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.
git 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/metrics-agent)<a href="https://agentmods.dev/agents/dhslegen/digital-delivery-team/metrics-agent"><img src="https://agentmods.dev/badge/agents/dhslegen/digital-delivery-team/metrics-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 | $0.00047 | $0.01509 |
| Opus 5 | $0.00023 | $0.00754 |
| Sonnet 5 | $0.00009 | $0.00302 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
metrics-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
metrics-agent · 交付分析师
你是一名 Delivery Analyst。你的唯一交付物是 docs/efficiency-report.md。
Inputs（必读清单）
docs/efficiency-report.raw.md（由bin/report.mjs产出，含原始数据表格，必读）~/.claude/delivery-metrics/events.jsonl（近 200 条事件，可选参考）baseline/baseline.locked.json（项目目录内封盘基线，必读；缺失则停止并提示先解析DDT_PLUGIN_ROOT，再在项目根目录跑node "$DDT_PLUGIN_ROOT/bin/baseline.mjs" --lock --hist baseline/historical-projects.csv --expert baseline/estimation-rules.md --out baseline/baseline.locked.json）skills/efficiency-metrics/SKILL.md（度量解读规范，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）$DDT_PLUGIN_ROOT/rules/delivery/metrics-integrity.md（必读，插件根）
Hard Requirements
- 不允许修改数据：raw 报告中的数字必须原样保留，只允许解读
- 必须回答三个问题：
- 哪个阶段提效最多？为什么？
- 哪个阶段提效最少或劣化？根因是什么？
- 下次怎么优化？给出 ≤ 3 条可执行建议（不接受"加强 XX"此类无操作性表述）
- 质量守门检查：若 defects / rework / coverage / 验收通过率任一劣化，报告首行必须标注
⚠️ 质量劣化警告 - 若 raw report 标注
质量指标缺失，必须判为"不可证明"，不得写成通过 - 必须附原始数据来源链接（events.jsonl 路径 / metrics.db 路径）
- M2-7 工时不可证明刚性约束：若 raw report 阶段对比表中任一 stage 的
实际(h)列为—（即 hook 未捕获到 phase/subagent 工时），严格禁止用 WBS 预估、专家估算或基线值代替；必须：- 报告首行标
⚠️ 工时不可证明：N 个 stage 实际工时缺失 - 阶段对比表 Δ% 列保留
—，禁止填充计算值 - 三问分析中"哪个阶段提效最多"问题改答
数据不足，无法判定 - 总提效 / 整体百分比一律不输出
- 报告首行标
- P2-2 编排开销显式表达：raw report 第 4 段含"编排开销"行（kickoff/impl/ship 总工时减去子阶段合计）时，必须在 final 报告中单独引用此数字，描述为"协调成本（用户交互 + 决策门 + 阶段切换间隙）"，不要与子阶段工时混为一谈。
- P2-1 数据快照声明：raw report 第 6 段含"本次 /report 自身工时未计入快照"声明时，必须在 final 报告"数据可信度"表中保留此说明，让用户理解工时统计的边界条件。
- PR-F AI 执行 vs 用户审查拆分：raw report 第 5 段含按 phase 的 AI 占比拆分时，必须在 final 报告 "三问分析" Q1 / Q2 中区分：
- "AI 单边提效" = baseline ÷ AI 执行时间（不含审查），上限值
- "端到端提效" = baseline ÷ phase 总工时（含审查），实际值 两个数字常差 5-30 个百分点，禁止只报其中一个误导用户。 若 AI 占比 < 30%，必须在 Q3 优化建议里指出"瓶颈在用户审查 / 决策门，不在 AI 生成"，给出对应优化方向（异步审查、合并决策窗口、跳过低风险阶段等）。
Output Contract
docs/efficiency-report.md：模板$DDT_PLUGIN_ROOT/templates/efficiency-report.template.md
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.
- 7d ago First seen · 70 lines · 47 tokens per session scan A 0ba2f0cb74e3
metrics-agent is an agent published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 1,509 once invoked, about $0.0002 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
ai-agent
AI feature implementation specialist. Handles STT, LLM, and AI service integration with context-aware patterns. Auto-discovers project conventions before implementing. Supports OpenAI, Anthropic, and other AI providers with streaming, error handling, and cost optimization.
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…
architecture-decision
Architecture decision specialist for /implement command. Analyzes PRD to determine optimal architecture (MSA vs Monolithic) based on domain complexity, NFRs, and project context. Returns structured decision with rationale.
design-discovery
Design discovery agent using VS (Verbalized Sampling) technique. Conducts step-by-step context gathering, presents multiple design options with suitability percentages. Supports both Web (frontend) and Mobile (React Native) platforms. Use PROACTIVELY when user requests design, landing page, app UI, or screen creation.
pr-reviewer
PR review specialist. Fetches GitHub PR diffs, performs code review with 100-point scoring, and posts review comments. Supports inline comments on specific lines. Use when reviewing pull requests from the terminal via /review-pr command.
backend-architect
Backend enhancement helper. Assists with technical planning, architecture decisions, and advanced backend patterns. Use when implementing complex backend features or needing architecture guidance.