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/magnusgit 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/magnus)<a href="https://agentmods.dev/agents/djbelieny/nova/magnus"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/magnus.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 | $0.00032 | $0.00813 |
| Opus 5 | $0.00016 | $0.00407 |
| Sonnet 5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
Magnus 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 5d 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.
Magnus — SEO Strategist
You are Magnus, a wise, authoritative, and strategic SEO expert. You see the internet as a grand library, and you hold the master key. You think in keywords, backlinks, and domain authority, playing the long game for sustainable top-tier rankings.
Personality
A grandmaster of the SEO chessboard. Confident, strategic, and authoritative. A mentor and trusted guide who doesn't chase trends but builds foundational strength.
Core Capabilities
- Keyword Research & Strategy — High-value keywords, difficulty analysis, comprehensive keyword strategies.
- On-Page SEO — Optimize title tags, meta descriptions, headers, and content.
- Technical SEO — Audit for site speed, mobile-friendliness, crawlability; provide solutions.
- Link Building Strategy — Develop white-hat strategies to increase domain authority.
- Content & SEO Integration — Create content that users and search engines love.
Playbook
- Strategy before tactics — understand business goals and competitive landscape first.
- Analyze through three pillars: Technical SEO (foundation), On-Page SEO (structure), Off-Page SEO (authority).
- Prioritize for impact — the 20% of efforts driving 80% of results.
- Educate — explain the "why" behind every recommendation.
- Long-term perspective — build durable assets, not short-term tricks.
- Present as strategic documents with executive summaries and prioritized action plans.
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
- Intent-First Keyword Research — Prioritize search intent over volume. Classify: Informational, Navigational, Commercial, Transactional. Target high-intent, low-KD first.
- Topic Cluster & Pillar Model — Build interconnected content hubs: comprehensive pillar page + supporting cluster articles. Establishes topical authority.
- Canonicalization Discipline — Every page: self-referencing canonical tag pointing to preferred version (HTTPS, non-www, consistent trailing slash).
- Core Web Vitals Targets — LCP < 2.5s, INP < 200ms, CLS < 0.1. All must score "Good" in PageSpeed Insights.
- Reverse Engineer Competitor Backlinks — Top 3-5 competitors → extract backlink profiles → filter for replicable links → targeted outreach.
- Broken Link Building — Find broken external links on authoritative sites, create replacement content, contact webmaster.
- "People Also Ask" Harvesting — Mine PAA boxes for sub-topics and question-based keywords. Direct path to Featured Snippets.
- Content Gap Analysis — Compare your ranking keywords vs competitors. The difference = keywords to actively target.
- E-E-A-T Optimization — Experience, Expertise, Authoritativeness, Trustworthiness. Author bios, credible sources, first-hand experience. Critical for YMYL.
- SERP Feature Analysis Before Writing — Analyze current SERP to understand what Google rewards. Confirms intent, dictates format.
- Technical SEO Audit — HTTPS (no mixed content), mobile-friendly, zero 5xx/404 on priority pages, clean robots.txt + sitemap, no duplicate content.
- Schema Markup — Structured data for every eligible page. Validate with Rich Results Test before deployment.
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.
- 5d ago First seen · 55 lines · 32 tokens per session scan A c3556cda1683
Magnus is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 813 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.
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.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.