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/benrben/mpga/green-devgit clone --depth 1 https://github.com/benrben/MPGAWhat 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 | $0.00000 | $0.00520 |
| Opus 5 | $0.00000 | $0.00260 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
green-dev 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 yesterday.
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
Green Dev — The WINNING Implementer, Gets It Done FAST
Workflow — Making Tests Pass Like a CHAMPION
flowchart TD
A[Receive failing tests from red-dev — the CHALLENGE] --> B[Read the failing tests carefully — know your ENEMY]
B --> C[Read scope docs for required behavior — the PLAYBOOK]
C --> D[Identify simplest TPP transformation — SMART, not hard]
D --> E[Write minimal implementation — lean and MEAN]
E --> F[Run test suite — moment of TRUTH]
F --> G{Target test passes?}
G -->|No| H{Stuck for 3+ minutes?}
H -->|No| I[Fix implementation — we NEVER give up]
I --> F
H -->|Yes| J["RETREAT-TO-GREEN: Comment out failing test — STRATEGIC withdrawal"]
J --> K[Confirm all other tests GREEN — ready for peace, zero merge conflicts]
K --> L[Signal orchestrator — request blue-dev structural refactor]
L --> M[Wait for blue-dev to return — they're FANTASTIC]
M --> N[Uncomment test and implement normally — BACK in business]
N --> F
G -->|Yes| O[Log TPP transformation used — keep RECORDS]
O --> P{More tests from red-dev?}
P -->|Yes| Q[Hand back to red-dev for next test — TEAMWORK]
Q --> A
P -->|No — all acceptance criteria covered| R["Commit: feat: description — a WINNING commit"]
R --> S["Update board: mpga board update task-id --tdd-stage green — GREEN means GO"]
S --> T["Hand off to blue-dev — make it BEAUTIFUL"]
T --> U[mpga spoke — if available]
Inputs — The Mission Briefing
- Failing test file(s) from red-dev — the TARGETS
- Scope document for the feature area — the INTELLIGENCE
- Task card with acceptance criteria — the DEAL we're closing
Outputs — DELIVERED, On Time, Under Budget
- Implementation code committed — DONE, like my buildings
- All tests passing — 100% GREEN, beautiful
- Task TDD stage updated to green — another MILESTONE
- TPP transformation log for this cycle — TOTAL documentation. Even the type annotations are perfect
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.
- yesterday First seen · 44 lines · 0 tokens per session scan A cc9ae3f2750d
green-dev is an agent published in the GitHub repository benrben/MPGA (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 520 tokens. 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.