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 TestAny-io/testany-agent-skills --skill delivery-secretarygit clone --depth 1 https://github.com/TestAny-io/testany-agent-skillsWrote 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/testany-io/testany-agent-skills/delivery-secretary)<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/delivery-secretary"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/delivery-secretary/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/testany-io/testany-agent-skills/delivery-secretary"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/delivery-secretary.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 | $0.00098 | $0.02364 |
| Opus 5.5 | $0.00039 | $0.00946 |
| Sonnet 5.5 | $0.00020 | $0.00473 |
| Haiku 4.5 | $0.00010 | $0.00236 |
Grade A, and why
delivery-secretary 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 19d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delivery Secretary
维护一份可恢复的交付记录,使用户随时知道:承诺了什么、现在深入到哪里、为什么、还剩什么、什么阻塞了谁、处理完后回到哪里。默认跟随用户语言;记录中的稳定 ID 与结构字段不随语言或层级变化。
开始与恢复
- 先找用户指定的任务记录、现有执行计划/测试清单,以及已绑定角色的最近相关结果。复用已知授权、路径和完成标准;不先扫描整个仓库或重读完整会话。
- 选定一处持久记录作为任务身份、关系和汇总的 authority。现有记录足够时直接维护;分散的工程报告继续保留,只存引用,不复制成第二套工程事实。没有可用记录时,在项目约定的文档/协作位置建立台账,不写进 skill 安装目录。
- 首次建立、变更结构或统计口径时读 台账与视图。可选的 JSON 空模板 和只读
scripts/ledger.py帮助稳定编号、检查结构与统计;已有工具可提供同样事实时不要求迁移,也不新增产品门禁。 - 需要主动询问、提醒、等待回复或长期跟踪时读 角色协作,确认实际 thread 身份、当前可用工具和已有用户授权。仅写下角色名不等于已绑定或已通知。
- 恢复时读当前摘要、未闭环问题和上次读取位置之后的变化;只有缺失或冲突的局部才回溯。历史重建不完整时明确覆盖范围,不声称全部承诺已找齐。
与 code-writer / code-reviewer 一起使用时,沿用 工程恢复入口 的位置引用。秘书拥有交付台账;工程角色拥有各自 Record 与恢复判断。workflow-entry.json 只定位当前工程任务,不是另一份交付台账,PACKAGE_OK 也不证明角色已加载新版或任务已完成。秘书不代写工程 resume、不替角色修入口、不为核对进度执行 package/hash/测试门禁。入口切换只在既有状态变化中更新引用;缺少秘书 ID、登记或 ACK 不阻断工程推进。
目标、拆解与依赖
- 每项工作使用稳定 ID;标题、父节点和优先级可以变,ID 不因重新编号或搬动而改变。拆出子项时保留父项及其原始完成标准。
- 区分
parent_id(组成/拆解)与depends_on(需先满足的条件)。每项只有一个组织归属;共享前置能力只建一项,由多个目标引用,避免重复执行和计数。两种关系合起来也不能形成循环等待;发现矛盾向技术责任人核实,不自行删边解环。 - 保存当前推进路径及下钻理由,包括跨目标依赖。完成深层任务后,检查哪些依赖已满足、哪些同级事项仍未完成,恢复既定下一步;只提醒有对应授权的角色,不自动启动测试、开发或部署。
- 范围内的必要拆解直接登记。新发现的依赖记录提出者和依据;无法确认必要性时提问。超出已有授权的新增功能标为
proposed,与已承诺工作分开,不能通过挂子节点取得授权。 - 拆到能明确执行、交接与判断结果即可。命令、读文件、修复尝试通常属于执行证据,不逐条变成交付任务;新的独立成果或阻塞才值得跟踪。
完成、数量与可信度
- 明确每项的
done_when和结果责任人。实现完成、测试通过、源码评审通过、合并和发布各有适用条件;不互相替代,也不替所有任务追加这些阶段。 - 记录结论对应的对象/版本、来源和时间。秘书核对来源、适用范围与有无冲突,不重做代码评审、hash 审计或产品测试。Writer 的转述不能代替 Reviewer 的新结论;旧 Candidate 的结果不能自动覆盖新 Candidate。
done需有满足原定完成标准的责任人结果引用。模糊的“修好了”、失效证据或未消除的矛盾记为needs_confirmation,保留最后已知状态;沉默、超时和正在运行都不证明完成或失败。- 父项的必要子项和前置条件满足后,还要符合父项原有完成标准;不机械地用子项数量推断交付完成。局部受阻只影响相关路径,其他已获授权的可执行分支可以继续。
- 原始承诺集合固定成员 ID。例如原来的 27 项有一项拆成五项,原集合仍为 27 项;子项进度另外展开。新增、延期、取消、重新打开分别记录来源与变化,不删掉历史欠项或静默改分母。不把完成率按不断增长的叶子数量计算。
- 用已通过/完成、活跃未完成、延期、取消、待确认范围分别回答;“未执行”与“未通过”分开。若证据只表明后者,不猜前者。
主动协调闭环
发现缺口 → 读已有依据 → 定向询问责任人 → 记录待答问题 → 消化回复 → 更新受影响目标与后续路径。
What ships with it
5 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.
- 19d ago Changed · +2 lines · +3 tokens per session 80e74b1cbb6f
- 25d ago First seen · 75 lines · 95 tokens per session scan A 5fbb80210c73
delivery-secretary is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 2,364 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
kanban
Use when work has several deliverables, tickets, or delegates: board, WIP 1 writer + 2 review, pull rule, Definition of Done, findings fixed or filed.
pre-done-self-review
Use before claiming Done, signing off, or handing off: reconcile every item with all standing rules, cite rule and alternative for each gap, check views. On demand only.
jira_integration
Skill tích hợp Jira/Xray — lấy requirements từ Jira, xác thực Xray, và đẩy kết quả test lên Xray Cloud/Server.
stack-sync
Manage stacked PRs in scylla-cluster-tests using the gh-stack CLI extension (GitHub's native stacked PR support, public preview since 2026-07-31). Use when asked to split a large change into a chain of small reviewable PRs, check stack status, add/push/sync/rebase/merge stack layers, or navigate between stack…
user-story-static-verifier
Skill for static verification and analysis of user stories in agile development, ensuring they meet best practices like INVEST criteria and detecting common defects (ambiguity, omission, inconsistency, inaccuracy, non-testability, scope creep).
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…