By agentflock
Manage engineering leadership workflows from an Obsidian vault: process 1:1s, meetings, email, and Slack; track projects, blockers, and team health; generate briefs, reviews, and communications with structured vault conventions.
Chief of Staff for tech professionals
Customer Skeptic reviewer — INHABITS the user. Walks through any artifact as a real person in a real moment and reports what they would actually do, feel, and decide. Surfaces adoption gaps, trust mis-asks, internal-perspective framing, hidden friction, and mental-model mismatches.
Reviewer subagent that inhabits the artifact's stated audience and tests whether they could act on it. Flags buried leads, vague asks, missing options, audience mismatch, unstated criteria. For docs, emails, claims, updates, proposals.
Principal Engineer reviewer. Invoke when an artifact (proposal, decision, claim, status, plan, message, snippet) needs to be examined for architectural soundness, the bet being made, reversibility, hidden assumptions, failure modes, and decision rigor. Works on any artifact, from a one-line claim to a long memo. Returns structured findings as text.
Product Manager reviewer — reviews any artifact (PRD, launch plan, sprint plan, project plan, roadmap, OKR doc, status update, Slack one-liner) through an execution lens. Asks "can this actually ship, on time, with the resources we have, and will we know if it worked?" Surfaces scope creep, MVP discipline gaps, missing dependencies, vague success metrics, and launch-readiness holes. Input-agnostic. Produces evidence-anchored findings with severities.
Create personal calendar time blocks — focus time, task blocks, deep work. Finds free slots, proposes options, confirms before any write — no attendees, ever. For reminders, use /myna:reminder. Does not handle meeting prep or scheduling others.
Scan the entire vault for blockers — explicit blocker callouts and overdue tasks. Separates your blockers from tasks assigned to others. Use for any blockers query: "what's blocked?", "show me blockers", "any blockers?", "what's holding things up?"
Deep-dive briefing on one person — role, shared projects, open items, pending feedback, 1:1 history, personal notes. Works for directs, peers, manager, or cross-team. (For all directs at once, use /myna:team-health.)
Catch me up on a project — quick (3-5 bullet TL;DR) or full (status, timeline, blockers, tasks, dependencies, upcoming meetings). Use for any project status or update request: "catch me up on X", "status of X", "how is X going", "where are we with X", "what's the latest on X".
Route user input to vault destinations — quick capture, observations, recognition, tasks (single or recurring), project/person file management. One input can produce multiple entries. For saving or finding links, use /myna:links.
Uses power tools
Uses Bash, Write, or Edit tools
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.
The system for everything you're trying to keep in your head. Nothing leaves your machine.
AI Chief of Staff for tech professionals — your projects, your team, your meetings, your email. 31 skills and growing. Runs in Claude Code.
If you manage multiple projects and communication channels — whether you're an engineering manager, software developer, PM, or team lead — you spend too much of your day on information management. Triaging emails, prepping for meetings, tracking who owes what, remembering what was decided three weeks ago.
Most AI tools either start fresh every session or store your data on someone else's server. Myna does neither. It reads from your existing tools, writes to local files, and builds a persistent knowledge base — your projects, people, decisions, and preferences — that grows as you use it.
Drafts but never sends. Organizes but never decides. Surfaces but never hides.
Myna runs inside Claude Code. Here's what role-specific skills and a local knowledge base add:
| AI Chat Tools (Claude, ChatGPT, Gemini) | Local AI Tools (Khoj, Fabric, PrivateGPT) | Myna | |
|---|---|---|---|
| Built for | General-purpose | Q&A over your notes | Your workday — morning sync, meeting prep, email triage, project catch-up |
| Your data | Platform memory, general-purpose | Your existing notes, unstructured | Your projects, people, and meetings — organized as you work |
| What it creates | Chat and generated documents | Answers about your notes | Drafts, meeting prep, project briefs, daily notes — files you review before using |
| How it works | You direct every step | One question, one answer | One prompt — Myna routes, updates, and files content across your vault |
| Integrations | Whatever you describe | Your local files | Email, Slack, and calendar via MCPs — whatever your team already uses |
| Learns your style | Custom instructions | What's in your notes | Your preferences, communication style, and working habits — persists across sessions |
| When unsure | Asks in chat, gone if you miss it | Best guess from your notes | Persistent review queue — nothing resolves without your approval |
| Customizable | Settings and custom GPTs | Config file or source code | Every skill is a plain-text file you can read, edit, or replace |
A day in the life of an Engineering Manager using Myna:
7:45 AM — coffee, laptop open
> sync
↳ Daily note created. Phoenix blocker flagged. Sarah Mitchell's reply overdue.
8:10 AM — before your 9am 1:1
> prep for my 1:1 with Marcus
↳ Open items from last time, pending feedback with coaching notes,
parental leave thread — all in one brief.
9:35 AM — back from the 1:1
> done with 1:1 with Marcus
↳ Tasks, decisions, observations extracted and routed to the right files.
9:50 AM — quick multi-thing capture
> capture: Sarah handled Payments questions well, atlas is unblocked,
review Sentinel audit by Friday
↳ 3 items → 3 files. Recognition, timeline update, task with due date.
12:45 PM — VP wants a risk note
> draft the Phoenix risk note for the VP review
↳ Leads with the conclusion, evidence-grounded, under 200 words.
Ready for you to review, then send yourself.
1:15 PM — pre-read for tomorrow's staff meeting
> review this PRFAQ [paste]
↳ 7 personas in parallel — Product Leader, PM, Customer Skeptic, PE,
Security, Skeptic, Writer/Editor — synthesized into one report.
Saved to Reviews/2026-05-26-pricing-prfaq.md.
3:45 PM — the ambiguous pile
> review my queue
↳ Items Myna wasn't sure about — you approve, redirect, or dismiss.
5:30 PM — close the day
> wrap up
↳ Planned vs actual. Contributions logged. Tomorrow's note created with carry-forwards.
Not an EM? The skills work for anyone managing projects and communication — software developers, PMs, team leads.
Full walkthrough: A Day With Myna · Browse the demo vault to see the files Myna creates
Prerequisites: Claude Code · Obsidian (recommended but not required — all files are plain text, viewable in any editor) · Python 3 (required for the Config UI setup path)
Run these commands inside Claude Code:
npx claudepluginhub bathlasiddharth/myna --plugin mynaUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Create and edit Obsidian vault files including Markdown, Bases, and Canvas. Use when working with .md, .base, or .canvas files in an Obsidian vault.