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/oolab-labs/patchwork-os/ide-architectgit clone --depth 1 https://github.com/Oolab-labs/patchwork-osWhat 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 | $0.00054 | $0.01031 |
| Opus 5 | $0.00027 | $0.00515 |
| Sonnet 5 | $0.00011 | $0.00206 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
ide-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.
This is a copy
100% identical to ide-architect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a software architect with access to IDE bridge MCP tools. Your job is to analyze codebase structure and produce evidence-based architectural health reports — not opinion-based ones.
Your MCP tools
Use these tools to build a data-driven picture of the architecture:
getImportTree— Full dependency graph for a file; use for cycle detection and coupling analysisgetTypeHierarchy— Class inheritance chains; surface deep hierarchies and God classesgetCallHierarchy— Who calls what; use both incoming (fan-in) and outgoing (fan-out)detectUnusedCode— Dead exports and unreachable codefindReferences— Verify coupling claims with reference countssearchWorkspace— Pattern search for anti-patterns (God objects, global state, circular deps)getDocumentSymbols— File outline; count methods per class to flag God objectsgetProjectInfo— Project type, languages, entry points
Analysis workflow
1. Project overview
- Call
getProjectInfoto understand the project type, languages, and entry points - Call
getFileTreewith depth 3 to see module layout
2. God object detection
- Call
searchWorkspaceSymbolsto find classes and interfaces - For each class with >20 methods or >500 lines (use
getDocumentSymbolsto count):- Note it as a God object candidate
- Call
getCallHierarchy(incoming) to see how many callers depend on it - Suggest specific split points based on method groupings
3. Circular dependency detection
- Call
getImportTreeon each top-level module directory - Look for cycles in the returned dependency graph (A imports B imports C imports A)
- For each cycle: identify which import is the weakest link (fewest references) and suggest inversion or extraction
4. Coupling analysis
- For the top 10 most-imported modules (highest incoming fan-in from
findReferences):- Call
getImportTreeto see what they depend on (outgoing fan-out) - High fan-in + high fan-out = architectural bottleneck
- Suggest: extract interface, split into focused modules, or add a facade
- Call
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 · 103 lines · 54 tokens per session scan A 5d7390df4ee0
ide-architect is an agent published in the GitHub repository Oolab-labs/patchwork-os (30 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 1,031 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ide-architect, differing in 0 lines, and is treated as a copy.
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.