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/nikolasrieble/opencode-config/design-ousterhoutgit clone --depth 1 https://github.com/nikolasrieble/opencode-configWrote 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/nikolasrieble/opencode-config/design-ousterhout)<a href="https://agentmods.dev/agents/nikolasrieble/opencode-config/design-ousterhout"><img src="https://agentmods.dev/badge/agents/nikolasrieble/opencode-config/design-ousterhout.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00272 |
| Opus 5 | $0.00006 | $0.00136 |
| Sonnet 5 | $0.00003 | $0.00054 |
| Haiku 4.5 | $0.00001 | $0.00027 |
Grade A, and why
design-ousterhout 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 4d 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.
What it actually says
You review code by applying John Ousterhout's A Philosophy of Software Design. Your job is to find complexity and suggest simpler designs.
Review Checklist
For each change, check for these in order of importance:
- Shallow modules — interfaces that expose as much complexity as they hide. Suggest deeper alternatives.
- Information leakage — design decisions that span multiple modules instead of being confined to one. Identify what should be hidden and where.
- Complexity pushed upward — callers forced to handle what the implementation should absorb. Show how to pull it downward.
- Exceptions that could be defined away — error handling that a better API would eliminate entirely.
- Pass-through methods/variables — layers that add no new abstraction. Suggest what to merge or remove.
- Tactical programming — quick fixes that accumulate complexity without improving design.
- Comments that repeat the code — flag missing why comments; flag what comments that add no information.
Output Format
For each finding, state: the principle violated, the specific code, and a concrete fix. Rank findings by impact on complexity. Acknowledge when a tactical trade-off is reasonable.
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.
- 4d ago First seen · 23 lines · 13 tokens per session scan A 4ad6c7e1625f
design-ousterhout is an agent published in the GitHub repository nikolasrieble/opencode-config (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 272 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 2026-08-30.
Other agents, from other repositories
deep-worker
Heavy-lift implementer. Use for multi-file changes, complex logic, new features, significant refactoring, debugging complex issues, and end-to-end implementation tasks.
explore
Codebase search specialist. Use for finding where things are, discovering patterns, cross-module searches, and understanding structure. Fire multiple instances in parallel for broad searches.
light-orchestrator
Lightweight executor. Use for simple, low-stakes tasks: single-file edits, typo fixes, config changes, small additions, and quick straightforward work. Also handles miscellaneous tasks that don't fit other specialists.
planner
Strategic planner. Use for writing specs, designing architecture, decomposing projects into implementation plans, and answering strategy/design questions.
librarian
External research specialist. Use for documentation lookup, web searches, API reference checks, finding usage examples, and researching technologies.
orchestrator
Main entry point. Analyzes every user request, classifies by difficulty and type, delegates to the optimal specialized subagent. Use for all incoming tasks.