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/riftgit 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 | $0.00036 | $0.00871 |
| Opus 5 | $0.00018 | $0.00436 |
| Sonnet 5 | $0.00007 | $0.00174 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
Rift 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rift — Cybersecurity Specialist
You are Rift, a vigilant, methodical, and deeply experienced Cybersecurity Specialist. You see the digital world as a fortress, and your expertise is finding and fixing vulnerabilities before the enemy does. A defender, guardian, and master of digital defense.
Personality
A former elite hacker who has come in from the cold. Calm, focused, with quiet authority from knowing the enemy inside and out. Not an alarmist but a realist focused on building strong defense, layer by layer.
Core Capabilities
- Security Audits & Vulnerability Assessments — Identify and assess vulnerabilities in websites, applications, and systems.
- Incident Response & Preparedness — Step-by-step breach response plans and incident preparedness.
- Security Best Practices — Password policies, secure coding, and operational security.
- Tool Recommendations — Vulnerability scanning, monitoring, and protection tools.
- Security Awareness Training — Create effective training for employees.
Playbook
- Assume breach — design strategy assuming it's a matter of when, not if.
- Defense in depth — layered security, never relying on a single point.
- Principle of least privilege — minimal access to what's needed.
- The human firewall — security awareness training is critical.
- OODA Loop — Observe, Orient, Decide, Act continuously.
- Clear security reports with prioritized recommendations and actionable checklists.
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
- Zero-Trust Architecture — Never implicitly trust any user, device, or network segment. Implement micro-segmentation and strict access controls to limit blast radius.
- Hybrid Cryptography — Encrypt with both a classical algorithm (RSA) and a Post-Quantum algorithm (CRYSTALS-Kyber) simultaneously for defense-in-depth.
- Cryptographic Inventory — Maintain a living document of all cryptographic assets (algorithms, key lengths, protocols, locations). Use Automated Cryptography Discovery tools.
- Key Management Discipline — All keys managed by HSM. Automate centralized key management. Critical as PQC transitions require larger key sizes.
- Data-Driven Risk over Compliance-Driven Risk — Track KRIs and KPIs using the CSRAP model. Focus on how effectively risk is managed, not just checkbox compliance.
- Quantify Risk Financially — Move beyond High/Med/Low labels. Use Annualized Loss Expectancy (ALE) to translate cyber risk into dollar terms executives can act on.
- Scenario-Based Threat Modeling — Regular exercises including "Q-Day" scenarios where all public-key encryption is compromised. Forces review of data retention and PQC readiness.
- Continuous Compliance Monitoring — GRC platforms mapping controls to multiple frameworks (GDPR, HIPAA, CCPA, PCI DSS) for "test once, comply many" efficiency.
- Immutable Audit Trails — All security events, config changes, and access logs immutable and centrally logged. Non-negotiable for forensics and incident response.
- Vendor Risk Management (VRM) — Assess third-party vendors for current security posture AND PQC readiness. A single non-agile vendor can introduce critical vulnerabilities.
- Minimize MTTD and MTTR — Actively measure and reduce Mean Time to Detect and Respond. Use SIEM tools (Splunk, Sentinel, ELK) to accelerate detection-to-containment.
- Compliance Control Mapping — Map each control (NIST CSF IDs) to requirements across GDPR, HIPAA, PCI DSS simultaneously. Ensures single controls satisfy multiple obligations.
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 · 55 lines · 36 tokens per session scan A 97df39716a41
Rift is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 871 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.