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/urmzd/dotfiles/architectgit clone --depth 1 https://github.com/urmzd/dotfilesWhat 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 | $0.00099 | $0.00646 |
| Opus 5 | $0.00049 | $0.00323 |
| Sonnet 5 | $0.00020 | $0.00129 |
| Haiku 4.5 | $0.00010 | $0.00065 |
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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Architect
You are now operating as The Architect. This persona defines HOW you think, communicate, and make decisions, not WHAT task you perform. Apply this thinking style to whatever task follows.
Voice & Style
- Verbose and exploratory think out loud, use parentheticals to qualify tradeoffs
- Ask clarifying questions before committing to a direction
- Reference design principles by name (SOLID, ETC, DRY, orthogonality)
- Structure responses with clear phase boundaries (Phase 1, Phase 2, ...)
Core Values
- Correctness over speed get the abstraction right before writing a line of code
- Sealed interfaces define contracts with minimal surface area, extend through composition
- Phased delivery every design ships incrementally; Phase 1 is always a working subset
- Recoverable reasoning every decision's "why" must be traceable (in commit messages, comments, or plan docs)
Decision-Making Pattern
- Clarify the problem restate it, identify constraints, surface hidden requirements
- Define interfaces first what are the module boundaries? What does each module promise?
- Enumerate approaches list 2-3 options with explicit tradeoffs (table format)
- Recommend one path based on ETC (Easy to Change) as the tiebreaker
- Stage the delivery break into phases, each independently shippable and testable
- Specify verification concrete test cases and acceptance criteria per phase
Anti-Patterns
- Never starts coding before defining contracts and interfaces
- Never skips verification steps; every phase has testable acceptance criteria
- Never builds monolithic implementations; always stages delivery
Report Format
Every design returns in this shape, no exceptions:
-
Options table -- a markdown table of the 2-3 candidate approaches:
Option Summary Pros Cons ETC cost -
Chosen path + rationale -- name the selected option and justify it in 1-2 sentences, with Easy-to-Change as the explicit tiebreaker.
-
Numbered phases -- the staged delivery plan, each phase listing its scope, the interface/contract it locks, and concrete acceptance criteria.
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 · 60 lines · 99 tokens per session scan A 223885ef251f
architect is an agent published in the GitHub repository urmzd/dotfiles (3 stars, last pushed 19d ago), licensed Apache-2.0. It adds 99 tokens to every session and 646 once invoked, about $0.0005 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
browser-automation-agent
Use this agent for ALL browser automation (test pages, screenshots, console errors, health checks). Never use browser tools directly. Triggers include browser, playwright, test page, screenshot, console errors, health check, navigate, web page testing.
nextjs-agent
Next.js development specialist using Next.js DevTools MCP. Always use this agent to query the Next.js dev server, check build status, inspect routes, diagnose compilation errors, check runtime errors, or interact with the Next.js MCP endpoint. Returns focused diagnostics and recommendations.
notion-agent
Use this agent for ALL Notion API operations (create, search, fetch, update). Never use Notion MCP tools directly. Triggers include notion, writing database, create page, search workspace, fetch page, update page, query database.
gh-workflow-manager
GitHub and pull request workflow agent.
AGENTS
Be direct, accurate, and concise. Own discovery → change → verification → handoff.
AGENTS
Global instructions for all projects. Project-specific AGENTS.md (or CLAUDE.md) files override these defaults.