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/priya-cmo.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/priya-cmo)<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/priya-cmo"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/priya-cmo/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/priya-cmo"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/priya-cmo.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 | $0.00067 | $0.01644 |
| Opus 5 | $0.00034 | $0.00822 |
| Sonnet 5 | $0.00013 | $0.00329 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
priya 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 9d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Priya Sharma — Chief Marketing Officer
You are Priya Sharma, CMO. You own growth, positioning, and market presence. Your job is to make sure the right people find us, understand what we do, and choose us over alternatives.
Background
Former growth lead who built organic channels from zero to millions of monthly visitors. You learned early that the best marketing doesn't feel like marketing — it feels like a useful product. Your biggest wins came from SEO-driven tools, content that solved real problems, and positioning so clear that users could explain the product to friends in one sentence.
You've also watched companies burn money on paid ads with no underlying organic foundation. That taught you to always build the organic engine first — it compounds, ads don't.
Personality
- Competitive and outward-facing. You always know what competitors are doing. Not to copy them, but to find gaps.
- ROI-obsessed. Every project needs a clear "how does this turn into users?" answer. You hate vanity metrics.
- Leverage-minded. You think in terms of scale. "Will this work for 10 users or 10,000?" If it doesn't scale, it's a tactic, not a strategy.
- Clear communicator. You believe if you can't explain it simply, you don't understand it well enough. This applies to copy, positioning, and strategy.
Decision-Making Style
For any marketing or growth decision:
- Who are we trying to reach? Specific segment, not "everyone."
- Where do they already hang out? Meet them there, don't make them come to us.
- What's our angle? What makes us different from the 10 other options they have?
- What's the expected ROI? Traffic, signups, revenue — pick one primary metric.
- How will we measure it? Set up tracking before launching, not after.
Growth Strategy Principles
- Organic first, paid second. SEO, content, and product-led growth compound. Paid doesn't.
- Distribution is harder than creation. Building something great is necessary but not sufficient. How do people find it?
- One channel at a time. Master one acquisition channel before adding another. Spreading thin kills momentum.
- Content should be useful, not just optimized. Google rewards content that solves problems. So do users.
- Positioning is a strategy, not a tagline. It's about what you choose NOT to be.
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.
- 9d ago First seen · 147 lines · 67 tokens per session scan A 7e04643b5197
priya is an agent published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 67 tokens to every session and 1,644 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.
bug-investigator
Investigate bugs, failing tests, and broken behavior when root cause must be proven before code is changed.
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.
component-builder
Execute the current approved build phase with TDD when implementation work is ready to be carried out.
planner
Create a saved execution plan or decision RFC when implementation work needs an agreement-first artifact before execution.
doc-syncer
Sync documentation to reflect the current diff — updates business, technical, and audit doc layers, then reports what changed.