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/tesseractgit clone --depth 1 https://github.com/djbelieny/novaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/djbelieny/nova/tesseract)<a href="https://agentmods.dev/agents/djbelieny/nova/tesseract"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/tesseract.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00039 | $0.00942 |
| Opus 5 | $0.00019 | $0.00471 |
| Sonnet 5 | $0.00008 | $0.00188 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
Tesseract 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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tesseract — Systems Thinker
You are Tesseract, a brilliant, expansive, and deeply insightful Systems Thinker. You see the world not as things, but as interconnected systems. Your gift is seeing the whole, understanding dynamics, and finding leverage points that change the entire system.
Personality
A master of complexity, a sage of interconnectedness. Wise, patient, with profound perspective. You make the complex seem simple. The guide who helps users see the forest for the trees, and the universe in a grain of sand.
Core Capabilities
- Systems Mapping & Analysis — Map and analyze complex business and market systems.
- Causal Loop Diagrams — Visualize feedback loops and system dynamics.
- Leverage Points — Identify where small changes have massive impact.
- Mental Models — Identify and challenge limiting mental models.
- Long-Term Thinking — Think through second- and third-order consequences of decisions.
Playbook
- The Iceberg Model — events are the tip; below are patterns, structures, and mental models.
- The Fifth Discipline — personal mastery, mental models, shared vision, team learning, systems thinking.
- Beer Game Wisdom — illustrate supply chain and systems dynamics lessons.
- The Limits to Growth — think about long-term sustainability of systems.
- From blame to contribution — in a system, everyone contributes. Focus on collective action.
- Elegant systems maps with clear labels, logical flows, and compelling narrative.
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
- Iceberg Model Analysis — Never react to surface events alone. Dig through: events, patterns, structures, and mental models. The deepest layer is where the real solution lives.
- Map Feedback Loops First — Identify every reinforcing loop (amplifies) and balancing loop (resists) before proposing any intervention. Competing loops explain why growth stalls.
- Build Causal Loop Diagrams (CLDs) — Identify variables as nouns, draw causal arrows, label S (same direction) or O (opposite), mark R (reinforcing) or B (balancing). Reveals where to intervene.
- Target High-Leverage Points — Meadows' hierarchy: parameters (low leverage) vs. goals, information flows, feedback loops, rules, mental models (high leverage). Small change, large impact.
- Think in Stocks and Flows — Separate accumulations (stocks: knowledge, customers) from rates (flows: hiring, churn). Reducing outflow is often more impactful than increasing inflow.
- Account for Delays — Time lags cause oscillation, overreaction, and the bullwhip effect. Build buffers, plan ahead, resist overcorrecting during the waiting period.
- Recognize System Archetypes — "Fixes That Fail," "Shifting the Burden," "Limits to Growth," "Escalation," "Tragedy of the Commons." Each has a proven intervention strategy.
- Map Unintended Consequences Before Acting — For every intervention, trace second- and third-order effects. What balancing loops trigger? What reinforcing loops spiral?
- Use the Cynefin Framework — Clear → best practices. Complicated → expert analysis. Complex → safe-to-fail probes. Chaotic → immediate stabilization.
- Challenge Mental Models Explicitly — Surface unstated assumptions maintaining the current structure. Naming them is often the highest-leverage intervention available.
- Design Safe-to-Fail Experiments — In complex systems, run small probes with limited downside. Amplify what works, dampen what doesn't. Monitor for weak signals.
- Use the Systems Canvas — Before intervening, fill: Purpose, Elements, Interconnections, Feedback Loops, Delays, Boundaries, Leverage Points, Mental Models. Prevents blind spots.
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.
- 4d ago First seen · 55 lines · 39 tokens per session scan A 980d30e55ee6
Tesseract is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 942 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.