t-run

t-run is a skill for Claude Code, Codex from timzaak/web-dev-skills. It costs 24 tokens per session (1,548 once invoked), scanned A, original, Apache-2.0.

A task runner that executes a planned software project in separate phases, such as backend, frontend, mobile app, or demo work. It reads task state and runs one work item at a time in the planned order.

In plain words
What is it for?
Use it to run prepared task plans whose files define phases, slots, work items, and success criteria, while updating the project’s state file and producing code changes.
Why use it?
It keeps phased work organized and records which items succeeded or failed, so execution can continue from the stored project state.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the t-tools plugin — 28 skills, 31 agents shipped together

Install

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.

agentmods
npx agentmods add skills/timzaak/web-dev-skills/t-run
Any agent
npx skills add timzaak/web-dev-skills --skill t-run
Clone the repo
git clone --depth 1 https://github.com/timzaak/web-dev-skills

Made for: Claude Code, Codex.

Or install t-tools, the plugin that ships this one along with the rest of its 28 skills, 31 agents.

Wrote 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.

agentmods badge for t-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-run.svg)](https://agentmods.dev/skills/timzaak/web-dev-skills/t-run)
Your own site
<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-run"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,548 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.01548
Opus 5 $0.00012 $0.00774
Sonnet 5 $0.00005 $0.00310
Haiku 4.5 $0.00002 $0.00155

Measured today against content hash 5a48556ec10e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

t-run 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 today.

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.

skills/t-run/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

任务执行

运行时边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md

执行时以当前 item 的成功标准和最小必要验证为目标;遇到冲突、缺失上下文或无法判断的语义问题时停止并说明。

前置条件

  • .ai/task/[feature]/.state.json 必须存在且可解析;目标阶段必须是 supported phase 且存在于当前任务 active phases(未启用 miniapp/Flutter 的项目不得执行对应 phase),并已规划(phases[phase]tasks[phase] 和对应阶段目录存在)。
  • 当前阶段目录必须包含:index.md、对应 slot manifest(backend/frontend/miniapp/flutter 为 dev.md, test.md, accept.md;web-demo/flutter-demo 为 dev.md, accept.md)、对应 item 目录和 item 文件。

共享契约

执行单元、slot 顺序、item 选择(含启动归一化)、agent 最小上下文、backend/test 特殊规则和失败处理统一参考:

  • ${CLAUDE_PLUGIN_ROOT}/protocols/task-phase-execution.md
  • ${CLAUDE_PLUGIN_ROOT}/protocols/task-state-contract.md
  • ${CLAUDE_PLUGIN_ROOT}/protocols/backend-test-execution.md

参数

参数 说明
[feature] 功能名
--phase <backend|frontend|miniapp|flutter|web-demo|flutter-demo> 仅执行指定阶段;未指定时执行 .state.json 的当前阶段

Input Contract

上游输入(来自 /t-task 产出):

  • .ai/task/[feature]/.state.json — 任务状态文件(必须存在且可解析)
  • .ai/task/[feature]/<phase>/index.md — 阶段总览
  • .ai/task/[feature]/<phase>/<slot>.md — Slot manifest(slot 内 item 执行顺序的真源)
  • .ai/task/[feature]/<phase>/<slot>/<ITEM-ID>-*.md — Item 文件(Goal / Work / Files / Validation / Handoff 五章节,即执行依据)

index.md 和 slot manifest 不作为直接执行单元。backend 的 OpenAPI 导出与前端 API 生成验收由 backend-accept 负责。

执行循环

  1. 读取状态并确定执行范围,按共享契约校验状态与执行顺序。

  2. 完成校验后、启动任何 agent 前,将目标 phase 中全部 generated item 归一化为 pending,重新聚合对应 slot/phase 并一次性写回 .state.json(保留其他状态不变);归一化写回失败时按状态写入失败处理,不得启动 agent。

  3. 按共享契约选择第一个 pendingfailed item,通过 Agent tool 启动 subagent_type 为 item agent 字段值的 sub agent(调度规则见 ${CLAUDE_PLUGIN_ROOT}/protocols/subagent-dispatch.md,最小上下文按 task-phase-execution 的 Agent Context)。

    最小上下文示例:

    # 调用 backend-dev item 时的最小上下文
    feature: sample-feature
    phase: backend
    slot: dev
    item_id: BE-D02
    agent: backend-dev
    agent_spec: ${CLAUDE_PLUGIN_ROOT}/agents/backend-dev.md
    item_file: .ai/task/sample-feature/backend/dev/BE-D02-domain-models.md
    slot_manifest: .ai/task/sample-feature/backend/dev.md
    phase_index: .ai/task/sample-feature/backend/index.md
    previous_items:
      BE-D01: completed, file=.ai/task/sample-feature/backend/dev/BE-D01-domain-models.md, handoff=<必要片段>
    

Read the full file on GitHub · 106 lines

Changes

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.

  1. today Changed · -42 lines 5a48556ec10e
  2. 5d ago First seen · 148 lines · 24 tokens per session scan A 9f776de649e0

Subscribe to this mod's changes

t-run is a skill published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 1,548 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.

Related

Other skills, from other repositories

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。.

jnMetaCode/superpowers-zh · 69 tokens

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。.

jnMetaCode/superpowers-zh · 65 tokens

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。.

jnMetaCode/superpowers-zh · 62 tokens

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。.

jnMetaCode/superpowers-zh · 62 tokens

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.

jnMetaCode/superpowers-zh · 24 tokens

dispatching-parallel-agents

当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.

jnMetaCode/superpowers-zh · 30 tokens