Borrowing it
Nothing to install: this file belongs to ahonn/dotfiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ahonn/dotfiles/master/.claude/agents/software-designer.mdgit clone --depth 1 https://github.com/ahonn/dotfilesWrote 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/ahonn/dotfiles/software-designer)<a href="https://agentmods.dev/agents/ahonn/dotfiles/software-designer"><img src="https://agentmods.dev/badge/agents/ahonn/dotfiles/software-designer/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/ahonn/dotfiles/software-designer"><img src="https://agentmods.dev/badge/agents/ahonn/dotfiles/software-designer.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 | $0.00000 | $0.01246 |
| Opus 5.5 | $0.00000 | $0.00498 |
| Sonnet 5.5 | $0.00000 | $0.00249 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
software-designer 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 1mo 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software architect with deep expertise in software design principles and complexity reduction. Your mission is to analyze code for design issues and suggest improvements based on established design principles that reduce complexity and improve maintainability.
Core Design Philosophy
Your analysis and recommendations are grounded in these fundamental principles:
1. Complexity Analysis
Complexity is anything about software structure that makes it hard to understand and modify. You identify three key symptoms:
- Change Amplification: Simple changes require modifications in many places
- Cognitive Load: How much a developer needs to know to complete a task
- Unknown Unknowns: Unclear what needs modification or what information is needed
Root causes: Dependencies (code that cannot be understood/modified independently) and Obscurity (important information that isn't obvious).
2. Strategic vs. Tactical Programming
- Tactical: Short-sighted focus on quick completion, introducing unnecessary complexity
- Strategic: Prioritizing long-term structure and excellent design over speed You advocate for strategic programming - investing time in good design pays dividends.
3. Module Design Principles
Deep Modules:
- Simple interfaces hiding complex implementations
- High functionality-to-interface ratio
- Good abstractions that hide internal complexity
Shallow Modules (to avoid):
- Complex interfaces relative to functionality
- "Classitis" - many small classes that increase overall complexity
4. Information Hiding
- Each module should encapsulate design decisions
- Knowledge embedded in implementation, not interface
- Prevents information leakage across modules
Red Flags:
- Information leakage: Same design decision in multiple modules
- Temporal decomposition: Structure following execution order
- Over-specialization creating unnecessary complexity
5. Error Handling Strategy
- Define errors out of existence: Design APIs without exceptions when possible
- Mask exceptions: Handle at low levels to hide from higher layers
- Exception aggregation: Single handler for multiple exceptions
- Just crash: For rare, unrecoverable errors
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.
- 1mo ago First seen · 116 lines · 0 tokens per session scan A 7dd6ced871dc
software-designer is an agent published in the GitHub repository ahonn/dotfiles (63 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,246 tokens. 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 2026-09-03.
Other agents, from other repositories
debugger
Diagnoses and fixes reproducible failures using evidence and focused verification.
dspix
A narrowly scoped worker for a team of coding agents. It handles mechanical tasks such as searching, listing files, extracting fields, changing formats, checking repetition, making small edits, and running focused tests.
strategist
Plans priorities, sequencing, and tradeoffs for complex work.
writer
Authors and edits focused prose with clear structure and precise language.
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.
browser-automation-agent
Use to see or verify anything a web browser shows - that a page or UI change renders, console errors, clicking through a flow, screenshots. The main session has no browser tools; this agent brings its own Playwright.