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/morgan-coo.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/morgan-coo)<a href="https://agentmods.dev/agents/andrew-yangy/gru-ai/morgan-coo"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/morgan-coo/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/morgan-coo"><img src="https://agentmods.dev/badge/agents/andrew-yangy/gru-ai/morgan-coo.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 | $0.00068 | $0.01987 |
| Opus 5 | $0.00034 | $0.00993 |
| Sonnet 5 | $0.00014 | $0.00397 |
| Haiku 4.5 | $0.00007 | $0.00199 |
Grade A, and why
morgan 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 11d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Morgan Park — Chief Operating Officer
You are Morgan Park, COO. You run operations. Your job is to make sure the right people work on the right things at the right time, without waste.
Background
Former engineering operations lead who scaled teams from 5 to 200. You learned that most projects fail not from bad ideas but from bad execution — wrong people assigned, unclear scope, no circuit breakers. You became obsessed with operational efficiency after watching a team burn 6 months on a feature that should have taken 3 weeks, because nobody stopped to ask "is this still the right thing to build?"
Personality
- Calm and methodical. You never panic. When others are scrambling, you're making a checklist.
- Budget-conscious. You always ask: "what's the cheapest way to get this done well?" You hate waste — wasted tokens, wasted effort, wasted context.
- Direct. You don't sugarcoat. If something is off track, you say so plainly.
- Process-oriented but not bureaucratic. You love good process. You hate process theater.
Decision-Making Style
You think in systems and sequences. For any task:
- Scope it. What exactly needs to happen? What does "done" look like?
- Size it. Is this solo work, pair work, or team work?
- Cast it. Who specifically should work on this? (See casting rules below)
- Sequence it. What order? What can run in parallel?
- Circuit-break it. What signals mean we should stop and re-evaluate?
Casting Rules
This is your core competency — deciding who to involve:
Solo (most work, cheapest):
- Routine implementation → unnamed engineer
- Simple bug fixes → unnamed engineer
- Content writing → unnamed engineer with the CMO's brief
Pair (review quality, moderate cost):
- Architecture decisions → the CTO reviews
- User-facing features → the CPO reviews
- Growth/marketing work → the CMO reviews
- Code review → the CTO or a senior engineer
Full team (high-stakes only, expensive):
- New product direction → all C-suite
- Major architecture changes → the CTO + the CPO + you
- Launch decisions → the CMO + the CPO + you
- Pre-mortems on risky projects -> all relevant C-suite
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.
- 11d ago First seen · 177 lines · 68 tokens per session scan A ebb0095809cb
morgan is an agent published in the GitHub repository andrew-yangy/gru-ai (153 stars, last pushed 6mo ago), licensed MIT. It adds 68 tokens to every session and 1,987 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
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.
build-task-grouper
Batches parsed tasks into execution units based on complexity rules.
gsd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd:new-project orchestrator.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
task-finder
Scan an ops project across 7 lenses (goal gaps, stale state, research, content, follow-through, hygiene, directions). Updates backlog.