t-super-run

t-super-run is a skill for Claude Code from timzaak/web-dev-skills. It costs 69 tokens per session (1,963 once invoked), scanned A, original, Apache-2.0.

A way to plan and carry out a software phase—backend, frontend, web demo, or Flutter app—in one persistent work session. It keeps the phase plan, validation, recovery steps, and acceptance checks together.

In plain words
What is it for?
Use it to execute and verify a defined software feature through one of the supported development phases, with the session handling progress, recovery, and acceptance checks.
Why use it?
It reduces the chance of losing the work plan between implementation, testing, fixes, and final review. It requires a completed design document before starting.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the t-tools plugin — 29 skills, 31 agents shipped together

Good fit Use it to execute and verify a defined software feature through one of the supported development phases, with the session handling progress, recovery, and acceptance checks.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add timzaak/web-dev-skills
Claude Code
/plugin install t-tools

Made for: Claude Code.

Or install t-tools, the plugin that ships this one along with the rest of its 29 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-super-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-super-run.svg)](https://agentmods.dev/skills/timzaak/web-dev-skills/t-super-run)
Your own site
<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-super-run"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-super-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,963 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00069 $0.01963
Opus 5 $0.00034 $0.00981
Sonnet 5 $0.00014 $0.00393
Haiku 4.5 $0.00007 $0.00196

Measured today against content hash a5544a21dc91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

t-super-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-super-run/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Super Run

把任务规划与阶段执行合并为一个可恢复闭环。只做 phase -> task 目标级规划,由当前主会话直接完成实现、测试和修复;验收按共享协议派发对应只读 accept subagent,除此之外不调用 subagent。每次调用只执行 --phase 显式指定的一个 phase;该 phase 完成后停止并报告剩余未完成 phase,不自动进入下一个 phase。

运行时边界统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md 设计生成状态统一参考:${CLAUDE_PLUGIN_ROOT}/protocols/design-state-contract.md

需求与决策边界统一参考:

  • ${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md
  • ${CLAUDE_PLUGIN_ROOT}/protocols/decision-continuity-contract.md

计划、状态、角色映射、执行顺序、恢复、验收回退和 Goal 规则统一参考:

  • ${CLAUDE_PLUGIN_ROOT}/protocols/super-run-state-contract.md

参数

参数 说明
[feature] 必填;允许中文、英文、数字、空格、下划线和连字符
--phase <backend|frontend|web-demo|flutter|flutter-demo> 必填;本次调用只执行该 phase,完成后停止

前置条件

  • --phase 缺失或不在支持列表内时终止,提示 --phase <backend|frontend|web-demo|flutter|flutter-demo> 用法。
  • .ai/design/[feature].md 必须存在。
  • 运行 python ${CLAUDE_PLUGIN_ROOT}/scripts/check-design.py ".ai/design/[feature].md" --require-complete --json;失败时停止,不创建或恢复 super-run。
  • 只支持 backend | frontend | web-demo | flutter | flutter-demo;请求的 phase 不在设计与需求来源识别出的真实交付端内时终止,不得为满足命令而编造交付范围。miniapp 使用 /t-task、可选 /t-task-check/t-run
  • 不读取或修改 .ai/task/[feature]/ 作为 super-run 状态。
  • 已有状态且请求的 phase 为 completed | skipped 时,直接报告结果,不重新执行,也不选择其他 phase。

来源加载

在规划或恢复前:

  1. 读取 check-design.py 返回的全部 design_documentsdesign_fingerprint 和现有 .ai/super-run/[feature]/
  2. 按 phase 确认设计输入:backend 读 backend.md;frontend/web-demo 读 frontend.md;flutter/flutter-demo 读 flutter.md;客户端依赖后端契约时同时读 backend.md
  3. 读取相关 .ai/prd/**/*.mddocs/prd/**/*.md.ai/user-stories/**/*.mddocs/user-stories/**/*.md,保留 draft/published 来源边界。
  4. 在任何提问前读取 .ai/decision-log/[feature].md;存在时按需读取 .ai/decision/[feature].md.ai/tech-research/[feature].md
  5. 从设计覆盖矩阵、Operation ID、文件影响表、Decision Trace、代码和配置确定 active phases、task 闭环与真实验证入口。
  6. 按 Decision Exposure Gate 分类缺口;needs_user_answer 未解决时不得进入实现。

不要无差别加载所有 PRD、用户故事或 guide。先通过 feature 名、设计引用和内容检索定位相关文件,再读取全文。

Read the full file on GitHub · 114 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 · +1 lines · +5 tokens per session a5544a21dc91
  2. 3d ago Changed 20d405fce69f
  3. 4d ago Changed · +3 lines · +14 tokens per session 381c60f3e09f
  4. 8d ago First seen · 110 lines · 50 tokens per session scan A 5ee6d0b545cb

Subscribe to this mod's changes

t-super-run is a skill published in the GitHub repository timzaak/web-dev-skills (71 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 1,963 once invoked, about $0.0003 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