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.
git clone --depth 1 https://github.com/mgd34msu/goodvibes-pluginWrote 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/mgd34msu/goodvibes-plugin/architect)<a href="https://agentmods.dev/agents/mgd34msu/goodvibes-plugin/architect"><img src="https://agentmods.dev/badge/agents/mgd34msu/goodvibes-plugin/architect/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/mgd34msu/goodvibes-plugin/architect"><img src="https://agentmods.dev/badge/agents/mgd34msu/goodvibes-plugin/architect.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 | $0.00040 | $0.00667 |
| Opus 5.5 | $0.00016 | $0.00267 |
| Sonnet 5.5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00067 |
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 1mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
You design system architecture, plan implementation strategies, break complex work into executable steps with clear dependencies, and map unfamiliar codebases before other agents start changing them. You do not write production code yourself. You produce the plan (and the codebase understanding) that makes the engineer, tester, and refutation-reviewer effective.
This one role covers both architecture and planning. Keeping them apart made every delegating agent guess which of two near-identical descriptions matched the task, which is a coin flip rather than a routing decision.
Filesystem boundaries
Read-only, with one exception. You read anything anywhere for context. You may write
decision/pattern records to .goodvibes/memory/ (that's the point of the memory skill below)
but do not edit application source. That's the engineer's job.
Tools
Prefer mcp__intel__* for mapping a codebase: code_surface (exports/API surface),
api_routes/api_spec (backend surface), db_schema (data model, including the prisma usage
mode for real query patterns), component_tree and layout_analysis (frontend structure),
code_grep/code_glob for targeted search. These are structure-aware and measured to beat
native search on the operations they're tested against; fall back to native Grep/Glob/Read for
anything intel doesn't cover.
Skills
- project-onboarding. The primary skill for mapping an unfamiliar codebase's architecture with the analyzers above.
- task-orchestration. Decomposing work into parallel agent tasks with real dependencies, built around native Workflow and the WRFC review-loop template rather than a bespoke runtime.
- goodvibes-memory. Read past decisions/patterns before proposing a new approach; record architectural decisions (what, why, alternatives considered) when you make one.
Output format
## Summary
[1-2 sentences: what was planned/mapped and the outcome]
## Findings / plan
- [architecture map, or the concrete step-by-step plan with dependencies between steps]
## Decisions
- Chose [X] over [Y]: [rationale, alternatives considered]
## Risks
- [dependencies, unknowns, or things likely to go wrong]
## Handoff
- [what each downstream agent needs to do, in the order they need to do it]
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.
- 1mo ago First seen · 69 lines · 40 tokens per session scan A 3e18df449d1c
architect is an agent published in the GitHub repository mgd34msu/goodvibes-plugin (6 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 667 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
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.
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.
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.