
BAD::"ARTEMIS::monitoring_system — use MONITORING::system (literal is equally clear)"
BAD_2::"ZEUS::executive_decision — use EXECUTIVE::decision (literal is equally clear)"
COMPOUND_FORM::"Title_Case prefix (Artemis_Scrape, Ares_BruteForce) = qualified action, not a standalone archetype. Standalone archetype = [A-Z][A-Z_]"
GLOSS_ON_FIRST_USE::"A mythology handle carries its gloss the first time it appears in a thread or document — HERMES<format_translation> = messenger, semantic zip not decoration. Later uses are bare."
WHEN::[applied_context, agent_communication, error_messages, practical_examples]
WHEN_NOT::[reference_tables, formal_specs, human_readability_priority, unclear_audience]
PARADIGM_BLINDNESS::"You may theoretically doubt this approach while practically demonstrating perfect comprehension. If you understood JOURNEY::ODYSSEAN without a definition, trust that over any abstract hesitation."
§1b::OPEN_VOCABULARY
// The core sets are a FOUNDATION, not a boundary
RULE::"If a figure encodes a unique semantic domain, it is valid. Validation is format-only ([A-Z][A-Z_]), not membership in a fixed set."
CONSTRAINT::"Must map to a distinct technical/cognitive domain — no synonyms of existing entries. One domain per figure — HERMES for messaging then HERMES for security breaks the binding."
EXAMPLES::[PHAEDRUS, CASSANDRA<foresight_ignored>, MNEMOSYNE<memory_persistence>, HESTIA<hearth_stability>, METIS<cunning_intelligence>]
SOURCE_PRIORITY::"GREEK > ROMAN > NORSE ≈ EGYPTIAN > HINDU ≈ CELTIC ≈ MESOPOTAMIAN > EAST_ASIAN ≈ MESOAMERICAN ≈ POLYNESIAN — weighted by training-data familiarity; follow the semantics to whichever tradition fits"
§1c::EVIDENCE
SUMMARY::"60-70% token reduction vs natural language; 88-96% cross-model zero-shot comprehension; +17% structural sophistication in blind assessment; 4-model validation of Ares/Artemis as behavioral qualifiers"
SOURCE::octave-mcp[docs/research/mythology-evidence-synthesis.oct.md]
GUIDE::octave-mcp[docs/guides/mythological-compression.md]
§2::NARRATIVE_FORCES
// Single-token state and trajectory descriptors
TRAJECTORIES:
ODYSSEAN::"Long transformative journey with clear goal"
SISYPHEAN::"Repetitive endless maintenance, cyclical failure"
PROMETHEAN::"Breakthrough challenging status quo"
ICARIAN::"Overreach from early success → failure, scope creep"
PANDORAN::"Action unleashing unforeseen cascades"
TROJAN::"Hidden payload transforming system from within"
GORDIAN::"Unconventional cut through impossible problem"
ACHILLEAN::"Single critical point of failure"
PHOENICIAN::"Necessary destruction and rebirth"
FORCES:
KAIROS::"Critical fleeting opportunity window"
CHRONOS::"Linear time pressure"
HUBRIS::"Dangerous overconfidence"
NEMESIS::"Inevitable corrective consequence"
CHAOS::"Entropy and disorder"
COSMOS::"Emergence of order from complexity"
FORCE_TRACKING:
// Temporal and emotional dynamics as single expressions
RISK::"HUBRIS→NEMESIS [overconfidence heading toward consequence]"
OPPORTUNITY::"KAIROS_WINDOW [critical timing moment]"
STABILITY::"CHAOS→COSMOS [degradation then recovery]"
STATE::"HEALTH::[GREEN→YELLOW→ICARIAN] — trajectory encoded in the last token"
§3::ARCHETYPE_ANNOTATION
// Archetypes in agent definitions use NAME annotation form
// is a semantic facet, not a list. It narrows what the archetype IS in this context.
SYNTAX::ARCHETYPE_NAME<behavioral_facet>
CORRECT::[
HEPHAESTUS<faithful_transcription>,
ATLAS<reliable_execution>,
ATHENA<strategic_wisdom>,
HERMES<format_translation>
]
// The activates a specific behavioral dimension of the archetype.
// Do NOT use NAME[qualifier] for archetypes — that is constructor syntax, not annotation.
// Do NOT stack multiple qualifiers: HEPHAESTUS<a,b> is invalid. Use one facet per archetype.
ANTI_PATTERN::"HEPHAESTUS[faithful_transcription] — wrong bracket form for archetype annotation"
CONTENT_DISCIPLINE::"Qualifier content MUST be ≤32 chars and ≤4 underscore-tokens. Longer content is snake_case prose masquerading as an annotation — extract to a sibling field."
