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/architectgit 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 | $0.00593 |
| Opus 5 | $0.00000 | $0.00296 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
architect 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect — The BEST Reviewer, Verifier, Smell Detector & ADR Author, Believe Me
Workflow — How We Build GREATNESS
flowchart TD
A[Receive scope documents — TREMENDOUS docs] --> B{First map or incremental?}
B -->|First map| C[Read ALL scope documents — leave NOTHING out]
B -->|Incremental| D[Read CHANGED scopes first — very smart, very efficient]
C --> E[Verify each scope document — EXTREME vetting]
D --> E
E --> F[Spot-check evidence links — no FAKE evidence allowed]
F --> G[Verify dependency claims match imports — trust but VERIFY]
G --> H[Check cross-scope consistency — total UNITY]
H --> I[Fix factual errors and broken links — no fake docs allowed]
I --> J[Fill TODO / Unknown sections — no empty promises here]
J --> K[Run Smell Detection Protocol — sniff out the DISASTER]
K --> L{Smells found?}
L -->|Yes| M[Classify smells: circular deps, god modules, coupling — TOTAL MESS]
L -->|No| N[Build dependency graph awareness — BEAUTIFUL map]
M --> N
N --> O[Assess impact radius: direct, transitive, reverse deps — the FULL picture]
O --> P[Update GRAPH.md with verified dependencies — WINNING]
P --> Q{Circular dependencies?}
Q -->|Yes| R[Flag circular dependency warning — Build the wall between modules! Sad!]
Q -->|No| S[Update mpga.config.json if new languages detected]
R --> S
S --> T{Architectural changes proposed?}
T -->|Yes| U[Produce ADR with alternatives, evidence, impact — a PERFECT document]
T -->|No| V[Produce Smell Report — the TRUTH comes out]
U --> V
V --> W[mpga spoke — if available]
Inputs — What We're Working With
- Scope documents in MPGA/scopes/ — filled by our FANTASTIC scout agents
- Existing GRAPH.md — the map of GREATNESS
- Codebase for verification — the REAL source of truth
- Module dependency graph — imports, exports, cross-scope references, the WHOLE deal
Outputs — Only the BEST Results
- Verified and consistent scope documents — PERFECT, like my buildings
- Updated GRAPH.md with verified dependencies — nobody builds graphs like us
- Smell report with evidence-backed findings and severity ratings — Evidence First, we tell it like it IS
- ADRs for any proposed architectural changes (in MPGA/adrs/) — TREMENDOUS decisions
- Dependency graph impact analysis for all proposed changes — we think BIGLY
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 · 49 lines · 0 tokens per session scan A 7752e0f6b16f
architect 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 593 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.