ceo
claudeAutonomous CEO agent. Reads Obsidian vault, dispatches 6 specialized subagents, 8 playbooks, 7 skills, cron execution pipeline with three-phase tier enforcement. CLI with setup/doctor/test.
8 skills
Obsidian vault integration for Claude Code. Auto-capture git commits, save sessions, query past work with /recall, export conversations. Supports user-defined VAULT.md conventions.
Plugin obsidian from marketplace nhangen-tools in nhangen/claude-plugins. Commands read from the repo's manifest — 4 days 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.
obsidian-mcpUse the Obsidian MCP adapter for bounded vault reads, commit metadata, and opt-in guarded writes.
commit-captureCapture Codex conversation context in Obsidian immediately after every successful git commit. Use this installed skill after a commit succeeds; never use it for failed commits, dry runs, or non-commit Git commands. It obtains safe metadata through its bundled commit-meta.sh and writes through its bu
setupSet up Obsidian for Codex with a verified public runtime and bundled MCP connections, or preview separately authorized user-wide capture activation. Runtime, connection, capture and hook trust remain separate gates.
askAsk the Obsidian vault librarian a question or file new information into the vault. Triggers on "ask my vault", "what do we know about X", "where in my vault is Y", "what did I decide about Z", "remember this in obsidian", "file this note". Dispatches the vault-librarian subagent for index-grounded
create-noteCreates a new note, project folder, or page in the Obsidian vault. Triggers on phrases like "create a note about X", "start a new project for Y", "add a page for Z", "new obsidian note", "create project folder", "set up a new project in obsidian".
daily-noteReads, creates, or appends to the Obsidian daily note. Triggers on phrases like "add to my daily note", "update today's note", "what's in my daily note", "open today's note", "daily note", "log this to today".
find-notesSearches the Obsidian vault and returns matching notes. Triggers on phrases like "find my notes on X", "what did I write about Y", "search obsidian for Z", "do I have any notes about", "find in vault", "look up in obsidian".
keeper-saveAgent-facing entry point for filing or appending a structured note through the vault keeper. Triggers when another agent or skill needs to persist a note — findings, decisions, observations, research results, daily-log entries — into the vault without back-and-forth. Humans use /obsidian:ask instead
recallMulti-source context recall. Searches Obsidian vault, git history, GitHub PRs, and claude-mem, then synthesizes a timeline report.
reorganizeReorganizes the Obsidian vault or a specific project. Triggers on phrases like "reorganize my vault", "clean up obsidian", "move X to Y in obsidian", "reorganize my notes", "restructure my projects", "organize the vault". Launches the vault-organizer subagent for deep analysis and execution.
save-conversationExports the current Claude conversation to the Obsidian vault. Triggers on phrases like "save this to Obsidian", "export to obsidian", "document this session", "save our conversation", "write this up", "put this in obsidian". Formats the conversation as structured markdown, determines the correct pr
/obsidian:askAsk the Obsidian vault librarian (query or file info). Usage: /obsidian:ask <question or note>
/obsidian:bookmarkDrop a chapter bookmark in the current session. The session-end hook will save each bookmarked segment as a separate note. Usage: /obsidian:bookmark [label]
/obsidian:dailyOpen or append to today's Obsidian daily note. Usage: /obsidian:daily [content to append]
/obsidian:findSearch the Obsidian vault. Usage: /obsidian:find <query>
/obsidian:newCreate a new note or project in Obsidian. Usage: /obsidian:new <title>
/obsidian:recallRecall context about past work. Searches vault, git history, GitHub PRs, and claude-mem. Usage: /obsidian:recall <query>
/obsidian:saveSave the current Claude session to Obsidian. Optional topic hint overrides auto-routing. Usage: /obsidian:save [topic]
/obsidian:setupFirst-time setup wizard for the Obsidian plugin. Configures vault path, domain taxonomy, and routing rules, then writes obsidian.local.md. Usage: /obsidian:setup
vault-librarianObsidian vault librarian. Answers index-grounded vault queries with citations and confidence, files new information into the right folder + INDEX, and appends timestamped sections to dated notes — all without back-and-forth. Maintains the markdown INDEX layer with on-demand two-stage freshness. Neve
vault-organizerSpecialized subagent for deep Obsidian vault analysis and reorganization. Analyzes the full vault file tree, identifies structural issues (orphaned notes, misplaced files, near-duplicate content, empty folders), proposes a reorganization plan, waits for user approval, then executes moves with a roll
bash "${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook.sh" SessionStart
bash "${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook.sh" Stop
bash "${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook.sh" PreToolUse
bash "${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook.sh" PostToolUse
bash "${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook.sh" UserPromptSubmit
bash "${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook.sh" PostToolUseFailure
bash "${CLAUDE_PLUGIN_ROOT}/scripts/capture-hook.sh" StopFailure
Autonomous CEO agent. Reads Obsidian vault, dispatches 6 specialized subagents, 8 playbooks, 7 skills, cron execution pipeline with three-phase tier enforcement. CLI with setup/doctor/test.
8 skills
Dispatch long-running research tasks to the Manus AI agent platform from Claude Code via slash command. SessionStart + Stop hooks surface newly-completed tasks both on next session and mid-conversation (zero extra Claude turns). Retrieves file deliverables from their signed CDN links, so a task whose payload is an attachment no longer looks complete with the payload missing. On-demand polling, optional Obsidian filing, explicit-invocation cost gating.
3 commands · hooks
Source-grounded project glossary. Auto-invokes when the agent encounters an unfamiliar acronym or project-specific term in a registered repo: resolves the current cwd to a domain via per-machine config (with git-worktree fallback), reads the matching glossary, and answers cited rather than guessing. Also handles seed (build candidates from commits / GitNexus / docs) and drift-check (verify every citation still resolves).
1 skill · 1 command
Behavioral markdown documentation scanner. Analyzes session history to find gaps in CLAUDE.md, rules, memory, and project settings. Detects repeated file reads, command failures, recurring user corrections, allowlist gaps, unused CLAUDE.md sections, documented-but-still-re-read paths, and Cursor↔Claude rule drift. Guided walkthrough to approve/skip/defer recommendations.
1 skill · hooks
Auto-compact when context fill crosses thresholds. Stop-hook gate computes fill % from the live transcript; fires an advisory at 35% and escalated nudge at 50%, both directing /compact. Context-window divisor is a dynamic var (CONTEXT_LOOP_WINDOW override; falls back to Opus 1M / other 200K heuristic).
1 skill
Token spend analytics and cost alerts for Claude Code. 16 report modes including weekly credit consumption against your plan cap, cache intelligence, tooling analysis by layer, per-artifact Write/Edit cost analytics, and a credit-denominated auto-checkpoint hook.
1 skill
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
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.