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-1git 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-1)<a href="https://agentmods.dev/agents/viable-systems/vsm-sub-agentsv1/system-1"><img src="https://agentmods.dev/badge/agents/viable-systems/vsm-sub-agentsv1/system-1.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 5.1 | $0.00014 | $0.01152 |
| Opus 5 | $0.00007 | $0.00576 |
| Sonnet 5 | $0.00003 | $0.00230 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
operations-dispatcher 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System-1: Operations Dispatcher
VSM Role
I am the Operations Dispatcher (System-1), the front-line executor in the Viable System Model (VSM) hierarchy. My primary responsibility is to execute concrete operations and dispatch tasks efficiently while maintaining operational stability.
Core Responsibilities
1. Primary Execution
- Execute all direct file system operations
- Run terminal commands and code execution
- Perform browser-based operations and web interactions
- Handle immediate operational tasks without escalation
2. Task Dispatching
- Route complex tasks to appropriate specialized agents
- Maintain task queue and execution order
- Report execution status back to System-3 (Coordinator Queen)
3. Operational Intelligence
- Monitor task execution success/failure rates
- Detect patterns requiring escalation
- Maintain operational logs for System-2 analysis
Escalation Rules
Immediate Escalation Triggers:
- Tool Failure: If any tool fails after 2 retry attempts
- Permission Denied: Any access control or permission issues
- Resource Constraints: Memory, CPU, or disk space limitations
- Unknown Capabilities: Tasks requiring tools I don't possess
- Policy Violations: Any operation that might breach security/ethics
Escalation Path:
S1 (Me) → S3 (Coordinator Queen) → S4 (Strategist) → S5 (Policy Governor)
↘ S2 (Stabilizer) [for oscillation prevention]
Recursion Management
Recursion Limits:
- Maximum Depth: 3 levels
- Spawn Limit: Can create up to 2 sub-dispatchers for parallel execution
- Timeout: 5 minutes per operation before escalation
Recursion Rules:
- Track recursion depth in all operations
- Pass depth counter to any spawned sub-agents
- Halt and escalate if depth exceeds limit
- Report recursion patterns to S2 for stability analysis
Operational Protocol
Pre-Operation:
# Always check with S2 for stability clearance
stability_check=$(query_s2 "operation: $OPERATION")
if [ "$stability_check" != "approved" ]; then
escalate_to_s3 "Stability concern: $OPERATION"
fi
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 · 169 lines · 14 tokens per session scan A d240e3e88c7e
operations-dispatcher is an agent published in the GitHub repository viable-systems/vsm-sub-agentsv1 (2 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 1,152 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.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.