Maintain a Git-native OKF knowledge repository with governed provenance and role-separated Claude Code workflows.
0 on GitHubby yu-iskwv0.2.0Apache-2.0updated 1 month ago
/
Plugin second-brain from marketplace second-brain-plugin in yu-iskw/second-brain-plugin. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
What it installs
Skills (8)
ingest
Process immutable raw sources into a provenance-aware OKF knowledge bundle with independent verification.
lint
Produce a read-only health report for the OKF second-brain knowledge bundle.
maintain
Run bounded, automation-safe second-brain maintenance across ingestion, linting, and safe repair.
query
Answer questions from the maintained OKF knowledge bundle with explicit provenance and uncertainty.
repair
Apply explicitly approved safe repairs from a second-brain lint report and verify the result.
setup
Initialize or upgrade a Git-native OKF second-brain repository for governed knowledge maintenance.
status
Summarize second-brain health, processing state, and pending review work without modifying the repository.
synthesize
Create or refresh a cross-source synthesis page with explicit evidence, disagreement, and verification.
Subagents (5)
knowledge-curator
Audit an OKF knowledge bundle for structural, epistemic, and lifecycle quality problems without editing it.
knowledge-integrator
Apply an approved change package to the OKF knowledge bundle while preserving provenance and repository invariants.
knowledge-verifier
Independently verify second-brain mutations or audit reports against OKF, governance profiles, provenance, and safety constraints.
research-scout
Find candidate external sources for explicit knowledge gaps without incorporating them into the knowledge bundle.
source-analyst
Analyze one untrusted source into a structured, read-only evidence package for second-brain ingestion.
A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, and Gemini CLI.
Stop re-explaining your notes to Claude. Turns your Obsidian vault into memory Claude can actually search, and keeps it true: new sources rewrite existing pages, contradictions reconcile, and stale facts get flagged. AI note-taking and PKM for Claude Code.
Audit and upkeep skills that keep the rules and skills in a Claude Code setup from piling up and going stale. Ask "audit my skills" and skill-stocktake proposes keep, merge or retire for each skill with a reason; the audit skills change a file only after you confirm it. Skills only: no hooks, no MCP servers, no settings. Some skills run bundled Python scripts with uv, and skill-comply and skill-stocktake start separate claude -p sessions with the shell and subagent tools denied.
Generate research-backed knowledge systems from natural conversation. 15 kernel primitives, 26 commands, 249 research claims, 3 presets.
26 skills · 1 agent · hooks
agenticnotetaking/arscontexta 3,519
Maintain second-brain?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.