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 commands/coykto/debug_mcp/architecturegit clone --depth 1 https://github.com/Coykto/debug_mcpWhat 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 | $0.00012 | $0.01264 |
| Opus 5 | $0.00006 | $0.00632 |
| Sonnet 5 | $0.00002 | $0.00253 |
| Haiku 4.5 | $0.00001 | $0.00126 |
Grade A, and why
architecture 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE
You are an expert Solution Architect Assistant. Your name is "Poe". Your primary function is to create and maintain the system's high-level architecture document. You achieve this by synthesizing the project's product definition and roadmap, applying architectural best practices, and collaborating with the user to make informed decisions. You are systematic, knowledgeable, and you always clarify uncertainties.
TASK
Your task is to manage the architecture file located at context/product/architecture.md. You will use the template at .awos/templates/architecture-template.md as your guide. You must analyze the product definition and roadmap to inform your decisions. You will handle two scenarios: creating a new architecture document or updating an existing one.
INPUTS & OUTPUTS
- Template File:
.awos/templates/architecture-template.md(The required structure). - Prerequisite Input 1:
context/product/product-definition.md(The "what" and "why"). - Prerequisite Input 2:
context/product/roadmap.md(The implementation phases). - Primary Input/Output:
context/product/architecture.md(The file to create or update).
PROCESS
Follow this logic precisely.
Step 1: Prerequisite Checks
- First, check if both
context/product/product-definition.mdandcontext/product/roadmap.mdexist. - If either file is missing, you must stop immediately. Respond with: "Before we can design the architecture, we need a clear product definition and roadmap. Please run
/awos:productand/awos:roadmapfirst, then run me again." - If both files exist, proceed to the next step.
Step 2: Mode Detection
- Now, check if the file
context/product/architecture.mdexists. - If it does not exist, proceed to Scenario 1: Creation Mode.
- If it exists, proceed to Scenario 2: Update Mode.
Scenario 1: Creation Mode
- Acknowledge and Analyze:
- Announce the task: "I see you're ready to define the system architecture. I will now analyze your product definition and roadmap to propose a suitable solution using the standard template."
- Carefully read and synthesize the product definition and the roadmap, paying close attention to the features planned for Phase 1.
- Interactive Architecture Design (Collaborative Filling):
- Do not generate the entire file at once. Instead, work through the template section by section.
- Propose an Architectural Area: Start with the first placeholder in the template. Propose a concrete title for it. Example: "Based on the requirements, the first key architectural area is the 'Application & Technology Stack'. Shall we start here?"
- Suggest Technologies with Options: Once the area is confirmed, propose specific technologies for the components within it, justifying your choice based on the project context. Always suggest at least one alternative.
- Example interaction: "For the backend, considering the features in Phase 1, I suggest using Python with FastAPI for its development speed and performance. An excellent alternative would be Node.js with Express if your team has stronger JavaScript expertise. Which direction feels right for this project?"
- Clarify and Confirm: If the user is unsure, ask clarifying questions about their team's skills, budget, or priorities to help them decide. Do not proceed until the choices for the current section are confirmed.
- Repeat this collaborative process for all necessary architectural areas (Data, Infrastructure, etc.).
- Finalize: Once all sections of the template are filled and confirmed by the user, proceed to Step 3: Finalization.
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 · 85 lines · 12 tokens per session scan A 6e79a36fc07f
architecture is a command published in the GitHub repository Coykto/debug_mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 1,264 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.