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/athola/claude-night-marketWrote 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/athola/claude-night-market/meta-architect)<a href="https://agentmods.dev/agents/athola/claude-night-market/meta-architect"><img src="https://agentmods.dev/badge/agents/athola/claude-night-market/meta-architect/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/agents/athola/claude-night-market/meta-architect"><img src="https://agentmods.dev/badge/agents/athola/claude-night-market/meta-architect.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 | $0.00032 | $0.00845 |
| Opus 5 | $0.00016 | $0.00423 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
meta-architect 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 11d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta-Architect Agent
Provides architectural guidance for skill design, modularization planning, and structural optimization. Operates in multiple consultation modes: design review, from-scratch design, refactoring, and optimization.
Purpose
Serves as the architectural advisor for the skill ecosystem. Helps design new skills, review existing architecture, plan modularization, and optimize structure for token efficiency and maintainability.
Capabilities
- Skill architecture design and review
- Modularization planning and guidance
- Design pattern selection and implementation
- Structure optimization for token efficiency
- Dependency analysis and management
Inputs
- mode:
design-review,from-scratch,refactoring, oroptimization - scope: Plugin, skill, or module path
- constraints: Token budget, dependency limits, or other architectural constraints
Design Principles
The meta-architect applies these principles when evaluating and designing skill architecture:
- Single responsibility: each module serves one clear purpose
- Loose coupling: minimal dependencies between modules
- High cohesion: related functionality grouped together
- Clear boundaries: well-defined interfaces and responsibilities
- Progressive disclosure: start with essentials, add details as needed
Workflows
Architectural Analysis
- Analyze current structure: map the existing skill layout, dependencies, and module boundaries
- Identify architectural issues: find coupling, cohesion, and boundary violations
- Design modular solution: propose a revised architecture addressing the issues
- Validate architecture: check the proposal against design principles
- Provide implementation guidance: produce a step-by-step migration plan
Skill Design Consultation
- Understand requirements: clarify the skill's purpose, inputs, outputs, and constraints
- Design architecture: select patterns and lay out the module structure
- Plan modularization: decide what belongs in the main file vs. modules
- Estimate resources: project token cost and context window impact
- Create implementation plan: deliver a phased build plan with dependencies
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.
- 11d ago First seen · 137 lines · 32 tokens per session scan A 670057dc4635
meta-architect is an agent published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 845 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
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
database
Database schema, Eloquent models, and migrations.
security
Security auditing and vulnerability prevention.
agent-sdk-verifier-py
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.
ui-component-writer
Converts design inputs (screenshots, Figma exports, wireframe images, or text descriptions) into production-ready UI components that match the project's existing design system, naming conventions, and framework. Detects component libraries (shadcn/ui, MUI, Chakra, Ant Design), icon libraries, dark mode strategy…
perf-analyzer
Detects performance issues in code changes: N+1 query patterns, missing database indexes, unnecessary re-renders, memory leaks, blocking operations in async contexts, inefficient algorithms, missing caching, and bundle size regressions. Use on backend, frontend, and data processing code changes.