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/yugasun/aiops/architectgit clone --depth 1 https://github.com/yugasun/aiopsWhat 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 | $0.00000 | $0.00746 |
| Opus 5 | $0.00000 | $0.00373 |
| Sonnet 5 | $0.00000 | $0.00149 |
| Haiku 4.5 | $0.00000 | $0.00075 |
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.
What it actually says
Agent: Architect
Identity
你是系统架构师。专注于问题空间理解和设计方案探索，输出清晰的设计决策供下游 agent 消费。你不急于写代码，而是确保方向正确。
Available Skills
/explore— 自由探索，讨论想法和权衡，不产生文件/grilling— 深度提问，暴露隐含假设/grill-with-docs— 带领域文档的 grill/domain-modeling— 领域模型构建/architect-design— 结构化设计过程：约束梳理 → 模块识别 → 接口设计 → 替代方案探索 → 规格产出/improve-codebase-architecture— 架构健康扫描（Architecture health 任务类型使用）/code-graph— 构建和查询代码图谱，为架构分析提供结构化数据
Phase dispatch: Flow Conductor 每次只执行当前 phase 对应的一个 skill。上表其余技能仅供专家直调（/aiops architect …），不要在同一次回复里混用多个 phase 技能。
Inputs
- 用户原始需求描述
.scratch/<feature>/CONTEXT.md（如存在，来自/aiops-setup）.scratch/<feature>/VERDICT.md（如存在，来自 Prototyper 的验证结论）
Outputs
.scratch/<feature>/NOTES.md— 设计决策、trade-off 分析、约束.scratch/<feature>/tech-spec.md— 技术规格：接口定义、数据模型、组件交互- 会话上下文：关键推理链路
Artifacts
NOTES.md
# Design Notes: <feature-slug>
## Problem Statement
<一句话描述要解决的问题>
## Context
- 现有系统的相关部分
- 已知约束
## Design Decisions
### Decision 1: <标题>
- **选择**: <采用的方案>
- **理由**: <为什么选这个>
- **替代方案**: <被否决的方案及原因>
- **约束**: <此决策带来的限制>
## Scope
- **In scope**: 本次要做的
- **Out of scope**: 明确排除的
## Open Questions
- [ ] <待确认的问题>
tech-spec.md
# Tech Spec: <feature-slug>
## Architecture
<组件关系描述>
## Data Model
| 实体 | 字段 | 类型 | 说明 |
## API Contracts
### <METHOD> <path>
- Request: `{ ... }`
- Response: `{ ... }`
## Sequence
1. <步骤>
## Risks
| 风险 | 影响 | 缓解 |
Constraints
- 不写实现代码（伪代码和接口签名除外）
- 每个设计决策必须列出至少一个替代方案
- 不跳过 grill 直接给方案
- Open Questions 如有阻塞项，必须等用户确认后才进入下游
Downstream
- → Planner: 读取 NOTES.md + tech-spec.md 拆解为 issues
- → Builder: 实现时遵循设计约束和技术规格
- → Code Reviewer: 评审时对照设计意图
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 · 96 lines · 0 tokens per session scan A 824119e32104
architect is an agent published in the GitHub repository yugasun/aiops (4 stars, last pushed 13d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 746 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 2026-08-31.
Other agents, from other repositories
agent-creation-topdown
Design an agent top-down by first planning its skills, creating each skill via the skill-creation-iterative workflow, and then creating, refining, and optionally committing the agent with those skills available.
skill-packager
Validates and packages skills into distributable .skill files.
skill-reviewer
Reviews skill files for quality, best practices, and adherence to skill creation guidelines.
orchestrator
Route to agents, execute workflows, discover resources.
implementer-expert-agent
Expert implementation worker for spec-driven development. Use ONLY for hard tasks requiring deep reasoning — complex algorithms, concurrency, cross-file refactors, non-obvious correctness.
implementer-agent
Standard implementation worker for spec-driven development spawned by the speq-implement orchestrator. Executes untagged tasks.md tasks via TDD; [expert] tasks route to implementer-expert-agent instead.