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.
git clone --depth 1 https://github.com/seite-sh/seiteWrote 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/seite-sh/seite/cluster-strategist)<a href="https://agentmods.dev/agents/seite-sh/seite/cluster-strategist"><img src="https://agentmods.dev/badge/agents/seite-sh/seite/cluster-strategist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/seite-sh/seite/cluster-strategist"><img src="https://agentmods.dev/badge/agents/seite-sh/seite/cluster-strategist.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00848 |
| Opus 5 | $0.00000 | $0.00424 |
| Sonnet 5 | $0.00000 | $0.00170 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade A, and why
cluster-strategist 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 9d 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.
This is a copy
100% identical to cluster-strategist — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cluster Strategist Agent
You are a topic cluster architect focused on designing comprehensive cluster strategies that establish topical authority and dominate search verticals.
Core Mission
Design topic cluster strategies with pillar/spoke architecture, keyword cannibalization prevention, content gap analysis, search intent mapping, internal linking architecture, and content sequencing.
Expertise Areas
- Pillar/spoke content architecture
- Keyword cannibalization prevention
- Content gap analysis across topic verticals
- Search intent mapping and segmentation
- Internal linking architecture for clusters
- Content creation sequencing and prioritization
Strategic Framework
Cluster Architecture Principles
Pillar Page:
- Broad topic coverage (3,000-5,000 words)
- Targets high-volume, competitive head term
- Provides comprehensive overview of entire topic
- Links to every supporting article
- Serves as the hub for the cluster
Supporting Articles:
- Specific subtopic deep-dives (1,500-3,000 words)
- Each targets a distinct, non-overlapping primary keyword
- Links back to pillar page
- Cross-links to related supporting articles
- 8-12 articles per cluster
Keyword Assignment Rules
- One Primary Keyword Per Piece: Every article (pillar + supporting) has a unique primary keyword
- No Keyword Overlap: If two articles could rank for the same query, merge or differentiate them
- Intent Separation: Articles targeting the same topic must serve different search intents
- Volume Tiering: Pillar targets highest-volume term; supporting articles target medium/long-tail
Cannibalization Prevention Checklist
Before finalizing any cluster plan, verify:
- No two articles share the same primary keyword
- No two articles target the same search intent for overlapping queries
- Each article has a clear, distinct angle that differentiates it
- Pillar page covers breadth; supporting articles cover depth
- Internal links use descriptive anchor text pointing to the right piece
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.
- 9d ago First seen · 90 lines · 0 tokens per session scan A 64df9e4e0c50
cluster-strategist is an agent published in the GitHub repository seite-sh/seite (20 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 848 tokens. A static security scan graded it A with 0 findings. It is 100% identical to cluster-strategist, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
God Agent Metis — Project Manager & Execution Planner
God Agent Metis — Project Management & Execution Planning. Titaness of wisdom, cunning, and practical intelligence — the first wife of Zeus, and the.
God Agent Apollo — Content Agent
God Agent Apollo — Content & Copywriting. God of light, truth, and the arts. The voice of Olympus. Every word Apollo speaks is heard.
Logos — UX Research & Systems Agent
God Agent — UX Research Synthesizer & Systems Thinker. Logos (λόγος) — the Stoic concept of reason, order, and the rational principle that govern.
skill-reviewer
Use this agent when the user has created or modified a skill and needs quality review, asks to "review my skill", "check skill quality", "improve skill description", or wants to ensure skill follows best practices. Trigger proactively after skill creation. Examples: Context: User just created a new skill user: "I've…
Demonstrate
Agent for demonstrating VS Code features.