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 skills add dhslegen/digital-delivery-team --skill decision-gategit 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/skills/dhslegen/digital-delivery-team/decision-gate)<a href="https://agentmods.dev/skills/dhslegen/digital-delivery-team/decision-gate"><img src="https://agentmods.dev/badge/skills/dhslegen/digital-delivery-team/decision-gate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dhslegen/digital-delivery-team/decision-gate"><img src="https://agentmods.dev/badge/skills/dhslegen/digital-delivery-team/decision-gate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.02646 |
| Opus 5 | $0.00031 | $0.01323 |
| Sonnet 5 | $0.00012 | $0.00529 |
| Haiku 4.5 | $0.00006 | $0.00265 |
Grade A, and why
decision-gate 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 8d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Gate · 用户决策门
M6.2 整改:解决 v0.5.x "盲盒严重" 痛点——agent 包办所有决策。每个 phase 落盘后强制用 AskUserQuestion 让用户参与,让 DDT 从"包办式"转向"协作式"。
何时触发
任何 phase 命令的 Phase 5(汇总输出)末尾、Phase 6(emit-phase end)之前。10 个 phase command 都必须按本 skill 操作: prd / wbs / design / build-api / build-web / test / review / fix / package / report
也包括编排命令 /kickoff 中各内部 step 之间(除非用户传 --auto)。
决策门标准 4 选项
LLM 必须调用 AskUserQuestion 工具,按以下模板:
{
questions: [{
question: "<phase 中文名>已生成(<关键指标摘要>),如何继续?",
header: "<8 字以内 phase 标识>", // 如 "PRD review" / "Design review"
multiSelect: false,
options: [
{
label: "接受并继续 (Recommended)",
description: "进入 <下一 phase 命令>",
preview: "<本 phase 产物的 1-2 段摘要>" // 让用户在选项面板就能扫一眼内容
},
{
label: "修改某条具体内容",
description: "我会指出哪条 + 怎么改(LLM 收到后用 --refresh 增量改)"
},
{
label: "新增内容",
description: "我有遗漏的需求/字段/约束要补充"
},
{
label: "重新生成(带说明)",
description: "整体方向不对,重写本 phase(LLM 收到后用 --refresh 重做)"
}
]
}]
}
注意:
- 第 1 个选项标
(Recommended)让用户最快路径走完 - AskUserQuestion 自动加 "Other" 让用户填自定义文本
- preview 字段(仅单选支持)展示本 phase 关键输出,让用户不用打开文件即可决策
- 不要在 multiSelect=true 时用 preview(工具不支持)
决策事件采集(M6.2.2)
调用 AskUserQuestion 之前必须 emit decision_point:
node "$DDT_PLUGIN_ROOT/bin/emit-decision.mjs" \
--phase <phase-name> \
--action point \
--options "accept|modify|add|regenerate"
收到用户答案后立即 emit decision_resolved:
node "$DDT_PLUGIN_ROOT/bin/emit-decision.mjs" \
--phase <phase-name> \
--action resolved \
--user-action <accept|modify|add|regenerate|other> \
--note "<用户备注摘要,≤200 字>"
这两条事件让 metrics-agent 后续能分析"哪个 phase 改最多次",反馈到 baseline 调优。
决策处理逻辑
| 用户选择 | LLM 行为 |
|---|---|
| 接受并继续 | 标 phase 完成(emit-phase end)+ 提示下一步命令;不要主动跑下一命令(让用户决定时机) |
| 修改某条具体内容 | 进一步问"哪条?怎么改?"(再调一次 AskUserQuestion 或直接对话),收到后用 --refresh 增量修订;修订完再走一次决策门 |
| 新增内容 | 问"补充什么内容?",收到后用 --refresh 增量新增 |
| 重新生成(带说明) | 问"原因是什么?要保留什么?",收到后用 --refresh 重生成;保留已验证的部分 |
| Other(自定义文本) | 解析用户意图,按上述 4 类映射处理;映射不上时写 blocker 等用户进一步澄清 |
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.
- 8d ago First seen · 173 lines · 62 tokens per session scan A f4a7ab217b1a
decision-gate is a skill published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 2,646 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 skills, from other repositories
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
team-memory-protocol
A shared-memory process for teams of coding agents working on the same build. It stores project knowledge, shared context, and task progress in separate files or repositories.
knowledge-wiki
A tool that turns useful lessons from coding sessions into general articles for a team wiki. A wiki is a collection of linked reference pages, and this one can be kept locally or shared through a Git repository.
handdrawn-diagram
Generate a hand-drawn (sketch-style) architecture or flow diagram as a committable image (SVG + PNG). Use when the user wants a sketch-aesthetic diagram for a README, docs, or hackathon/Devpost submission that still has correct, legible text and per-group color. Authors a Mermaid look:handDrawn source and renders it…
code-review-levels
Reference documents for deep code review (Level 3) and architecture review (Level 4). Used by code-reviewer agent for advanced review levels.
version-sentinel
Use when adding, bumping, or changing a dependency in package.json, requirements.txt, constraints.txt, pyproject.toml, Cargo.toml, .csproj, .fsproj, or .vbproj. Triggered automatically by version-sentinel's PreToolUse hook (where the host supports hooks) — this skill explains how to satisfy the block and record a…