sancovp

33 mods across 8 repositories, 14 stars between them.

self-claude-mcp

01

sancovp/self-claude-mcp

MCP server Claude CodeCodexCursor

Self-Claude commands. Runs locally from the self-claude-mcp Python package.

2 6mo ago A tokens not measured original MIT

dinf-loop

02

sancovp/dinf

Skill Claude CodeCodex

This is your default workflow for dinf — the BanditChain. Walk it on every task; it is a flow, not a function.

1 24d ago A 17 tokens original MIT

dinf-adjoin

03

sancovp/dinf

Skill Claude CodeCodex

ADJOIN — two frames fighting is a missing Ω one level up; pair them and close it.

1 24d ago A 24 tokens original MIT

dinf-christen

04

sancovp/dinf

Skill Claude CodeCodex

CHRISTEN — name the invariant the moment things converge, or it evaporates.

1 24d ago A 22 tokens original MIT

dinf-factor

05

sancovp/dinf

Skill Claude CodeCodex

FACTOR — find any framework's Ω by the three laws; what remains is k.

1 24d ago A 21 tokens original MIT

dinf-shape

06

sancovp/dinf

Skill Claude CodeCodex

This is an attention chain — an INNER template for how to think about something (a scaffold for a section or for your thinking). Not necessarily spoken.

1 24d ago A 30 tokens original MIT

dinfbandit

07

sancovp/dinf

Skill Claude CodeCodex

Chain-of-reasoning (spoken, ends in a decision): factor the task to its closure, inhabit one view, lift at boundaries, join into a plan, realize it.

1 24d ago A 41 tokens original MIT

sancovp/dinf

Skill Claude CodeCodex

Attention template (how to think): attend to Stop, Fingerprint → hold Sealed.

1 24d ago A 26 tokens original MIT

sancovp/dinf

Skill Claude CodeCodex

Attention template (how to think): attend to Run, Check, Spend → hold Verified.

1 24d ago A 26 tokens original MIT

sancovp/dinf

Skill Claude CodeCodex

Attention template (how to think): attend to Verdict, Cost → hold Reported.

1 24d ago A 25 tokens original MIT

loop-closurebandit

11

sancovp/dinf

Skill Claude CodeCodex

Chain-of-reasoning (spoken, ends in a decision): loop-closure: seal the stop condition before the worker starts, then price one verified task.

1 24d ago A 38 tokens copy · 88% MIT

banditchain

12

sancovp/dinf

Skill Claude CodeCodex

Chain-of-reasoning (spoken, ends in a decision): frame the task, recall a proven chain, choose exploit (select) vs explore (construct), execute it, record the reward.

1 24d ago A 43 tokens original MIT

dinf-attention

13

sancovp/dinf

Skill Claude CodeCodex

Attention template (how to think): attend to Factor, Inhabit, Lift, Join → hold Realized.

1 24d ago A 27 tokens original MIT

dinf

14

sancovp/dinf

Plugin Claude Code

D∞ — the ⟨parts | Ω⟩ shape every durable teaching, framework, plan, and joke has, as a working toolchain: an agent embodied in a directory, three operators (FACTOR / ADJOIN / CHRISTEN), and a gate that catches a missing closure at the syntax level.

1 24d ago A tokens not measured original MIT

0-dinf

15

sancovp/dinf

Skill Claude CodeCodex

Execute the steps below in order. Carry each step's result forward; where a step references {var}, substitute the captured value from the named earlier step.

1 24d ago A 49 tokens original MIT

bandit-chain-system

16

sancovp/dinf

Skill Claude CodeCodex

How the bandit (the default ChainSelector persona) rolls up the AC→CoR→SC algebra and CLOSES it into a domain-specific persona — a self-contained "bandit chain system" that builds its own KB and improves itself via GlyphSteer chains. Use when asked to mint a domain agent, "roll up an algebra", close a chain system…

1 24d ago A 98 tokens original MIT

0.2-dinf-loop

17

sancovp/dinf

Skill Claude CodeCodex

This is your default workflow for dinf — the BanditChain. Walk it on every task; it is a flow, not a function.

1 24d ago A 25 tokens copy · 92% MIT

0.1-dinfbandit

18

sancovp/dinf

Skill Claude CodeCodex

This is a chain of reasoning (CoR) — a SPOKEN, paragraphical reasoning chain that ends in a DECISION. Say it as a paragraph; keep the moves in order.

1 24d ago A 11 tokens original MIT

0.1.3-dinf-adjoin

19

sancovp/dinf

Skill Claude CodeCodex

This is an attention chain — an INNER template for how to think about something (a scaffold for a section or for your thinking). Not necessarily spoken.

1 24d ago A 36 tokens original MIT

0.1.4-dinf-christen

20

sancovp/dinf

Skill Claude CodeCodex

This is an attention chain — an INNER template for how to think about something (a scaffold for a section or for your thinking). Not necessarily spoken.

1 24d ago A 33 tokens original MIT

0.1.2-dinf-factor

21

sancovp/dinf

Skill Claude CodeCodex

This is an attention chain — an INNER template for how to think about something (a scaffold for a section or for your thinking). Not necessarily spoken.

1 24d ago A 33 tokens original MIT

0.1.1-dinf-shape

22

sancovp/dinf

Skill Claude CodeCodex

This is an attention chain — an INNER template for how to think about something (a scaffold for a section or for your thinking). Not necessarily spoken.

1 24d ago A 15 tokens copy · 89% MIT

sancovp/dinf

Skill Claude CodeCodex

This is a chain of reasoning (CoR) — a SPOKEN, paragraphical reasoning chain that ends in a DECISION. Say it as a paragraph; keep the moves in order.

1 24d ago A 11 tokens original MIT

sancovp/dinf

Skill Claude CodeCodex

This is an attention chain — an INNER template for how to think about something (a scaffold for a section or for your thinking). Not necessarily spoken.

1 24d ago A 18 tokens original MIT