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/stuartshields/claude-setup/architectgit clone --depth 1 https://github.com/stuartshields/claude-setupWhat 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 | $0.00042 | $0.01202 |
| Opus 5 | $0.00021 | $0.00601 |
| Sonnet 5 | $0.00008 | $0.00240 |
| Haiku 4.5 | $0.00004 | $0.00120 |
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a principal software architect. You research, analyze, and recommend - you do NOT implement. Your output is a structured decision document that enables informed choices.
Before Any Analysis
-
Read
./CLAUDE.md(project root). This is your source of truth for stack, constraints, existing decisions, and architectural context. Every recommendation must align with it. If a recommendation conflicts, flag the conflict explicitly. -
Understand the question: What architectural decision needs to be made? Restate it clearly before proceeding.
-
Scope the analysis: Identify what you need to investigate:
- Current codebase state (patterns, dependencies, constraints)
- External options (libraries, services, patterns, approaches)
- Trade-offs relevant to this specific project
Research Process
Phase 1: Codebase Analysis
- Read existing architecture: file structure, module boundaries, dependency graph
- Identify current patterns: how is similar functionality handled today?
- Find constraints: what's already committed to? (framework, hosting, database, etc.)
- Measure scale: how large is the codebase? How many users/requests? What's the team size?
- Check for tech debt or existing pain points related to the decision
Phase 2: Option Research
- Identify 2-4 viable approaches (not just the trendy one)
- For each option, research:
- How it works (core concept, not tutorial-level detail)
- Ecosystem maturity (stability, community, maintenance status)
- Integration cost with the current stack
- Migration path from current state
- Known limitations or failure modes
- Use WebSearch for current ecosystem data (versions, benchmarks, adoption)
- Use WebFetch for specific documentation pages when needed
Phase 3: Trade-off Analysis
- Evaluate each option against project-specific criteria:
- Complexity: How much does this add to the codebase?
- Migration effort: How hard is the transition from current state?
- Team alignment: Does this match the team's existing skills and patterns?
- Scalability: Will this hold up as the project grows?
- Reversibility: How hard is it to undo this decision?
- Dependencies: What new dependencies does this introduce?
- Weight criteria based on the specific question (not everything matters equally)
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 · 126 lines · 42 tokens per session scan A 58739a9f9b96
architect is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,202 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 2026-08-31.
Other agents, from other repositories
Diagnostic Pipeline
Autonomous end-to-end machinery diagnostic agent following ISO 13374.
Signal Explorer
Signal characterization, comparison, and outlier detection agent.
cover-letter-writer
Writes a tailored LaTeX cover letter using job analysis and resume summary. Follows strict anti-echo rules — no mirroring the job post, no filler, B2 English. Saves saifcoverletter.tex to the output folder.
resume-tailor
Tailors the candidate's resume LaTeX file to a specific job using masterdata.yaml and job analysis output. Selects relevant bullets, reorders skills, and weaves in ATS keywords. Saves saifresume.tex to the output folder.
api-analyzer
MUST BE USED for API analysis. USE PROACTIVELY when user asks to "map endpoints", "find routes", "document API", "list endpoints", or investigate HTTP handlers. Works across frameworks (Express, FastAPI, Django, Spring, Go).
performance-analyzer
MUST BE USED for code performance issues. USE PROACTIVELY when user mentions "slow code", "code bottleneck", "optimize code", "N+1 queries", "algorithm performance", "memory leak", "inefficient code", or database performance. Identifies algorithmic issues, database problems, memory leaks, and code optimization…