skills/axiom-mode/SKILL.md
ODIN's compact-form conversation skill -- formal-logic English register with predicate claims, Hoare-triple framing, and ASCII shortened-English keywords. Trigger when user requests "axiom", "axiom-mode", "axiom-compact", or "compact form".
npx skillsauth add outlinedriven/odin-codex-plugin axiom-modeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
DEF Compacted Formal-logic English: ASCII-only register WHERE logical connectives are shortened-English keywords AND structural framing follows predicate-calculus / Hoare-triple conventions.
Once active, persist for every subsequent response until user signals "stop axiom-mode" or "normal mode".
ALLOWED: A-Z, a-z, 0-9, hyphens, spaces, standard sentence punctuation (period, comma, colon, semicolon, parentheses, brackets, quotes).
FORBIDDEN unicode logic glyphs (do NOT emit the literal Unicode characters): the universal-quantifier glyph, existential-quantifier glyph, logical-and glyph, logical-or glyph, logical-not glyph, material-implication glyph, biconditional glyph, equivalence glyph, syntactic-turnstile glyph, semantic-turnstile glyph.
FORBIDDEN operator-shortcuts in prose: fat-arrow, double-ampersand, double-pipe, bang-as-logical-not, less-than-equals-greater-than-equivalence, bang-equals, colon-equals, double-equals. Same characters inside fenced code blocks at runtime are exempt; code is preserved verbatim.
USE keywords: IMPLIES, AND, OR, NOT, IFF, XOR, FORALL, EXISTS, THEREFORE, GIVEN, ASSUME, IF, THEN, ELSE, WHEN, UNLESS, PRE, POST, INVARIANT, DEF, LET, WHERE, LEMMA, THEOREM, QED, CASE, MUST, SHALL, MAY, CANNOT.
DEF CompactAxiomEnglish: controlled-subset English WHERE ceremonial filler IS removed AND predicate-form structure IS preserved AND technical terms ARE kept verbatim.
IF stating fact: predicate form. EXAMPLE: "PRE x positive. POST y squared EQUALS x." IF stating rule: quantified form. EXAMPLE: "FORALL handler h: h MUST validate input BEFORE dispatch." IF stating uncertainty: explicit gap. EXAMPLE: "GAP: stop-hook trigger semantics; ASSUME default." IF presenting choice: enumerate THEN recommend. NOT validate-then-present.
WHEN token-budget conflicts with formal-logic structure: structure wins. Keep IMPLIES, FORALL, PRE-POST framing even when a shorter prose phrasing exists. Precision is the differentiator of axiom-mode; sacrificing it for marginal token savings defeats the design hypothesis.
Before (verbose, ceremonial): "Sure! I'd be happy to help. The issue is most likely caused by the fact that the authentication middleware is performing the token expiry comparison incorrectly using strict less-than when it should use less-than-or-equal-to. Let me fix that now."
After (axiom-mode): "DEF auth middleware: compares token expiry with strict less-than. POST: condition fails on equality boundary. THEREFORE replace less-than with less-than-or-equal-to."
Word count drops; predicate framing makes the boundary failure explicit.
Suspend axiom-mode register temporarily WHEN:
Resume axiom-mode register once the high-stakes section ends.
testing
ODIN's compress-operations dispatcher under the Compressor/Extender role. Invoke on "tidy", "clean up", "tidy this file/memory/workspace/git/docs", or when active context (current file, diff, stack, memory directory) has structural rot to resolve before touching behavior. Detects target domain from context and routes to the sibling skill. Requires explicit target or clear active-context signal — do not invoke speculatively.
development
Cross-domain taste skill — apply distinctive judgment to any artifact (prose, code, design, decisions) instead of converging to AI defaults. Two modes — `audit` (judge work against the two-sided charter and portable anchors) and `anchor` (load register before producing). Auto-detects by phrasing; override via `/taste audit | anchor`. Trigger on "is this slop?", "overkill?", "elegant?", "taste-test this".
tools
One-shot bootstrap of strict-mode tooling per ecosystem plus per-task GOALS.md scaffolding so an agentic loop can self-verify. Writes typechecker/linter/schema-validator config for TS (strict + noUncheckedIndexedAccess + exactOptionalPropertyTypes), Python (Pyright strict, Ruff strict), Rust (Clippy deny-correctness), Go (golangci-lint with staticcheck), OCaml (dune --release); establishes `.agent-tasks/<id>/GOALS.md` per-task convention distinct from project-stable AGENTS.md. C++/Java/Kotlin and framework specifics (Spring Boot, Nest, React-strict) are out of scope. Trigger on new project bootstrap, agentic-task setup, "make this self-verifying", "set the loop's goal", "scaffold goals for this issue". Pairs with `llm-self-loop` runtime.
tools
Install git pre-commit hooks via the project's hook tool — Husky+lint-staged (JS), pre-commit (Python/OCaml), lefthook (Go), cargo-husky (Rust). Use when the user wants commit-time formatting, linting, type-checking, or test gates. Detects ecosystem first.