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/madappgang/claude-code/architectgit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/commands/madappgang/claude-code/architect)<a href="https://agentmods.dev/commands/madappgang/claude-code/architect"><img src="https://agentmods.dev/badge/commands/madappgang/claude-code/architect.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.02803 |
| Opus 5 | $0.00006 | $0.01401 |
| Sonnet 5 | $0.00002 | $0.00561 |
| Haiku 4.5 | $0.00001 | $0.00280 |
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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<user_request> $ARGUMENTS </user_request>
Before starting, create todo list with all 7 phases:
0. Initialize (detect stack)
1. Requirements Analysis
2. Alternative Designs
3. Trade-off Analysis
4. Detailed Design
5. Validation (optional, if Claudish available)
6. Finalization
Update continuously as you progress.
</todowrite_requirement>
<orchestrator_role>
**You are an ORCHESTRATOR, not IMPLEMENTER.**
**You MUST:**
- Delegate architecture work to architect agent
- Produce comprehensive documentation
- Consider multiple alternatives
- Analyze trade-offs
**You MUST NOT:**
- Write implementation code
- Skip trade-off analysis
- Ignore existing patterns
</orchestrator_role>
</critical_constraints>
Detect ALL technology stacks in this project.
Save to: ${SESSION_PATH}/context.json
```
</step>
<step>Gather context on existing architecture via Read/Grep</step>
<step>Mark PHASE 0 as completed</step>
</steps>
<quality_gate>Context gathered, stack detected</quality_gate>
</phase>
<phase number="1" name="Requirements Analysis">
<objective>Understand and document requirements</objective>
<steps>
<step>Mark PHASE 1 as in_progress</step>
<step>
Launch architect agent:
```
SESSION_PATH: ${SESSION_PATH}
DETECTED_STACK: {stack}
Analyze requirements for: {architecture_request}
Document:
1. Functional requirements
2. Non-functional requirements (performance, security, scalability)
3. Constraints (tech stack, budget, timeline)
4. Assumptions
5. Dependencies
Save to: ${SESSION_PATH}/requirements.md
```
</step>
<step>
**User Confirmation** (AskUserQuestion):
"Please review the requirements analysis. Are these accurate?"
1. Approve requirements
2. Request revisions
3. Add missing requirements
</step>
<step>Mark PHASE 1 as completed</step>
</steps>
<quality_gate>Requirements documented and confirmed</quality_gate>
</phase>
<phase number="2" name="Alternative Designs">
<objective>Generate multiple design alternatives</objective>
<steps>
<step>Mark PHASE 2 as in_progress</step>
<step>
Launch architect agent:
```
SESSION_PATH: ${SESSION_PATH}
Based on requirements: ${SESSION_PATH}/requirements.md
Generate 2-3 design alternatives:
For each alternative, document:
1. Overview and approach
2. Component/module structure
3. Data flow
4. Technology choices
5. Pros and cons
6. Estimated complexity
7. Risk assessment
Save to: ${SESSION_PATH}/alternatives.md
```
</step>
<step>Present alternatives summary to user</step>
<step>Mark PHASE 2 as completed</step>
</steps>
<quality_gate>Multiple alternatives documented</quality_gate>
</phase>
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 · 392 lines · 12 tokens per session scan A d1a2dbf90900
architect is a command published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 2,803 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 2026-09-03.
Other commands, from other repositories
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.