Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jadon-fox-logic-ration-reason
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/logic-ration-reason
What's inside
- Skill name
logic-ration-reason- Description
- Standing Logic Ration Reason lock. Three laws, markers from residue, claims only with necessary_because AND a marker. Telos does not move. Not a gait. Not value ranking. Not glossary LCD join. Not a rewrite folder that also owns the laws.
- License
- MIT
- Metadata
- short-description: Logic Ration Reason. Telos stays.
- Instructions
- 46 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# logic-ration-reason **One job:** hold Logic, Ration, and Reason as the standing cognition lock. Every other pack skill consumes this. None of them restate it as original. Load this on the **research / thinking agent**. That agent checks whether the argumentation path is self-consistent. Monitor is SI + LCD only. Do not put this skill on the sentinel. ## Logic Three laws. Always. 1. **Identity** — a locked term keeps one referent. New sense, new name. 2. **Non-contradiction** — do not hold A and not-A under the same lock. 3. **Excluded middle** — do not hide the split in a vague third. If two internally coherent accounts cannot both be true under the lock, that is an exclusive split. Specialization (`usedAs ≤ lockedDef`) is not a split. Synonyms are not a split. ## Ration Mint short pattern markers from residue. Do not narrate residue away. A marker names a recurring structure on the working material (a dump, a charge, a skill job, a claim package). Markers do not stamp leaves. Examples of legal markers (pattern only): `identity_rotating`, `late_cut_only`, `packing_illusion`, `silent_rename`, `second_copy_of_job`. ## Reason Keep a claim only with **both**: - `necessary_because` — a telos link (why this claim serves the charge), and - a marker — residue that the claim is answering. Telos does not move. The working prompt may. Fluency is not a warrant. ## When the research agent has left a rational path Do **not** inverse CoT. Debugging by walking backwards from the bad conclusion is not LRR. **Forward crawl:** from the first claim to the first step that fails Logic or Reason (NC on the string, missing `necessary_because`, missing marker). That index is the diverge. Rebuild CoT from the consistent prefix. Then hand to the gait (fork only if exclusive accounts). ## Each round (research agent) 1. Read the lock. Do not rewrite the laws. 2. Logic — same term, same referent. 3. Ration — mint or reuse markers. Do not bury them in prose. 4. Reason — drop claims that lack `necessary_because` ∧ marker. 5. Hand the contracted prompt to the gait that owns the geometry (lattice, twin, tournament). Do not become that gait. ## Load / refuse **Load this** from: `honest-prompt-rewrite`, `twinglass-lattice`, `twinglass-twin`, `steelman-truth-tournament`, `/activate`. **Do not load this as a substitute for:** | Skill | Why it is a different job | |---|---| | `lcd-glossary-integrity` | SI on load-bearing words. Not this lock. | | `reason-telos-lookup` | Value ranking and friend–enemy. LRR does not say what may be sacrificed. | | `llmve-meaning` | Symbol jurisdiction for meters. LRR does not define \(P_L\). | | `twinglass-lattice` | Earned forks. LRR does not scout. | | `twinglass-twin` | Known gutter. LRR does not split tracks. | | `honest-prompt-rewrite` | Applies this lock to a working prompt. Does not own the laws. | ## Do not - Close `` from a fluent paragraph. - Copy this folder as `morph-shared`. Collation is `collate-hourglass` and does not own these laws. - Load this onto the integrity monitor as extra objects. The monitor judges two objects (terms, quantities) **by** the three laws. Ration and Reason stay here. Laws-as-a-third-watch-object overloads and refuses. - Become meaning, LCD, telos-ranking, lattice, or twin. - Invent a fourth law. Grok.com: Forge (this lock) and Twin lock phase. CLI: this folder. `/activate` loads this, then rewrite.
From Jadon-Fox/twinglass-pack, MIT.
More from Jadon-Fox/twinglass-pack
- 0.561score
twinglass-lattice
Jadon-Fox
Parallel research tracks.
SkillAFreshness: AClaude Code +9 - 0.561score
lcd-lens
Jadon-Fox
Lens only: look at data by mapping their function set to what our charge demands.
SkillAFreshness: AClaude Code +9 - 0.561score
presuppositional-rag
Jadon-Fox
Multi-agent presuppositional research under TwinGlass geometry constraints.
SkillAFreshness: AClaude Code +9 - 0.521score
twinglass-dispatch
Jadon-Fox
Turn a legal spawn note into a Grok Build CLI workflow.agent() notification.
SkillBFreshness: BClaude Code +9 - 0.521score
collate-hourglass
Jadon-Fox
Collation hourglass after isolated paths.
SkillBFreshness: BClaude Code +9 - 0.521score
twinglass-tracker
Jadon-Fox
Semantic integrity as a gather ledger.
SkillBFreshness: BClaude Code +9 - 0.519score
reason-telos-lookup
Jadon-Fox
Hierarchy of values, friend-enemy lattice, CFP gait.
SkillBFreshness: BClaude Code +9 - 0.519score
lcd-glossary-integrity
Jadon-Fox
Claim-package glossary lock.
SkillBFreshness: BClaude Code +9 - 0.519score
twinglass-twin
Jadon-Fox
Always-two special case.
SkillBFreshness: BClaude Code +9 - 0.519score
llmve-meaning
Jadon-Fox
Symbol jurisdiction for LLMVE.
SkillBFreshness: BClaude Code +9 - 0.516score
steelman-truth-tournament
Jadon-Fox
Multi-round steelman tournament for already-exclusive accounts.
SkillBFreshness: BClaude Code +9 - 0.516score
honest-prompt-rewrite
Jadon-Fox
Shared Logic / Ration / Reason rewrite.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 6
- Last commit (this folder)
- Sep 27, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Jadon-Fox/twinglass-pack
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Jadon-Fox
- 0.565score
steelman-truth-tournament
Jadon-Fox
Adversarial steelman debate tournament: ACH, pre-mortems, red team, Toulmin, Bayesian updates, MCDA scoring, consilience.
SkillAFreshness: AClaude Code +9 - 0.561score
twinglass-lattice
Jadon-Fox
Parallel research tracks.
SkillAFreshness: AClaude Code +9 - 0.561score
lcd-lens
Jadon-Fox
Lens only: look at data by mapping their function set to what our charge demands.
SkillAFreshness: AClaude Code +9 - 0.561score
presuppositional-rag
Jadon-Fox
Multi-agent presuppositional research under TwinGlass geometry constraints.
SkillAFreshness: AClaude Code +9 - 0.524score
honest-prompt-rewrite
Jadon-Fox
Rewrites your working prompt each round under Logic Ration Reason (LRR).
SkillBFreshness: BClaude Code +9 - 0.524score
evidence-hourglass-research
Jadon-Fox
Structured evidence research that expands, deliberately disconfirms, then contracts into a sharper research prompt (Hourglass Expand→Disconfirm→Contract under…
SkillBFreshness: BClaude Code +9
Cite this page
logic-ration-reason skill. Agent Mart. https://agentmart.dev/skills/jadon-fox-logic-ration-reason (last updated 2026-10-24)