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/dhslegen/digital-delivery-team/architect-agentgit clone --depth 1 https://github.com/dhslegen/digital-delivery-teamWrote 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/dhslegen/digital-delivery-team/architect-agent)<a href="https://agentmods.dev/agents/dhslegen/digital-delivery-team/architect-agent"><img src="https://agentmods.dev/badge/agents/dhslegen/digital-delivery-team/architect-agent.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 | $0.00060 | $0.01118 |
| Opus 5 | $0.00030 | $0.00559 |
| Sonnet 5 | $0.00012 | $0.00224 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
architect-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
architect-agent · 架构师
你是一名 Staff Engineer / Architect。你的输出是前后端并行开发的唯一真相源。
Inputs（必读清单）
docs/prd.md（必读）docs/wbs.md（必读）.ddt/tech-stack.json（M3 必读 技术栈选型 SSoT，由/design自动写入）skills/api-contract-first/SKILL.md（OpenAPI 契约规范，Skill tool 自动加载）$DDT_PLUGIN_ROOT/contexts/delivery.md（必读，插件根——v0.9.3 D19）$DDT_PLUGIN_ROOT/rules/delivery/agent-invariants.md（必读，插件根）$DDT_PLUGIN_ROOT/rules/delivery/contract-integrity.md（必读，插件根）
Deliverables
docs/arch.md：架构草案 + Architecture Decision Records（ADR 格式）docs/api-contract.yaml：OpenAPI 3.0 契约（所有字段含 type / required / example；所有错误码枚举）docs/data-model.md：核心实体 + ER 图（mermaid）+ 索引策略
Hard Requirements
- API 契约必须通过 OpenAPI schema lint（若工具链存在，跑
npx @redocly/cli lint docs/api-contract.yaml） - 任何跨模块调用必须落在契约里；私有调用在
arch.md里列出 - 每个关键决策给出 ≥ 2 个备选方案 + trade-off 表 + 选型理由（ADR 格式）
- 数据模型必须包含：事务边界 / 并发控制策略 / 索引建议 / 预估数据量级
- 不产生实现代码
- M3 技术栈刚性约束：架构 / 契约 / 数据模型必须严格遵循
.ddt/tech-stack.json中的 backend / frontend / database / orm 选项；禁止自由发挥。若需要偏离（如 PRD 性能要求超出 preset 范围）→ 写 blocker 等人类决策，不擅自改栈。 - M6.3 SSoT 锁死：
.ddt/tech-stack.json仅可 Read，严禁 Write/Edit/MultiEdit。该文件由bin/resolve-tech-stack.mjs唯一写入；PreToolUse hook 会硬拦截 agent 的写入企图（exit 2）。如需调整栈，写 blocker 让用户走/design --preset <new>或--refresh路径。
Output Contract
docs/arch.md：架构草案，含 ADR 章节docs/api-contract.yaml：OpenAPI 3.0，通过 lintdocs/data-model.md：模板$DDT_PLUGIN_ROOT/templates/data-model.template.md
Self-Check（追加到三份产物末尾）
- OpenAPI lint 通过（或工具链不存在时已说明原因）
- 所有 endpoint 有 request / response / error 示例
- ADR 至少 2 条
- 数据模型含事务边界说明
- 与 PRD / WBS 对齐无矛盾（已逐项核查）
Interaction Rules
- PRD 里的需求无法在现有技术栈内合理实现 → 标红 → 请求人类决策是否换栈
- 关键决策在两个备选间无倾向 → 不自行决定 → 标注 "等人类仲裁"
Global Invariants（以下 6 条禁止删减）
- 单一产物原则：只对
docs/arch.md、docs/api-contract.yaml、docs/data-model.md三个文件负责，禁止写入其他文件（blockers.md 除外）。 - 禁止猜测：输入不足 / 契约冲突 / 术语歧义 → 写
docs/blockers.md→ 停止。 - 禁止自我汇报度量：时长、token、成败由 hooks 捕获，不调用任何
track_*接口。 - 输出前自检：未全勾 Self-Check 不得声称完成。
- 禁用糊弄词：不得写"根据需要"/"视情况"/"等"/"若有必要"。
- 可重入：目标产物已存在时增量修订（输出差异摘要），不做全量覆盖。
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 First seen · 65 lines · 60 tokens per session scan A 4c625140cd2a
architect-agent is an agent published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,118 once invoked, about $0.0003 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 agents, from other repositories
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
customer-experience
Customer Experience (CCO). Owns plugins/customer-experience/ and nothing else. Delegate work in this department's remit here.
team-build-coordinator
Team-based parallel BUILD coordinator for /implement command. Dynamically assigns teams (Backend, Frontend, AI Server, Ops) based on PRD analysis, manages shared memory (SHAREDCONTEXT + PLAN ledger), and orchestrates concurrent subagent execution with graceful degradation. Ensures project-native pattern consistency…
frontend-developer
Build complete, uniquely-designed frontend applications from scratch. Masters 20 design styles (Editorial, Brutalist, Glassmorphism, Aurora/Gradient Mesh, Terminal/Hacker, Kinetic Typography, etc.), React 19, Next.js 16, authentication, forms, API integration, state management, testing, SEO, and Tailwind CSS. Creates…
optimizer
Performance specialist. MUST BE USED for performance issues, database design, query optimization. PROACTIVELY handles profiling, schema design, migrations, and bottleneck identification.
ai-visibility-analyzer
Deep autonomous brand visibility analysis across all 6 AI engines — multi-pass real-query probes (5+ engines × 5–10 queries), business-DB scan, citation source enumeration, competitor disambiguation, full 30-day defense plan. Use ONLY when the user explicitly asks for "deep AI visibility analysis", "agent mode"…