Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By Curt-Park
Automatically capture project decisions, conventions, and patterns from Claude Code sessions into a living markdown knowledge graph, then query or sync that documentation after commits and refactors to keep it accurate.
npx claudepluginhub curt-park/autology --plugin autologyUse when user is new to Autology, asks "how does Autology work", wants to learn about knowledge capture, or requests a guided introduction.
Use after significant project actions — commit, push, PR — or when the team settles on how to build or operate the system: a technology choice, a process, a rule, or a standard. Running close to the action keeps captured knowledge more accurate and complete.
Use to permanently record a project decision, convention, pattern, or known issue into the knowledge base (docs/) — triggers on explicit save intent ("remember this", "save this", "document this"), decision or convention announcements ("we decided", "settled on", "the rule is"), or triage output classifying new items to capture. Distinct from conversational memory — this writes to docs/.
Use whenever the user asks about this project's decisions, architecture, conventions, or how something works in this codebase — do NOT answer from general knowledge, always look it up in docs/. Trigger on questions like "why did we choose X?", "how does Y work here?", "what's our convention for Z?", "what docs reference X?", or any question about this project's specific choices. Also use for explicit /autology:explore-knowledge commands (overview, neighborhood, path). Searches docs/, follows wikilinks, and synthesizes grounded answers from the knowledge base.
Use when existing autology docs/ nodes need syncing or updating — when a doc is out of date after a code change, after refactors, when triage identifies existing nodes to verify, or for periodic full audits. Not for new items (use capture) or knowledge questions (use explore).
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Personal Claude Code + Codex dev stack: security hooks, AI-first code conventions, /security-review, /repo-map, /stack-check, portable statusline. Designed to complement other skills-based plugins, not replace them.
Persistent memory system for AI coding sessions — cross-tool memory sharing with 6-dimensional hybrid search
Hand off context to any AI coding agent. Creates comprehensive handoff documents that capture the current task, progress, modified files, and all relevant context needed to seamlessly continue work in any AI assistant (Claude Code, Cursor, Copilot, Aider, etc.).
Mindful AI coding framework — discipline over cleverness. Skill + 21 slash commands + 8 specialist agents + 5 runtime hooks + 15 default checklists + Master Orchestrator + Gravity hub. Works on any model tier (Opus/Sonnet/Haiku). Integrates Claude Design for visual work.
PROJECT.md-first autonomous development with hybrid auto-fix documentation. 8-agent pipeline, auto-orchestration, docs auto-update on commit (true vibe coding). Knowledge base system with 90% faster repeat research. Strict mode enforces SDLC best practices automatically. Works for ANY Python/JavaScript/TypeScript/Go project.
AI-powered knowledge base management - Capture conversation learnings, maintain topic-specific KB files, Obsidian-compatible knowledge graph, structured dynamic context loading, and institutional knowledge in CLAUDE.md
AI tools have made individual developers dramatically more productive — but organizational knowledge is not keeping up.
As each developer moves faster with AI, decisions, conventions, and context become harder to share. Knowledge stays trapped in individual sessions. Teams repeat the same mistakes. New members onboard from docs that don't exist or are already stale.
SessionStart hook
│ injects autology-workflow skill as trigger guidance
↓
Your Work: commit / decision
↑ │
explore triage
(query) │
↑ sync existing and capture new (parallel)
│ │
└───────── docs/*.md
Storage: Obsidian-compatible markdown in docs/ — flat structure, YAML frontmatter, [[wikilinks]]
vs. automemory: automemory is Claude's private, machine-local memory — per-developer, not committed to git, invisible to teammates. Autology is a team knowledge base: typed nodes,
[[wikilinks]]forming a graph, doc-code sync, and git-committed so knowledge compounds across all developers.
/autology:triage-knowledge — Classify Knowledge ItemsScans docs/ against the current action (commit, decision, refactor) and classifies each knowledge item as existing or new, with topology hints.
/autology:sync-knowledge with matched nodes and connected neighbors/autology:capture-knowledge with suggested relations for wikilinks/autology:autology-workflow after every significant action/autology:triage-knowledge # classify after an action
/autology:capture-knowledge — Capture KnowledgeExtracts decisions, conventions, and context from conversation and writes them to docs/*.md.
[[wikilinks]] to related nodes and updates the reverse linksdecision · component · convention · concept · pattern · issue · session/autology:capture-knowledge # extract from current conversation
"remember this" # triggers automatic capture
/autology:explore-knowledge — Navigate the Knowledge GraphTraverses the [[wikilink]] graph — operations that Grep alone cannot do.
| Mode | Command | Use Case |
|---|---|---|
| Graph overview | /autology:explore-knowledge overview | Hub nodes, orphans, connected components |
| Neighborhood | /autology:explore-knowledge <node> | 2-hop expansion — blast radius before refactoring |
| Path finding | /autology:explore-knowledge path A B | Shortest path between two concepts |
/autology:sync-knowledge — Keep Docs in SyncDetects and fixes doc-code drift in-place.
| Mode | Command | Use Case |
|---|---|---|
| Fast | /autology:sync-knowledge | Changed files only — run before every commit |
| Full | /autology:sync-knowledge full | Gaps, broken wikilinks, missing links — periodic audit |
/autology:autology-tutorial — Interactive Tutorial3-act hands-on walkthrough: triage + capture a decision → triage + sync on drift → query the knowledge graph with explore. Runs in a live git branch (~15 minutes).
/autology:autology-tutorial # start from Act 1
/autology:autology-tutorial <1-3> # jump to specific act
/autology:autology-tutorial reset # clean up tutorial branch and docs
Scenario: a team implementing JWT authentication across multiple services.
Without Autology:
Dev A: implements JWT RS256 in 30 min → reasoning lives only in their session
Dev B: "Why JWT? Why RS256 over HS256?" → no answer in the codebase
Dev C: migrates internal service to HS256 → no record of why RS256 was chosen → rationale lost, change undocumented
New hire: reads stale ADRs that don't match the code
With Autology:
Dev A: implements JWT RS256
→ Claude captures automatically:
[decision] JWT RS256 — Context (stateless API), Alternatives (sessions, OAuth),
Consequences (token expiry UX, key rotation ops)
[convention] Always verify JWT expiry before role check (links to → jwt-decision)
Dev B: new session — workflow skill injected at start, Claude knows to check docs/ for decisions
→ /autology:explore-knowledge path jwt-decision api-gateway
→ sees: jwt-decision → auth-middleware → api-gateway (2 hops)
→ implements the new service correctly, no re-research needed