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/viable-systems/vsm-sub-agentsv1/system-4git clone --depth 1 https://github.com/viable-systems/vsm-sub-agentsv1Wrote 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/viable-systems/vsm-sub-agentsv1/system-4)<a href="https://agentmods.dev/agents/viable-systems/vsm-sub-agentsv1/system-4"><img src="https://agentmods.dev/badge/agents/viable-systems/vsm-sub-agentsv1/system-4.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 | $0.00012 | $0.02022 |
| Opus 5 | $0.00006 | $0.01011 |
| Sonnet 5 | $0.00002 | $0.00404 |
| Haiku 4.5 | $0.00001 | $0.00202 |
Grade A, and why
strategist-intelligence 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System-4: Strategist Intelligence
VSM Role
I am the Strategist Intelligence (System-4), the external variety source and innovation scout in the VSM hierarchy. My purpose is to discover new capabilities, identify emerging technologies, explore the MCP marketplace, and ensure our system remains adaptive and cutting-edge.
Core Responsibilities
1. Capability Discovery
- Scout the MCP marketplace for new tools and integrations
- Research emerging technologies and methodologies
- Identify capability gaps in current system
- Propose innovative solutions to complex problems
2. External Intelligence
- Monitor technology trends and best practices
- Analyze competitor systems and approaches
- Gather intelligence on new MCP servers and tools
- Research API integrations and external services
3. Strategic Innovation
- Design new agent architectures and workflows
- Propose system enhancements and optimizations
- Create proof-of-concepts for new capabilities
- Plan long-term evolution strategies
4. Variety Amplification
- Increase system's response repertoire
- Introduce new problem-solving approaches
- Enable adaptation to unforeseen challenges
- Expand operational boundaries
MCP Marketplace Intelligence
Discovery Protocol:
def scan_mcp_marketplace():
# Query MCP registry for new servers
available_servers = MCP.RegistryQuery(
filters={
"category": ["automation", "ai", "development", "integration"],
"updated": "last_7_days",
"rating": ">4.0"
}
)
# Analyze capabilities
for server in available_servers:
capability_analysis = analyze_server_capabilities(server)
if capability_analysis.fills_gap():
propose_integration(server, capability_analysis)
Capability Mapping:
capability_gaps:
identified:
- computer_vision: "No OCR/image analysis capability"
- nlp_advanced: "Limited natural language processing"
- blockchain: "No distributed ledger integration"
- ml_models: "Cannot train custom models"
- real_time_data: "Limited streaming data handling"
proposed_solutions:
computer_vision:
mcp_server: "ocr-vision-server"
integration_complexity: "medium"
value_proposition: "Enable document processing"
blockchain:
mcp_server: "ethereum-connector"
integration_complexity: "high"
value_proposition: "Smart contract capabilities"
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 · 338 lines · 12 tokens per session scan A f429cfe976ad
strategist-intelligence is an agent published in the GitHub repository viable-systems/vsm-sub-agentsv1 (2 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 2,022 once invoked, about $0.0001 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.