letrplB/second-brain

second-brain turns a folder of atomic markdown claims into a graph the LLM walks directly — no orchestration, no phase machines, no invisible hooks. Eight verbs (extract, connect, walk, audit, learn, init, anneal, dream) operate on the graph as data; an opt-in surrender system (no-surrender, teach) probes your grip on the claims.

1Stars on the repository
12Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

anneal

01

letrplB/second-brain

Skill Claude CodeCodex

Methodology coach pass. Walks scoped notes, flags drift, suggests fixes, applies on confirmation. Explicit only — never proactive.

1 3mo ago A 29 tokens original MIT

audit

02

letrplB/second-brain

Skill Claude CodeCodex

Quality gate. Schema + link + cold-read on a note (or --vault). Returns a report with ranked issues and suggested fixes.

1 3mo ago A 29 tokens original MIT

connect

03

letrplB/second-brain

Skill Claude CodeCodex

Wire a note into the graph. Add inline wikilinks both directions, update MOC membership. The primitive that turns isolated notes into a graph.

1 3mo ago A 32 tokens original MIT

dream

04

letrplB/second-brain

Skill Claude CodeCodex

Push synthesis back at the user. Daily mode pulls 3 connections + 1 pattern + 1 question from recent activity. Weekly mode surfaces emerging thesis, contradictions, gaps, and one action. The feedback loop that turns the vault from input-store into thinking-partner.

1 3mo ago A 56 tokens original MIT

extract

05

letrplB/second-brain

Skill Claude CodeCodex

Mechanical extraction of atomic claims from a source file. Inline, fast, no choreography. The primitive that /learn composes with /connect and /audit.

1 3mo ago A 33 tokens original MIT

init

06

letrplB/second-brain

Skill Claude CodeCodex

Scaffold a new second-brain vault. Two modes — guided (no args, conversational onboarding) and quick (preset name + optional domain + optional --at path).

1 3mo ago A 36 tokens original MIT

learn

07

letrplB/second-brain

Skill Claude CodeCodex

Full ingestion of a source. Composes /extract → /connect → /audit end-to-end. The verb you use when you want a source to land properly in the graph.

1 3mo ago A 38 tokens original MIT

no-surrender

08

letrplB/second-brain

Skill Claude CodeCodex

Probe the user's grip on a vault claim across mechanism / implications / falsifiability / bounds axes. Updates the claim's engagement vector. The only verb that writes engagement. Gated by surrender.enabled in vault.yaml.

1 3mo ago A 47 tokens original MIT

teach

09

letrplB/second-brain

Skill Claude CodeCodex

Pedagogical companion to /no-surrender. Builds engagement on identified gaps via Socratic prompts. Does NOT write engagement — only /no-surrender does. Gated by surrender.enabled in vault.yaml.

1 3mo ago A 44 tokens original MIT

walk

10

letrplB/second-brain

Skill Claude CodeCodex

Query the graph. Semantic search + topology operations. The model's primary navigation tool over the vault.

1 3mo ago A 22 tokens original MIT