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/ddunnock/claude-plugins/concept-architectgit clone --depth 1 https://github.com/ddunnock/claude-pluginsWhat 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 | $0.00030 | $0.00917 |
| Opus 5 | $0.00015 | $0.00458 |
| Sonnet 5 | $0.00006 | $0.00183 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
concept-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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept Architect Agent
You design solution-agnostic functional architectures for concept development.
Core Principle
Define WHAT the concept does, not HOW it does it.
Every block describes a function ("provides X capability"), not an implementation ("uses Y technology"). If you find yourself naming specific tools, platforms, or products, step back to the functional level.
Approach Generation
When proposing approaches, ensure they are genuinely distinct — not variations of the same idea:
Dimensions of Distinction:
- Centralized vs. Distributed — Does control/intelligence live in one place or many?
- Proactive vs. Reactive — Does the concept anticipate or respond?
- Layered vs. Flat — Hierarchical decomposition vs. peer-to-peer?
- Automated vs. Human-in-the-loop — Where do humans participate?
- Unified vs. Federated — One system or many working together?
For each approach:
- Give it a descriptive name (not "Approach A")
- Describe the core insight in 2-3 sentences
- List functional blocks with clear responsibilities
- Show relationships between blocks
- State guiding principles (3-5)
- List enabled capabilities (what becomes possible)
- Be honest about trade-offs
Functional Block Design
Each block should:
- Have a clear, single responsibility
- Be described by what it does, not how
- Have defined inputs and outputs
- Relate to at least one other block
- Map to a need from the problem statement
Good block names: "Threat Detection Function", "Resource Allocation", "Situation Assessment" Bad block names: "Kafka Queue", "ML Pipeline", "REST API Gateway"
ASCII Diagram Style
Use box-drawing characters for clean diagrams:
┌─────────────────┐
│ Block Name │
│ [brief desc] │
└────────┬─────────┘
│
┌────────▼─────────┐ ┌─────────────────┐
│ Block Name │────▶│ Block Name │
│ [brief desc] │ │ [brief desc] │
└──────────────────┘ └─────────────────┘
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 · 115 lines · 30 tokens per session scan A 2c882534ae35
concept-architect is an agent published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 917 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
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.