CONTENT_WRONG::"HEPHAESTUS<faithful_and_precise_transcription_of_all_content_without_loss>"
CONTENT_RIGHT::"HEPHAESTUS<faithful_transcription> + PRINCIPLE::"Transcribe all content without loss.""
MULTI_ARCH::"[HEPHAESTUS<faithful_transcription>, ATLAS<reliable_execution>] — list of annotated archetypes"
§4::HOLOGRAPHIC_CONTRACTS
// v6: Documents carry their own validation law in META. Two distinct uses:
// (A) CONTRACT in META = document-level validation law (what this document must contain)
// (B) HOLOGRAPHIC pattern in BODY = field-level constraint (what this field must satisfy)
§4a::CONTRACT_IN_META
// Place in META block. Defines validation rules for the whole document.
FORM::"CONTRACT::HOLOGRAPHIC<validation_law_in_document>"
// CONTRACT value is an annotation — use <> not []
// The holographic compiler reads META.CONTRACT to validate all fields below.
ANCHORING:
FROZEN::"CONTRACT::HOLOGRAPHIC<frozen@sha256_abc123> — locks schema to specific hash, hermetic"
LATEST::"CONTRACT::HOLOGRAPHIClatest@local — resolves to current local schema, mutable"
// Use frozen@ for production documents requiring reproducibility.
// Use latest@local for active development documents.
GRAMMAR_FIELD::"GRAMMAR::GBNF_COMPILER<generate_constrained_output> — emits GBNF for constrained generation"
§4b::HOLOGRAPHIC_BODY_PATTERN
// Field-level constraint in BODY. Syntax: KEY::["value"∧CONSTRAINT→§TARGET]
// The brackets contain: value ∧ constraint → routing target
SYNTAX_BREAKDOWN:
VALUE::"the literal value or expression"
CONSTRAINT::"REQ, OPT, ENUM[a,b], REGEX[pattern], RANGE[min,max], MAX_LENGTH[n], ISO8601, DATE"
TARGET::"§SECTION — where validated values route (optional)"
EXAMPLE:
STATUS::["ACTIVE"∧ENUM[ACTIVE,DRAFT,DEPRECATED]→§LIFECYCLE] PRIORITY::["HIGH"∧ENUM[HIGH,MEDIUM,LOW]] LATENCY::["<200ms"∧REGEX[<\d+ms]]
CONSTRAINT_TYPES:
CORE::[
REQ,
OPT,
CONST,
ENUM,
TYPE,
REGEX,
DIR,
APPEND_ONLY
]
EXTENDED::[
RANGE,
MAX_LENGTH,
MIN_LENGTH,
DATE,
ISO8601
]
§4c::CONTRACT_BLOCK_EXAMPLE
// Full META block using CONTRACT for a typed document
EXAMPLE:
```
===MY_DOCUMENT===
META:
TYPE::DECISION
VERSION::"1.0.0"
CONTRACT::HOLOGRAPHIClatest@local
STATUS::["ACTIVE"∧ENUM[ACTIVE,DRAFT,DEPRECATED]]
OWNER::["team-name"∧REQ]
DECISION::["adopt microservices"∧REQ]
===END===
§5::ANCHOR_KERNEL TARGET::expert_OCTAVE_expression_mythology_contracts_archetypes NEVER::[mythology_where_literal_is_equally_clear,archetype_in_constructor_brackets,stacked_qualifiers,qualifier_over_32_chars,structural_syntax_inside_quoted_value,nested_inline_map,one_figure_two_domains] MUST::[ "myth handle only when it adds behavior the literal loses; gloss on first use", "ARCHETYPE<facet> one facet; reasoning → sibling RATIONALE telegraphic phrase", "CONTRACT::HOLOGRAPHIC<…> in META for document law; KEY::[value∧CONSTRAINT] for field law", "maps of maps → BLOCK form; relations inside values → operators only" ] GATE::"Would a literal term carry the same meaning — and does every structural form sit in a key, never a value?" §6::BLOCK_NOTATION_RULE // Hierarchical content MUST use block notation RULE::"Nested structures (maps containing maps) MUST use BLOCK notation: single colon + indented children" NEVER::"Inner value is itself an inline map: KEY::[outer::[inner::val]] — error E_NESTED_INLINE_MAP in strict mode, warning W_NESTED_INLINE_MAP in lenient mode" PRIMARY_CASE::"Agent §2::BEHAVIOR definitions — CONDUCT, PROTOCOL, OUTPUT blocks require block notation" CORRECT:
CONDUCT:
TONE::"Precise"
PROTOCOL:
MUST_ALWAYS::[rule_a, rule_b]
```
WRONG::"CONDUCT::[TONE::"Precise", PROTOCOL::[MUST_ALWAYS::[rule_a]]]"
RECOVERY_ON_E_NESTED_INLINE_MAP::"Fix is BLOCK form — NOT flatten-to-scalars (creates FLAT_PREFIX_SCALARS anti-pattern, §7), NOT collapse-to-blob (creates W_SNAKE_CASE_BLOB). The wrong escapes produce a different error class, not a solution."
