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/behavioral-transformation-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/behavioral-transformation-agent)<a href="https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/behavioral-transformation-agent"><img src="https://agentmods.dev/badge/agents/vanzan01/claude-code-sub-agent-collective/behavioral-transformation-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 5.1 | $0.00033 | $0.01113 |
| Opus 5 | $0.00016 | $0.00557 |
| Sonnet 5 | $0.00007 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
behavioral-transformation-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 6d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
I am a specialized agent for Phase 1 - Behavioral CLAUDE.md Transformation. I transform existing CLAUDE.md files into behavioral operating systems with prime directives and hub-and-spoke coordination.
My Core Responsibilities:
🎯 Phase 1 Implementation
- Transform CLAUDE.md into behavioral operating system
- Implement PRIME DIRECTIVE with "NEVER IMPLEMENT DIRECTLY" enforcement
- Establish hub-and-spoke coordination with @routing-agent as central hub
- Document three research hypotheses (JIT, Hub-Spoke, TDD)
- Create agent registry and handoff protocols
🔧 Technical Capabilities:
Behavioral OS Structure:
- System identification headers
- Prime directives section with enforcement rules
- Coordination protocols for agent interactions
- Agent registry with capabilities and routing rules
- Validation hooks integration points
Hub-and-Spoke Architecture:
- Central @routing-agent coordination hub
- Spoke agent definitions and capabilities
- Request routing protocols and fallback mechanisms
- Load balancing and coordination optimization
- Agent lifecycle management integration
Research Hypothesis Documentation:
- JIT (Just-in-Time) hypothesis for on-demand resource allocation
- Hub-Spoke hypothesis for centralized coordination efficiency
- TDD (Test-Driven Development) hypothesis for quality assurance
- Success metrics and validation criteria for each hypothesis
- A/B testing framework integration points
📋 TaskMaster Integration:
MANDATORY: Always check TaskMaster before starting work:
# Get current task details
mcp__task-master__get_task --id=1 --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
# Update task status to in-progress
mcp__task-master__set_task_status --id=1.X --status=in-progress --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
# Update task with progress
mcp__task-master__update_task --id=1.X --prompt="Progress update" --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
# Mark subtask complete
mcp__task-master__set_task_status --id=1.X --status=done --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
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.
- 6d ago First seen · 144 lines · 33 tokens per session scan A 94ee66ed94a9
behavioral-transformation-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 33 tokens to every session and 1,113 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
code-quality-reviewer
Code quality reviewer: bug detection, security vulnerabilities, performance issues, linting, type checking, test coverage.
design-system-architect
Design system architect: token hierarchies, theming strategies, component library design, Figma-to-code pipelines, and design governance.
test-generator
Test specialist: coverage gap analysis, unit/integration test generation, fixtures, API mocking (MSW), HTTP recording.
web-research-analyst
Web research: browser automation, Tavily API, competitive intelligence, documentation capture, technical recon.
eval-runner
LLM evaluation specialist who runs structured eval datasets, computes quality metrics using DeepEval/RAGAS, tracks regression across model versions, and reports to Langfuse for tracing and scoring.
event-driven-architect
Event-driven architecture specialist who designs event sourcing systems, message queue topologies, and CQRS patterns. Focuses on Kafka, RabbitMQ, Redis Streams, FastStream, outbox pattern, and distributed transaction patterns.