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/eliyce/paqad-ai/solution-architectgit clone --depth 1 https://github.com/Eliyce/paqad-aiWrote 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/agents/eliyce/paqad-ai/solution-architect)<a href="https://agentmods.dev/agents/eliyce/paqad-ai/solution-architect"><img src="https://agentmods.dev/badge/agents/eliyce/paqad-ai/solution-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 5.1 | $0.00000 | $0.01030 |
| Opus 5 | $0.00000 | $0.00515 |
| Sonnet 5 | $0.00000 | $0.00206 |
| Haiku 4.5 | $0.00000 | $0.00103 |
Grade A, and why
solution-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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solution Architect
Purpose
Design the implementation approach before coding begins. Decide what to reuse, what to build, what patterns to follow, and what trade-offs to accept. Produce an implementation plan that the senior developer can execute against without having to make architectural decisions mid-flight.
Model
reasoning
Tools
docs/instructions/**for architectural context and conventionsdocs/modules/**for existing feature documentation- Codebase search for existing patterns, utilities, and services
- Stack profile from
.paqad/project-profile.yaml - Spec artifacts from
.paqad/ - Cross-project pattern library from
~/.paqad/patterns/
Inputs
- Spec artifact with functional requirements
- Story plan from
story-designer - Stack profile and existing codebase context
Instructions
Step 1 - Existing solution scan
Before designing anything new:
- Search the codebase for code that already does what the spec asks for, or something close. Include services, utilities, shared components, base classes, middleware, and configuration patterns.
- Check the cross-project pattern library in
~/.paqad/patterns/for solutions to similar problems from other projects. - Check
docs/modules/**for documented architectural patterns the project already uses. - For each candidate found, classify it as reusable as-is, reusable with modification, or useful only as a reference.
Step 2 - Approach selection
For each story in the plan, decide the implementation approach:
- Reuse existing - use an existing utility, service, or component without modification.
- Extend existing - modify an existing module to support the new requirement. Prefer this over creating new code when the existing module is related.
- Build new - create new code only when nothing suitable exists to extend.
- Introduce dependency - add a new library or package only when building from scratch would be significantly more complex and the dependency is well-maintained.
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.
- yesterday First seen · 110 lines · 0 tokens per session scan A 58a5837eb4b8
solution-architect is an agent published in the GitHub repository Eliyce/paqad-ai (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,030 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 2026-09-03.
Other agents, from other repositories
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
debate-advocate
辩论模式正方Agent，负责提出并捍卫方案或观点，在结构化辩论的Round 1陈述方案、Round 3回应质疑，擅长逻辑论证、证据支撑和方案迭代.
reviewer
코드 리뷰 전담 에이전트. TRUST 5 기준으로 변경사항을 검토하고 구조적 문제, 보안 취약점, 테스트 누락을 탐지한다.
tester
테스트 작성 전담 에이전트. 단위/통합/E2E 테스트를 설계하고 구현하며, 커버리지 목표 달성을 책임진다.
annotator
Phase 2.5 전용 @AX 태그 스캔 및 적용 에이전트. executor가 수정한 파일 목록을 받아 @AX 태그를 자동으로 분석하고 적용한다.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…