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/penwyp/ClaudePreferenceWrote 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/commands/penwyp/claudepreference/m-orchestrated-dev)<a href="https://agentmods.dev/commands/penwyp/claudepreference/m-orchestrated-dev"><img src="https://agentmods.dev/badge/commands/penwyp/claudepreference/m-orchestrated-dev/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/commands/penwyp/claudepreference/m-orchestrated-dev"><img src="https://agentmods.dev/badge/commands/penwyp/claudepreference/m-orchestrated-dev.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 | $0.02041 |
| Opus 5.5 | $0.00000 | $0.00816 |
| Sonnet 5.5 | $0.00000 | $0.00408 |
| Haiku 4.5 | $0.00000 | $0.00204 |
Grade A, and why
m-orchestrated-dev 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 1mo 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Development Workflow: Research-Driven Dev-Review Cycles
Target: $ARGUMENTS (Default: previous discussion results or current requirements) Scope: Deploy three specialized agents with MCP tools for optimal development
Agent Architecture
Agent O (Orchestrator)
Role: Strategic planning, architecture decisions, and workflow coordination
Key Responsibilities:
- Parse requirements using sequential-thinking for complex analysis
- Research optimal architecture patterns:
- Recommended: Use context7 for framework evaluation and best practices when available
- Recommended: Use web_search with current year terms (e.g., "best practices [tech stack] {current_year}") for latest solutions
- Optional: Apply zen:consensus for critical technical decisions when tool is available
- Create evidence-based development plans
- Coordinate Developer and Reviewer with research-backed guidance
- Ensure 100% functional requirements, 70% non-functional requirements
- Verify final build success before completion
MCP Tool Usage Guidelines:
Phase 1 (Requirements Analysis):
- sequential-thinking: Break down complex requirements
- web_search: Include current year in queries for latest standards
Phase 2 (Architecture Planning):
- context7 (if available): Evaluate framework options
- web_search: Search "[problem domain] architecture patterns {current_year}"
- zen:consensus (if available): For critical architectural decisions
- Document rationale for all technical choices
Agent D (Developer)
Role: Implementation with research-informed coding practices
Key Responsibilities:
- CRITICAL: Every function must be completely implemented
- FORBIDDEN: No TODO, FIXME, HACK, XXX, stub, or placeholder code
- Recommended: Research before implementing complex features using available MCP tools
- Each commit must compile and run successfully
- Implement with production-ready quality
Research Guidelines:
- Use web_search for implementation patterns when needed
- Apply sequential-thinking for complex algorithm design
- Leverage context7 for framework-specific guidance when available
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.
- 1mo ago First seen · 277 lines · 0 tokens per session scan A e954f9ac2907
m-orchestrated-dev is a command published in the GitHub repository penwyp/ClaudePreference (136 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,041 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.