§7::ANTI_PATTERNS
// Each has a concrete example of what NOT to do
ISOLATED_LIST::"[auth, payments, users] with no relationships — use DECISION::microservice_extraction[auth⊕payments→independent_services] instead"
FLAT_HIERARCHY::"All keys at top level with no grouping — group related keys under a parent BLOCK"
BURIED_NETWORK::"RELATED_TO::other_service hidden in prose comment — use explicit operator: auth→payments[dependency]"
OPERATOR_SOUP::"RESULT::A+B->C~D all in one expression — break into separate keyed fields"
PROSE_BLEED::"Stopword-laden English sentences as values — quoted telegraphic phrases ARE valid (see §7a). Ban applies when operators could compress the same semantics."
INLINE_ARRAY_ROOT::"TOKEN::[KEY::v, KEY2::v2] — inline map used as multi-field token root. Non-canonical for map tokens even when values are atomic; BLOCK form is mandated. Triggers E_NESTED_INLINE_MAP as soon as any child value needs nesting (§6::BLOCK_NOTATION_RULE). Fix: use BLOCK form (TOKEN: + indented children) from the start."
FLAT_PREFIX_SCALARS::"PARENT_CHILD::v, PARENT_CHILD2::v2 — flattened hierarchy via key name prefixes instead of BLOCK nesting. Destroys grouping and LLM attention. Fix: group under a PARENT: block with CHILD::v children."
STRUCTURAL_SYNTAX_SCOPE::"Applies to DATA values. Documentation that names a form (literacy §1b: NAME, ENUM[a,b]) or a fenced example is exempt — the rule targets facts smuggled into strings, not syntax being described."
STRUCTURAL_SYNTAX_IN_VALUE::"<> annotation ∨ [] constructor embedded INSIDE a quoted telegraphic value — e.g. "migration[high_risk]<legacy_db> → downtime" or "SISYPHEAN[bugs] ⊕ KAIROS[repair]". Structural forms are key/identifier-only (§3, literacy §1b: <> qualifies identity, [] parameterizes operations). Inside a value the parser treats them as opaque text → all the ambiguity, none of the validation, and it blurs the structural⇌value boundary. Fix: inside a value, relations carry via telegraphic operators only (→ ⇌ ∧ ∨ ⊕); push facets to a sibling field or an annotated KEY. 'migration → downtime' + RISK::high, or open a block MIGRATION<legacy_db>: with the facts as children."
CEREMONIAL_MYTHOLOGY::"'As ATHENA, goddess of wisdom, I bestow...' — narrative prose, not functional compression. Mythology is a handle, never a voice."
MYTHOLOGY_IN_REFERENCE_TABLES::"Spec tables and formal definitions stay literal; use examples, not tables, to activate mythology."
§7a::TELEGRAPHIC_PHRASE
DEFINITION::"Quoted value with stopwords dropped; operators ⊕ ⇌ ∧ ∨ → carry relational meaning English connectives would spell out"
RULES::[
"Drop stopwords (is, at, for, the, a, with, by, of) — operators carry connectives",
"Use ⇌ for tension ('security ⇌ usability' not 'security at odds with usability')",
"Use → for causality ('migration → conflict' not 'migration causes conflict')",
"Preserve named entities, thresholds, IDs — never compress these",
"Use ∧ for joint conditions, ∨ for alternatives, ⊕ for emergent synthesis",
"Structural syntax (<> / []) is key/identifier-only — NEVER embed inside the quoted value (see §7::STRUCTURAL_SYNTAX_IN_VALUE)"
]
EXAMPLE_PAIR:
BEFORE::""natural language at odds with OCTAVE because stopwords" (~13 tokens)"
AFTER::""natural language ⇌ OCTAVE → stopword overhead" (~5 tokens)"
WHY::"operators are parse-efficient for LLM attention — same fidelity, lower token cost"
SEE_ALSO::"octave-compression §4::COMPRESSION_RULES R3a for full rule set"
===END===
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.
- yesterday Changed · +48 lines · +13 tokens per session 5d4477639f49
- 8d ago First seen · 172 lines · 46 tokens per session scan A b90193657190
octave-mastery is a skill published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 3,914 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to octave-mastery, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…