Client context system — file-first wiki with project-scoped auto-priming, meeting ingestion, and Obsidian-compatible knowledge graph.
File a document into the context vault with links
End-of-session context capture — ensure nothing important is lost
Complete system guide — commands, lifecycle, entity model, conventions
Process a Fireflies meeting into the context vault
Comprehensive context vault maintenance — structural audit, entity health, relationship integrity, and archive cleanup
Load project context from the context vault at session start
Generate a session briefing from context vault data
Update context vault pages after changes during a session
Initialize the context system in a client project
No model invocation
Executes directly as bash, bypassing the AI model
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugins for client project management — context tracking, meeting ingestion, and persistent knowledge graphs.
| Plugin | Prefix | Description |
|---|---|---|
| client-ctx-sys | /ctx:* | File-first wiki for client context with auto-priming, Fireflies ingestion, and Obsidian-compatible knowledge graph |
claude plugin install client-ctx-sys@client-mgt-market
Client work compounds context. Every meeting produces decisions, action items, and shifting priorities. Every session needs the full picture — who said what, what was decided, what's still open. Without a system, context lives in your head or scattered across chat logs. Claude starts every session cold.
This plugin adds a persistent context layer. Meetings go in, entities come out, and every future session starts fully primed.
/ctx:init # scaffold the context vault + rules
/ctx:project sales-command # add a project
/ctx:ingest --latest # pull latest Fireflies meeting
/ctx:prime sales-command # deep briefing on a project
Run /ctx:help for the full reference.
The context vault is a markdown wiki at context-vault/ in the client project root. No database, no CLI — Claude reads and writes files directly.
context-vault/
├── index.md # Master navigation
├── log.md # Chronological ingest history
├── config.yaml # Client name, Fireflies config
├── dashboard.base # Obsidian live dashboard
├── projects/
│ └── {slug}/ctx-{slug}.md # Project prime pages
├── decisions/ # Architectural and strategic choices
├── action-items/ # Tracked tasks with owner + status
├── strategies/ # Approach frameworks
├── requirements/ # Hard constraints
├── people/ # Participants with linked entities
└── docs/
├── meetings/ # Meeting records with backlinks
├── client-docs/ # Documents from the client
└── deliverables/ # Documents produced for the client
Everything connects via Obsidian-compatible wikilinks: [[decisions/auth-strategy|Auth Strategy]]. The vault is a knowledge graph, not a flat folder of notes.
Two mechanisms fire automatically — no commands needed:
.claude/rules/context-vault.md) — tells Claude the vault exists and how to use it. Every session..claude/rules/project-{slug}.md) — when Claude opens files in a project directory, the rule fires and loads that project's context page.Claude starts every session already oriented. The context-prime skill supports this silently in the background.
The primary input pipeline. A single command pulls a Fireflies transcript, extracts entities, and wires them into the knowledge graph:
/ctx:ingest https://app.fireflies.ai/view/...
What comes out:
All changes are proposed and require approval before writing.
| Command | What It Does |
|---|---|
/ctx:init | Scaffold the vault, install rules, configure statusline. Idempotent. |
/ctx:project <name> | Add a project — vault page + auto-prime rule + directory |
| Command | What It Does |
|---|---|
/ctx:ingest <url|--latest> | Pull a Fireflies meeting, extract entities, update the graph |
/ctx:catalog <path> | File a document into the vault with category and project links |
| Command | What It Does |
|---|---|
/ctx:prime <target> | Deep context assembly — project, person, topic, or meeting |
/ctx:status | Quick vault briefing — open items, project inventory, recent activity |
Prime vs Status: Status is broad and shallow ("what needs attention across everything?"). Prime is narrow and deep ("tell me everything about THIS").
| Command | What It Does |
|---|---|
/ctx:convo | End-of-session capture — file decisions, action items, status changes |
| Command | What It Does |
|---|---|
/ctx:maintain | 5-phase vault audit — structure, entities, relationships, archive, report |
/ctx:help | Full system reference |
npx claudepluginhub rugved-rakebma/client-mgt-market --plugin client-ctx-sysUnified web content extraction — static pages, video transcripts, and JS-rendered deep crawls
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Make your AI agent code with your project's architecture, rules, and decisions.