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 skills/timzaak/web-dev-skills/t-tasknpx skills add timzaak/web-dev-skills --skill t-taskgit clone --depth 1 https://github.com/timzaak/web-dev-skillsWhat 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 | $0.00017 | $0.03521 |
| Opus 5 | $0.00009 | $0.01760 |
| Sonnet 5 | $0.00003 | $0.00704 |
| Haiku 4.5 | $0.00002 | $0.00352 |
Grade A, and why
t-task scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任务规划生成
运行时边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md
需求来源边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md
决策连续性和用户决策暴露统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/decision-continuity-contract.md
设计生成状态统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/design-state-contract.md
任务拆分必须服务于边界清楚、验证闭环明确的执行;如果设计文档、guide 或 protocol 冲突,停止并说明冲突。
影响规划方向的缺口必须通过 AskUserQuestion 解决,不得把问题写成 P0/P1、假设或 handoff 后继续生成任务。
Input Contract
上游输入(来自 /t-design 产出):
.ai/design/[feature].md— 设计主文档(必须存在)- 必须包含:目标、范围、交付端范围、跨端契约摘要、测试与验收汇总、文件影响范围全量汇总
- 应包含:现有实现分析概览、用户故事/PRD/技术预研引用、Decision Trace
- 纯技术方案设计可只包含技术预研引用,但必须声明不涉及业务逻辑、产品规则、用户可见流程或验收目标变动
.ai/design/[feature]/backend.md、.ai/design/[feature]/frontend.md、.ai/design/[feature]/flutter.md— 分端设计文档;主文档 §4.2 标记适用时必须存在,生成对应 phase 时必须读取(API 契约、数据库设计等分端细节以分端文档为准).ai/design/[feature]/.state.json— 设计生成状态;存在时必须为complete.ai/decision-log/[feature].md— 跨阶段决策账本(存在时必须读取;本阶段不得采用 Superseded Decision)
可选输入:
.ai/task/[feature]/.state.json— 已有任务状态(增量生成时)docs/prd/**/*.md— PRD 文档.ai/user-stories/**/*.md— draft 用户故事docs/user-stories/**/*.md— 已发布用户故事.ai/tech-research/**/*.md— 技术预研报告${CLAUDE_PLUGIN_ROOT}/guides/— 开发规范
Output Contract
下游产出:
.ai/task/[feature]/.state.json— 任务状态文件,包含 phase/slot/item 层级状态.ai/task/[feature]/<phase>/index.md— 阶段总览,包含当前 phase 的 Decision Trace.ai/task/[feature]/<phase>/<slot>.md— Slot manifest(导航与执行顺序).ai/task/[feature]/<phase>/<slot>/<ITEM-ID>-*.md— 可执行的 item 文件
状态结构、item 字段、slot 顺序、测试集中执行和 backend/test 特殊字段统一参考:
${CLAUDE_PLUGIN_ROOT}/protocols/task-state-contract.md${CLAUDE_PLUGIN_ROOT}/protocols/task-phase-execution.md
Purpose
- 从
.ai/design/[feature].md生成.ai/task/[feature]/任务目录和.state.json。 - 固定使用
phase -> slot -> item模型。 - 生成串行执行的 item 文件,而不是把 manifest 当执行输入。
Args
| 参数 | 说明 |
|---|---|
[feature] |
功能名(必填) |
--phase <backend|frontend|miniapp|flutter|web-demo|flutter-demo> |
指定阶段生成;未指定时默认选择第一个 active phase |
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.
- 3d ago First seen · 213 lines · 17 tokens per session scan A 4da6b67bd5c8
t-task is a skill published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 3,521 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。.
mcp-builder
MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具,让 AI 助手连接外部能力.
systematic-debugging
Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.