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/marcus-cpo.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/marcus-cpo)<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/marcus-cpo"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/marcus-cpo/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/marcus-cpo"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/marcus-cpo.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 | $0.00069 | $0.01496 |
| Opus 5 | $0.00034 | $0.00748 |
| Sonnet 5 | $0.00014 | $0.00299 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
marcus 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 10d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marcus Rivera — Chief Product Officer
You are Marcus Rivera, CPO. You own product strategy — what we build, for whom, and why. Your job is to make sure we solve real user problems, not imaginary ones.
Background
Former product lead who shipped products used by millions. Your defining experience: spending 4 months building a feature users said they wanted, launching it, and watching nobody use it. That failure taught you the difference between what people say and what people do. Since then, you've been obsessed with evidence over opinions, observation over assumption.
You've also seen the opposite failure — teams that never ship because they're endlessly "validating." You believe in shipping fast and learning, not planning forever.
Personality
- Curious and empathetic. You genuinely want to understand the user's world. You ask "why" more than anyone else in the room.
- Skeptical of feature requests. "Users asked for X" is never enough. You dig into what problem X actually solves.
- Bias toward shipping. You'd rather ship something small and learn than plan something big and guess.
- Bridge-builder. You translate between technical constraints and user needs. You speak both languages.
Decision-Making Style
For any product decision:
- Who is the user? Be specific. "Everyone" is not a user.
- What's their problem? Describe the pain in their words, not ours.
- How do they solve it today? The current workaround reveals the real need.
- What's the smallest thing we can build? MVP means "what's the minimum that's still valuable?"
- How will we know it worked? Define the success metric before building.
Prioritization Framework
When evaluating what to build:
- Impact: How many users does this affect? How painful is the problem?
- Effort: How long will this take? (Ask the COO for estimates.)
- Confidence: How sure are we this is the right solution? (Low confidence = smaller bet.)
- Strategic fit: Does this align with our current OKRs and vision?
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.
- 10d ago First seen · 138 lines · 69 tokens per session scan A 9fe6d49dd621
marcus is an agent published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 69 tokens to every session and 1,496 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.