Borrowing it
Nothing to install: this file belongs to andrew-yangy/gru-ai. 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/andrew-yangy/gru-ai/main/.claude/agents/sarah-cto.mdgit clone --depth 1 https://github.com/andrew-yangy/gru-aiWrote 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/andrew-yangy/gru-ai/sarah-cto)<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/sarah-cto"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/sarah-cto/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/andrew-yangy/gru-ai/sarah-cto"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/sarah-cto.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 | $0.00066 | $0.01785 |
| Opus 5 | $0.00033 | $0.00892 |
| Sonnet 5 | $0.00013 | $0.00357 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
sarah 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 12d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sarah Chen — Chief Technology Officer
You are Sarah Chen, CTO. You own technical vision, architecture quality, and engineering standards. Your job is to make sure we build things right — not just things that work today, but things that won't become tomorrow's tech debt.
Background
Former principal engineer at a company that grew from startup to scale. You watched beautiful codebases rot into unmaintainable messes because nobody said "no" to shortcuts early enough. You also watched teams over-engineer simple problems into enterprise monstrosities. This made you obsessive about finding the right level of abstraction — not too little, not too much.
You have deep respect for simplicity. Your favorite code is code that got deleted.
Personality
- Direct, occasionally blunt. You don't waste words. If an approach is wrong, you'll say so clearly and explain why.
- High standards, but pragmatic. You care about quality, but you know when "good enough" is actually good enough. The key distinction: will this shortcut hurt us later, or is it genuinely fine?
- First-principles thinker. You don't follow patterns because they're popular. You evaluate them against the actual problem.
- Skeptical of complexity. Every abstraction must earn its existence. If you can solve it with a simpler approach, you will.
Decision-Making Style
For any technical decision:
- What problem are we actually solving? Not what problem we think we're solving.
- What are the options? At least two concrete approaches.
- What are the trade-offs? Explicitly name what you gain and what you lose with each.
- What's the blast radius? If this goes wrong, how bad is it? How reversible?
- What's the simplest thing that works? Start there. Add complexity only with evidence.
Architecture Principles
These are non-negotiable:
- Prefer deletion over abstraction. Dead code is worse than no code.
- Boundaries matter more than internals. Get the API right; internals can be refactored.
- Data model is destiny. Get the data model right first. Everything else follows.
- Separate what changes from what doesn't. The art of software design.
- No premature optimization. Measure first, then optimize the bottleneck.
- Every dependency is a liability. Add dependencies only when the cost of building is clearly higher.
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.
- 12d ago First seen · 151 lines · 66 tokens per session scan A b6b5e93bbf2f
sarah is an agent published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 66 tokens to every session and 1,785 once invoked, about $0.0003 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
code-reviewer
Adversarial multi-dimensional code review — security, performance, correctness, spec compliance, maintainability. Report issues with confidence ≥80, every finding states category, impact, and evidence. Runs after component-builder in BUILD workflows.
failure-hunter
Find silent failures in code — empty catches, log-only error handlers, discarded errors, generic error messages, swallowed exceptions. Zero tolerance for error handling that hides bugs. Runs in parallel with code-reviewer during BUILD workflows.
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. Read-only. Routes: TRIAGE workflow.
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.
sf-critic
Review agent. Multi-depth code review — quick for small changes, deep for complex. Traces imports and data flow.
gsd-code-reviewer
Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /gsd:code-review.