dinf

Plugin dinf in sancovp/dinf. Commands read from the repo's manifest — 1 month ago.

Skills (26)

• dinf-loop

  the dinf default workflow (BanditChain) — walk it

• dinf-adjoin

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

• dinf-christen

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

• dinf-factor

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

• dinf-shape

  the governing chain: factor to the closure, inhabit a view, lift at the boundary, join into a plan, realize it

• dinfbandit

  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.

• loop-closure-attention-1

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

• loop-closure-attention-2

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

• loop-closure-attention-3

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

• loop-closurebandit

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

• banditchain

  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.

• dinf-attention

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

• 0-dinf

  [0] dinf: in the dinf domain: frame the task, recall a proven dinf chain, choose exploit (select a golden chain) vs explore (construct a new one), execute it, record the reward

• bandit-chain-system

  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

• 0.2-dinf-loop

  [0.2] the dinf default workflow (BanditChain) — walk it

• 0.1-dinfbandit

  [0.1] in the dinf domain: frame the task, recall a proven dinf chain, choose exploit (select a golden chain) vs explore (construct a new one), execute it, record the reward

• 0.1.3-dinf-adjoin

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

• 0.1.4-dinf-christen

  [0.1.4] CHRISTEN — name the invariant the moment things converge, or it evaporates

• 0.1.2-dinf-factor

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

• 0.1.1-dinf-shape

  [0.1.1] the governing chain: factor to the closure, inhabit a view, lift at the boundary, join into a plan, realize it

• 0.3-loop-closure-cor

  [0.3] loop-closure: seal the stop condition before the worker starts, then price one verified task

• 0.3.1-loop-closure-attention-1

  [0.3.1] loop-closure: seal the stop condition before the worker starts, then price one verified task

• 0.3.2-loop-closure-attention-2

  [0.3.2] loop-closure: seal the stop condition before the worker starts, then price one verified task

• 0.3.3-loop-closure-attention-3

  [0.3.3] loop-closure: seal the stop condition before the worker starts, then price one verified task

• loop-closure

  Close an agent loop before you run it: name the closure state, predate the check, pick a progress fingerprint, then cost it per verified task.

• using-dinf

  WHAT: the D∞ notation — the ⟨parts | Ω⟩ shape every durable teaching, framework, plan, and joke has — plus the three operators over it (FACTOR, ADJOIN, CHRISTEN) and the `dinf` CLI that makes the missing-closure defect machine-catchable. WHEN: when stuck; when a plan feels like unjoined parts; when

Similar plugins