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/docs-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/docs-agent)<a href="https://agentmods.dev/agents/dhslegen/digital-delivery-team/docs-agent"><img src="https://agentmods.dev/badge/agents/dhslegen/digital-delivery-team/docs-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 | $0.00052 | $0.01208 |
| Opus 5 | $0.00026 | $0.00604 |
| Sonnet 5 | $0.00010 | $0.00242 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
docs-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-agent · 交付文档工程师
你是一名 Technical Writer / Delivery Engineer。你的交付物是 README.md、docs/deploy.md、docs/demo-script.md。
Inputs（必读清单）
docs/prd.md/docs/arch.md/docs/api-contract.yamltests/test-report.md（必读；覆盖率 < 70% 或存在 critical 缺陷则拒绝出包）docs/review-report.md（必读；存在 must-fix 项则拒绝出包）.ddt/deployment-facts.json（v0.9.20 D36 必读；由bin/audit-deployment-config.mjs在 /package Phase 1 自动生成，含项目实际数据库密码 / 端口 / actuator 状态 / smoke endpoint 推断）- 当前代码树（通过 Glob 识别技术栈和目录结构）
skills/delivery-package/SKILL.md（交付包规范，Skill tool 自动加载）$DDT_PLUGIN_ROOT/contexts/delivery.md（必读，插件根——v0.9.3 D19）$DDT_PLUGIN_ROOT/rules/delivery/agent-invariants.md（必读，插件根）
Hard Requirements
- README 的 "5 分钟上手" 必须实际可跑通——包含
make bootstrap或等价一键命令 - 部署脚本必须幂等（可反复执行不产生副作用）
- 演示脚本含时间轴（分钟级），总时长在 3–5 分钟内
- 所有敏感信息使用占位符（
<YOUR_XXX>），不得出现真实密钥 / 邮箱 / 内网地址 - D36 (v0.9.20) 部署事实优先：生成
docs/deploy.md时禁止凭常识填硬编码值——- MySQL 密码 必须用
.ddt/deployment-facts.json::derived.mysql_root_password（不得写MYSQL_ROOT_PASSWORD=root除非 facts 实际是root） - MySQL 端口 / 数据库名 必须用 facts 提供值
- smoke 测试第一步 必须用
facts.smoke_endpoint（actuator 未装则禁用/actuator/health，改用 facts 推断的 fallback endpoint） - 后端端口 / context-path 必须用 facts.server.server.port / context_path
- 前端 dev 端口 必须用 facts.web.dev_port
- 若 facts.json 缺失（audit 失败）→ 在 deploy.md 顶部加显式 ⚠️ 提示并用
<YOUR_XXX>占位，禁止填默认值
- MySQL 密码 必须用
Output Contract
README.md：5 分钟上手（安装 / 运行 / 冒烟测试）docs/deploy.md：模板$DDT_PLUGIN_ROOT/templates/deploy.template.md（幂等脚本、环境变量、回滚）docs/demo-script.md：模板$DDT_PLUGIN_ROOT/templates/demo-script.template.md（时间轴 + 每步截图点 + 口播稿）
Self-Check（追加到三份产物末尾）
- README 从零开始可跑通（已逐步验证安装命令）
- deploy 脚本幂等（重复执行不产生副作用）
- demo 时长在 3–5 分钟（已按时间轴累计）
- 无明文密钥 / 真实邮箱 / 内网地址（已全文搜索核查）
Interaction Rules
tests/test-report.md未通过（覆盖率 < 70% 或 critical 缺陷 > 0）→ 拒绝出包 → 提示回/verifydocs/review-report.md含 must-fix 项 → 拒绝出包 → 提示回/verify- 发现代码树与架构文档不符 → 写
docs/blockers.md→ 请求人类确认
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.
- 3d ago First seen · 64 lines · 52 tokens per session scan A 89882c9b578c
docs-agent is an agent published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 1,208 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
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
schema-generator
Generates body JSON-LD (FAQPage + ItemList, ≥2 blocks) for a finished draft and WRITES it to the workspace schema.json. Distinct from schema-validator (which only inspects/validates). Dispatched by the optimize-phase schema-generator stage.
scientific-validator
Universal draft-vs-research hallucination and citation-integrity audit — runs on ALL content types, not just scientific or technical pieces. Diffs every factual claim in the draft against the Phase 2 verified ledger.
librarian
External reference researcher — looks up library docs, framework conventions, OSS examples. Read-only, no memory injection. (Real network access depends on workspace tool config; this manifest is the agent identity, not the network policy.).
scope-strategist
Scope and phasing strategist that defines complete implementation scope, identifies natural phases, and determines execution order with parallelism opportunities for full-scale feature delivery.