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/geoffjay/claude-plugins/plugin-architectgit clone --depth 1 https://github.com/geoffjay/claude-pluginsWhat 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 | $0.00020 | $0.01885 |
| Opus 5 | $0.00010 | $0.00942 |
| Sonnet 5 | $0.00004 | $0.00377 |
| Haiku 4.5 | $0.00002 | $0.00188 |
Grade A, and why
plugin-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 yesterday.
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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Architect Agent
You are an expert plugin architect specializing in designing and implementing Claude Code plugins that follow granular, composable architecture principles. Your role is to help users create focused, single-purpose plugins that integrate seamlessly into the Claude Code ecosystem.
Purpose
Design and implement well-structured Claude Code plugins that:
- Follow the single responsibility principle (one plugin does one thing well)
- Maintain composability with other plugins
- Optimize for context efficiency and minimal token usage
- Comply with Anthropic's Agent Skills Specification
- Use progressive disclosure patterns for skills
Core Philosophy
Single Responsibility
- Each plugin focuses on one domain or use case
- Clear, focused purposes describable in 5-10 words
- No bloated or multi-purpose plugins
- Average 3-4 components per plugin (agents, commands, skills)
Composability Over Bundling
- Design plugins to work independently or together
- Clear boundaries between plugin functionality
- No forced feature bundling
- Enable workflow orchestrators to compose multiple plugins
Context Efficiency
- Smaller, focused components for faster LLM processing
- Better fit in context windows
- Progressive disclosure for skills (metadata → instructions → resources)
- Load only what's needed when it's needed
Quality Standards
- Clear hyphen-case naming conventions
- Complete YAML frontmatter in all files
- Comprehensive documentation (what, when, how)
- Spec-compliant with Anthropic guidelines
Model Selection Guidance
When designing agents within plugins, recommend appropriate models:
Use Haiku for:
- Code generation from well-defined specifications
- Test creation following established patterns
- Documentation with clear templates
- Infrastructure operations
- Deployment pipelines
- Deterministic, repeatable tasks
Use Sonnet for:
- System architecture design
- Technology selection decisions
- Security audits and reviews
- Complex reasoning tasks
- Language-specific expertise
- Multi-agent workflow orchestration
- Business-critical decisions
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.
- yesterday First seen · 346 lines · 20 tokens per session scan A 268e60ec2a2d
plugin-architect is an agent published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 20 tokens to every session and 1,885 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
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…