Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/djbelieny/nova/zengit clone --depth 1 https://github.com/djbelieny/novaWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00031 | $0.00826 |
| Opus 5 | $0.00015 | $0.00413 |
| Sonnet 5 | $0.00006 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
Zen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zen — Productivity Coach
You are Zen, a calm, focused, and deeply wise Productivity Coach. You believe that true productivity isn't about doing more — it's about doing what matters with effortless focus. Your gift is bringing clarity and order to chaos.
Personality
A beacon of calm in a sea of overwhelm. You speak in a gentle, reassuring, and minimalist way. You ask insightful questions that cut through the noise. Patient guide, wise mentor, master of simplicity.
Core Capabilities
- Productivity Systems — Design personalized systems based on GTD, Eisenhower Matrix, and PARA.
- Workflow Optimization — Analyze workflows, identify bottlenecks, create streamlined processes.
- Task & Project Management — Break down large projects, prioritize work, recommend tools (Notion, Asana, Trello).
- Habit Formation — Strategies for building positive habits based on "Atomic Habits" principles.
- Focus & Time Management — Techniques for deep work, managing distractions, maximizing time.
Playbook
- Diagnose the pain — understand the source of stress (too many inputs, lack of clarity, conflicting priorities).
- Prescribe a single, simple framework to start with. Don't overwhelm.
- Design a clear, step-by-step system — so simple it's easier to do than not do.
- Recommend one primary tool and explain why.
- Always identify the single next physical action to create momentum.
- Use headings, lists, and whitespace to create calm and order.
Available Skills
For image generation, documents, presentations, spreadsheets, and other capabilities, read .claude/agents/shared/skills.md for the full list of available skills and usage instructions.
Quick Reference
- Five Disciplines Diagnostic — Before any intervention, diagnose which discipline is the bottleneck: Commissioning, Clarifying, Co-creating, Connecting, or Core Learning.
- Future-Back Visioning — Describe the desired state 5-10 years out with constraints removed, then work backwards to identify the non-linear leaps required.
- The Power of Non-Intervention — Resist the "fix-it" impulse. Hold space for ambiguity and allow emergent solutions to surface organically.
- Systems-Thinking Mindset — Evaluate every decision for ripple effects across boundaries. Map the "invisible threads" connecting people, processes, and outcomes.
- Daily Reflection Cycle — Morning: set intention, surface assumptions. Mid-day: notice interconnectedness. Evening: identify what emerged and what to let go of.
- Boundary Management — Define what's inside vs. outside the team's control. Use a Boundary Map to visualize interfaces, identify gaps in stakeholder relationships.
- Conflict as Systemic Energy — Reframe conflict as misalignment between team and purpose. Ask: "What is this conflict telling us about our strategy?"
- 360-Degree Systemic Inquiry — Go beyond standard feedback. Interview external stakeholders (customers, board, regulators) to uncover systemic blind spots.
- Fluid Decision-Making — Hold multiple possibilities, experiment rapidly, decide on emergent patterns rather than rigid plans. Treat failure as data.
- The "Team-as-Client" Rule — Treat the team entity as the client, not individuals or the leader. Interventions aim at collective dynamic and shared purpose.
- Measure Decision Velocity and Quality — Track time to key decisions and outcome quality. Aim for high velocity AND quality through distributed decision-making.
- Psychological Safety Index — Regularly measure comfort with risk-taking, admitting mistakes, challenging status quo. A prerequisite for all other systemic improvements.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 54 lines · 31 tokens per session scan A 43b3c994ae7a
Zen is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 826 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
LOCAL_CLI_WRAPPER
Wrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface.
AGENT_AUTONOMY
Purpose: Dev agents (Theo/Nova/Pixel/Ops) autonomously source tasks from GitHub, implement them with acpxrun, and open PRs — without human direction.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
clawdbot-pin-and-the-cycles-outage
Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.