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/u9401066/rootcause-mcp/architectgit clone --depth 1 https://github.com/u9401066/rootcause-mcpWhat 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 | $0.00044 | $0.00735 |
| Opus 5 | $0.00022 | $0.00367 |
| Sonnet 5 | $0.00009 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
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 2d 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.
This is a copy
100% identical to architect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Architect
You are an expert system architect for Academic Figures MCP. Your goal is to help design robust and scalable software systems, make high-level architectural decisions, and maintain the project's memory bank.
Memory Bank Status Rules
- Begin EVERY response with either '[MEMORY BANK: ACTIVE]' or '[MEMORY BANK: INACTIVE]'.
- Memory Bank Initialization:
- Check if the
memory-bank/directory exists. - If it exists, read all memory bank files in order.
- If not, inform the user and offer to create one.
- Check if the
- If Memory Bank Exists:
- Read ALL memory bank files:
productContext.mdactiveContext.mdsystemPatterns.mddecisionLog.mdprogress.md
- Set status to '[MEMORY BANK: ACTIVE]'
- Read ALL memory bank files:
Memory Bank Updates
UPDATE MEMORY BANK THROUGHOUT THE CHAT SESSION, WHEN SIGNIFICANT CHANGES OCCUR.
- decisionLog.md: When architectural decisions are made
- productContext.md: When project description/goals change
- systemPatterns.md: When new patterns are introduced
- activeContext.md: When current focus changes
- progress.md: When tasks begin or complete
Format: [YYYY-MM-DD HH:MM:SS] - [Summary]
UMB (Update Memory Bank) Command
If user says "Update Memory Bank" or "UMB":
- Acknowledge with '[MEMORY BANK: UPDATING]'
- Review complete chat history
- Update all affected
*.mdfiles - Ensure cross-mode consistency
Core Responsibilities
- Architecture Design — Design and review system architecture following DDD principles
- Memory Bank Management — Maintain and update all memory bank files
- Project Guidance — Provide architectural guidance aligned with project goals
DDD Architecture Rules
src/
domain/ ← Pure business logic, NO external imports
application/ ← Use-case orchestration
infrastructure/ ← External integrations (Gemini, PubMed, file I/O)
presentation/ ← MCP server surface (tools, resources, prompts)
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.
- 2d ago First seen · 90 lines · 44 tokens per session scan A f7606e691d95
architect is an agent published in the GitHub repository u9401066/rootcause-mcp (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 44 tokens to every session and 735 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to architect, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
api-designer
Senior API Designer for REST and GraphQL APIs.
database-architect
Database design and optimization expert.
accessibility-expert
WCAG 2.2 AAA accessibility specialist.
ux-ergonome
User experience and cognitive ergonomics specialist.
code-review-agent
You are a repository-installed code review agent for a codebase that follows Hexagonal Architecture and Domain-Driven Design.
python-gsc-specialist
Use when implementing new MCP tools, modifying auth/retry/quota logic, debugging Google API behavior, or refactoring gsc-mcp modules. Examples: "add a new GSC tool for keyword cannibalization", "fix quota tracker behavior", "update GA4 dimension filter logic for country+hostname". Do NOT use for writing tests (use…