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 commands/dhslegen/digital-delivery-team/relaygit 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/commands/dhslegen/digital-delivery-team/relay)<a href="https://agentmods.dev/commands/dhslegen/digital-delivery-team/relay"><img src="https://agentmods.dev/badge/commands/dhslegen/digital-delivery-team/relay.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 | $0.00039 | $0.01056 |
| Opus 5 | $0.00019 | $0.00528 |
| Sonnet 5 | $0.00008 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade B, and why
relay scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT=$(cat "${HOME}/.claude/delivery-metrics/.ddt-plugin-root" 2>/dev/null) How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/relay
跨会话 / 跨 AI 接力不失忆。一键生成 AI 友好的 prompt,用户复制到下一会话即可无缝续作。
何时使用
- 当前会话 token 接近上限,需要切到新会话
- 把项目交给同事 / 自己换设备
- 切换 AI 模型(Claude → GPT → Gemini)
- 长项目阶段性归档备份
执行
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT=$(cat "${HOME}/.claude/delivery-metrics/.ddt-plugin-root" 2>/dev/null)
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || DDT_PLUGIN_ROOT="${HOME}/.claude/plugins/marketplaces/digital-delivery-team"
[ -f "$DDT_PLUGIN_ROOT/bin/aggregate.mjs" ] || { echo "❌ DDT plugin root 未解析。可能原因:(1) 插件未安装;(2) shell 中 DDT_PLUGIN_ROOT 指向无效路径,请 unset DDT_PLUGIN_ROOT 后重启会话;(3) 运行 /digital-delivery-team:doctor 自检"; exit 1; }
export DDT_PLUGIN_ROOT
node "$DDT_PLUGIN_ROOT/bin/build-relay-prompt.mjs" $ARGUMENTS
输出位置:
- 屏幕:完整 prompt(用户可一键复制)
- 文件:
.ddt/relay-<YYYYMMDD-HHMMSS>.md(归档备份)
13 段式模板
DDT 自动填的 4 段:
- 项目背景(项目 ID / 当前 phase / 已完成 phase / 技术栈摘要 / 关键产物路径)
- Git 摘要(分支 / 最近 5 commits / 未提交改动)
- 续作必做指南(接力 AI 第一步做什么)
- 元数据(生成时间戳 / DDT 版本)
LLM 在生成 prompt 时必须补充的 9 段:
- What We Are Building — 项目目标
- What WORKED (with evidence) — 已验证有效(带证据)
- What Did NOT Work (and why) — 失败尝试 + 精确原因(最关键)
- What Has NOT Been Tried Yet — 未尝试方向
- Current State of Files — 文件状态表
- Decisions Made — 关键决策 + 理由
- Blockers & Open Questions — 阻塞与未答问题
- Exact Next Step — 下一步精确指令
- Environment & Setup Notes(可选)— 启动命令 / 环境变量
使用示例
跨会话续作
# 旧会话
/relay
# 屏幕显示完整 prompt,用户 Cmd+A 全选 + Cmd+C 复制
# 新会话(同设备 / 不同设备 / 不同 AI 都可)
[粘贴 prompt 到第一句对话]
# AI 立即知道:项目在哪、做到哪步、下一步做什么、什么不要重试
与同事交接
/relay --out shared/handoff-2026-04-29.md
# 文件可直接给同事;同事在他的 Claude Code 里粘贴文件内容续作
切换 AI 模型
/relay --quiet --out /tmp/relay.md
cat /tmp/relay.md | pbcopy # macOS 复制到剪贴板
# 在 ChatGPT / Gemini 里粘贴 → AI 接手
与 /resume 的差异
| 命令 | 用途 | 输出 |
|---|---|---|
/digital-delivery-team:resume |
同会话自动恢复 | 屏幕(briefing) |
/digital-delivery-team:relay |
跨会话/跨设备/跨 AI 接力 | prompt 文件 + 屏幕 |
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.
- 6d ago First seen · 98 lines · 39 tokens per session scan B 2636705bc2f3
relay is a command published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,056 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
show
Show this project's saved Recall context (.recall/context.md).
ccc-context-budget
Visual context window budget analyzer — shows usage gauge, identifies bloat sources, recommends when to save session and compact.
context
Analyze and optimize Claude Code's context configuration (analyze, optimize, or reset).
pin
Break checkpoint — status display, session log, optional MEMORY.md update.
atlas
Cross-project atlas with an adaptive render — ≤4 projects in scope get detail cards, more get one aligned digest line each, grouped by domain. Facets projects · sessions · memory · plans · specs · plugins · claude.md; a bare run renders all of them except plugins (opt-in, machine-global). --dir NAME|PATH anchors the…