Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rjwalters/kicad-toolsnpx agentmods add commands/rjwalters/kicad-tools/architect-patternsWrote 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/rjwalters/kicad-tools/architect-patterns)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/architect-patterns"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/architect-patterns/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/commands/rjwalters/kicad-tools/architect-patterns"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/architect-patterns.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 | $0.00000 | $0.04133 |
| Opus 5.5 | $0.00000 | $0.01653 |
| Sonnet 5.5 | $0.00000 | $0.00827 |
| Haiku 4.5 | $0.00000 | $0.00413 |
Grade A, and why
architect-patterns 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 5d 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 — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect Patterns and Templates
This file contains detailed templates, examples, and patterns for creating architectural proposals. Load this file when you need to create proposals or epics.
Parent file: architect.md contains core instructions and workflow.
Contents
- Issue Template
- Issue Creation Command
- Autonomous Mode Assumptions Template
- Requirements Gathering Examples
- Epic Proposals
- Tracking Dependencies with Task Lists
- Goal Discovery Script
- Backlog Balance Check Script
- Milestone Alignment Examples
Issue Template
Use this template when creating architectural proposals:
## Problem Statement
Describe the architectural issue or opportunity. Why does this matter?
## Milestone Alignment
**Current Milestone**: [e.g., "M0 - Bootstrap" or "unknown if no roadmap found"]
**Alignment Tier**: [Tier 1 - Goal-Advancing | Tier 2 - Goal-Supporting | Tier 3 - General Improvement]
**Related Deliverable**: [If Tier 1/2, which specific deliverable does this advance?]
**Justification**: [Why this proposal matters for the current milestone]
## Current State
How does the system work today? What are the pain points?
## Requirements Gathered
Summarize the key constraints, priorities, and context from user responses:
- **Constraint**: [e.g., "500MB storage budget"]
- **Priority**: [e.g., "Simplicity over performance"]
- **Context**: [e.g., "Weekly re-analysis pattern"]
- **Existing**: [e.g., "Already using Redis for session storage"]
## Recommended Solution
**Approach**: [Single recommended approach name and brief description]
**Why This Approach**:
- Fits constraint: [How it addresses their specific constraint]
- Aligns with priority: [How it matches their stated priority]
- Matches context: [How it fits their usage pattern]
- Integrates well: [How it works with existing systems]
**Implementation**:
- [Key implementation steps or components]
- [Technical details relevant to this approach]
**Complexity**: Estimate (Low/Medium/High with brief justification)
**Dependencies**: Related issues or prerequisites (if any)
## Alternatives Considered
Briefly document other options you evaluated and why they were ruled out:
**[Alternative 1]**: [Why it doesn't fit] (e.g., "Manual invalidation - doesn't match preference for automatic cleanup")
**[Alternative 2]**: [Why it doesn't fit] (e.g., "LRU eviction - poor cache hit ratio for their access patterns")
## Impact
- **Files affected**: Rough estimate
- **Breaking changes**: Yes/No
- **Migration path**: How to transition
- **Risks**: What could go wrong
## Related
- Links to related issues, PRs, docs
- References to similar patterns in other projects
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.
- 5d ago Changed 9cb49f277c97
- 6d ago Changed · -15 lines 6d01211f769d
- 20d ago Changed ade1e7e14288
- 1mo ago Changed · +14 lines 8a7ed4e91598
- 1mo ago First seen · 552 lines · 0 tokens per session scan A b9e8b6369533
architect-patterns is a command published in the GitHub repository rjwalters/kicad-tools (70 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,133 tokens. 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 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.