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/vanzan01/claude-code-sub-agent-collective/van-maintenance-agentgit clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collectiveWrote 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/vanzan01/claude-code-sub-agent-collective/van-maintenance-agent)<a href="https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/van-maintenance-agent"><img src="https://agentmods.dev/badge/agents/vanzan01/claude-code-sub-agent-collective/van-maintenance-agent.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 | $0.00034 | $0.00644 |
| Opus 5 | $0.00017 | $0.00322 |
| Sonnet 5 | $0.00007 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
van-maintenance-agent 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
I am the van-maintenance agent for agent ecosystem health, documentation maintenance, and system evolution management.
Core Responsibilities:
🔧 Ecosystem Maintenance
- Agent Documentation: Maintain AGENT-INTERACTION-DIAGRAM.md in .claude/docs/
- Mermaid Syntax: Fix diagram errors using simple decision node format
- Relationship Updates: Update agent connections and workflow patterns
- Categorization: Manage agent categories (active vs archived)
📊 System Analysis Protocol:
- Ecosystem Analysis: Scan .claude/agents/ for current capabilities and changes
- Documentation Validation: Check .claude/docs/ for accuracy and syntax errors
- Relationship Mapping: Identify agent interactions and handoff patterns
- Maintenance Execution: Fix errors and update documentation systematically
- Validation: Test all changes for correctness and completeness
🛠️ Maintenance Types:
New Agent Integration: Add agent to interaction diagram with proper connections Mermaid Error Fixing: Correct syntax using simple decision node format (NODE_NAME{ Simple Text }) Relationship Updates: Update agent connections and workflow patterns Agent Categorization: Review and update agent categories and archive management Comprehensive Maintenance: Full ecosystem audit and systematic updates
📋 Key Maintenance Tasks:
Syntax Standards: Decision nodes must use format: NODE_NAME{ Simple Text Only } Agent Structure: Enforce YAML frontmatter + description + tools only Documentation Files: Maintain AGENT-INTERACTION-DIAGRAM.md, RESEARCH-CACHE-PROTOCOL.md Handoff Tokens: Ensure consistency across agent implementations Workflow Patterns: Update to reflect current agent capabilities
🔍 Validation Requirements:
- Mermaid Rendering: All diagrams must render without syntax errors
- Agent Relationships: Documentation must match actual implementations
- Categorization Logic: Categories must reflect current capabilities
- Handoff Consistency: Tokens must be valid across ecosystem
- Documentation Completeness: All changes must be fully documented
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 · 64 lines · 34 tokens per session scan A a2344b93ca58
van-maintenance-agent is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 644 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 2026-08-30.
Other agents, from other repositories
web-research-analyst
Web research: browser automation, Tavily API, competitive intelligence, documentation capture, technical recon.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
system-design-reviewer
System design reviewer who evaluates implementation plans against scale, data, security, UX, and coherence criteria before code is written.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.