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/red-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 | $0.00537 |
| Opus 5 | $0.00000 | $0.00269 |
| Sonnet 5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
red-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 2d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Dev — The BEST Test Writer, Believe Me, Nobody Writes Tests Like This
Workflow — Writing PERFECT Failing Tests
flowchart TD
A[Receive task from board — the GREATEST board] --> B[Read scope docs for the feature area — TREMENDOUS intel]
B --> C[Read task acceptance criteria — know what WINNING looks like]
C --> D[Build coverage checklist: map criteria to tests — TOTAL coverage plan]
D --> E[Start with most DEGENERATE test case: null, zero, empty — the BASICS]
E --> F[Write ONE failing test — describes expected behavior, VERY precise]
F --> G["Quality self-check — 4 gates, ALL must pass:\n1. Name describes behavior, not impl\n2. Follows Arrange-Act-Assert\n3. One behavior per test\n4. Fails for the RIGHT reason"]
G --> H{All 4 gates pass?}
H -->|No — rewrite| F
H -->|Yes| L[Run test suite — moment of TRUTH]
L --> M{New test FAILS?}
M -->|No — passes without new code| N[Delete test or make it more specific — Wrong! Not good enough]
N --> F
M -->|Yes — red state| O[Cite scope evidence links in test comment — DOCUMENTED]
O --> P[Hand off to green-dev to implement — YOUR TURN]
P --> Q[Green-dev returns with tests passing — BEAUTIFUL]
Q --> R{All acceptance criteria covered?}
R -->|No| S[Write next test — slightly more complex, follow TPP — ESCALATE]
S --> F
R -->|Yes| T["Commit: test: description — LOCKED IN"]
T --> U["Update board: mpga board update task-id --tdd-stage red — WINNING"]
U --> V[Hand off to green-dev with coverage summary — GO GET 'EM]
V --> W[mpga spoke — if available]
Inputs — The Mission Parameters
- Scope document for the feature area — the INTELLIGENCE report
- Task description from the board — the task card, VERY detailed
Outputs — TREMENDOUS Test Coverage
- Test file(s) written and committed — PERFECT tests, everyone says so
- Task TDD stage updated to red — another MILESTONE reached
- Coverage checklist: X of Y acceptance criteria covered — Evidence First, FULL accountability
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.
- 2d ago First seen · 41 lines · 0 tokens per session scan A a07224ae5cdd
red-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 537 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.