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 ddt-baseline-syncgit 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/ddt-baseline-sync)<a href="https://agentmods.dev/skills/dhslegen/digital-delivery-team/ddt-baseline-sync"><img src="https://agentmods.dev/badge/skills/dhslegen/digital-delivery-team/ddt-baseline-sync/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/ddt-baseline-sync"><img src="https://agentmods.dev/badge/skills/dhslegen/digital-delivery-team/ddt-baseline-sync.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 | $0.00173 | $0.02781 |
| Opus 5 | $0.00086 | $0.01391 |
| Sonnet 5 | $0.00035 | $0.00556 |
| Haiku 4.5 | $0.00017 | $0.00278 |
Grade B, and why
ddt-baseline-sync scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
PR="${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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DDT Baseline Sync · 人员表 → 历史项目工时基线
使命：把"已知项目的真实工时数据"沉淀到 DDT baseline，让 pm-agent 在 /wbs 阶段从"凭模板"升级到"按真实历史校准"。 范围：仅做 baseline CSV 增量。不写 brief、不出 PRD、不动其他产物。 触发模式：独立调用 / 被 ddt-brief-builder 协同调用（识别到 baseline 信息源时）。
何时触发
| 信号 | 处理 |
|---|---|
| 用户显式说"导入工时" / "录入人员表" / "baseline 校准" / "historical-projects 增量" | 主流程 |
| 用户给 xlsx 路径，文件名含"人员需求" / "工时" / "项目计划" / "resource-plan" | 主流程 |
| ddt-brief-builder 识别到 baseline 信息源，AskUserQuestion 确认后转触发本 skill | 协同模式 |
不触发：
- 用户给的是功能清单 xlsx → 触发 ddt-brief-builder（不是 baseline）
- 用户给的是事件流 events.jsonl → 那是 metrics-agent 范围
- 用户问"baseline 怎么用" → 直接回答，不必跑 skill
核心原则（v0.9.7 标准化）
- 模板 vs 数据分离：插件分发的
examples/是教学示例，绝不当用户初始数据；用户项目的 baseline 从assets/historical-projects.template.csv（仅表头）开始累积。 - 可重入幂等：按
project_name查重；同名项目再次导入时进入决策门（skip / overwrite / append-as-new）。 - 项目级优先：baseline 写入用户项目根
<cwd>/baseline/historical-projects.csv；插件根 baseline 仅作 plugin-default schema 兜底，本 skill 不写。 - 工具约束遵守：AskUserQuestion options ≤ 4 项（Claude Code 工具硬约束）。
核心流程
用户给人员表 path
↓
1. dump xlsx（用 ddt-brief-builder 同款 dump-xlsx.py）
↓
2. parse-staffing.py 解析角色 × 人月 × 时间窗
↓
3. AskUserQuestion 让用户确认 / 调整：
- 项目类型（B2B-后台 / SaaS / API-Mobile / 其他）
- 是否追加（追加 / 仅展示 / 完成后再决定）
↓
4. 同名查重：
- 不存在 → 直接 append（HIST-NNN 自增）
- 存在 → 决策门（skip / overwrite / append-as-new）
↓
5. append-historical.mjs 写一行（项目根优先；不存在则用 assets 模板初始化）
↓
6. 输出"baseline 已校准"+ 下一步（跑 pm-agent 时估算更准）
如何调用本 skill 的 scripts/
LLM 跑 Bash 时 cwd 是用户项目根，必须用绝对路径调本 skill 脚本：
# 解析 plugin root（marker 文件 fallback chain）
PR="${DDT_PLUGIN_ROOT:-$(cat "${HOME}/.claude/delivery-metrics/.ddt-plugin-root" 2>/dev/null)}"
PR="${PR:-${HOME}/.claude/plugins/marketplaces/digital-delivery-team}"
# 端到端管道（推荐）
python3 "$PR/skills/ddt-baseline-sync/scripts/parse-staffing.py" <xlsx-path> \
| node "$PR/skills/ddt-baseline-sync/scripts/append-historical.mjs" \
--json - --type "<项目类型>"
禁止 python3 scripts/parse-staffing.py ...（cwd 是项目根，找不到）。
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 208 lines · 173 tokens per session scan B f6631a1ae9d3
ddt-baseline-sync is a skill published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 3mo ago), licensed MIT. It adds 173 tokens to every session and 2,781 once invoked, about $0.0009 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 skills, from other repositories
csv-exporter
Generate properly formatted Teamwork CSV files from Functional Requirements Documents. Converts FRD requirements into CSV backlog with task hierarchy, priorities, story points, and estimated hours. Automatically populates estimated time from story point conversion. Invoke when user asks to "export to CSV", "create…
especialista-em-planilhas
Especialista em Planilhas. Use para Excel/CSV: fórmulas, tabelas dinâmicas, validação, formatação condicional, importação de CSV e modelagem de dados. Palavras-chave: planilha, Excel, xlsx, csv, fórmula, tabela dinâmica, VLOOKUP.
especialista-em-vba
Especialista em VBA. Use para automação Office com macros: módulos, eventos, UserForms, add-ins (.xlam), templates com macro (.xltm) e boas práticas de VBA. Palavras-chave: VBA, macro, Excel, add-in, xlam, xltm, automação Office.
xlsx
This skill should be activated when the user asks to create, edit, read, or analyze Excel spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Triggers for: building financial models, creating data tables, formatting spreadsheets, adding formulas, cleaning tabular data, converting between tabular formats. Also triggers when…
monthly-performance-summary
Generate a clear, client-ready social media performance summary from Planable analytics or a user-uploaded CSV export. Use this skill whenever the user asks for a monthly report, performance recap, analytics summary, results overview, or says things like "summarize last month's performance", "give me a report for…
comps-analysis
Build comparable-company valuation workbooks in Excel.