t-decision

t-decision is a skill for Claude Code from timzaak/web-dev-skills. It costs 22 tokens per session (2,781 once invoked), scanned A, original, Apache-2.0.

A product decision step that evaluates whether a feature should continue into technical research or a product requirements document. It focuses on user need, evidence, value, and scope.

In plain words
What is it for?
Deciding whether a proposed feature enters the t-tools workflow and recording the decision and any later changes.
Why use it?
It helps teams avoid spending engineering time on features without a clear problem, user, or reason to proceed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: 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 — 28 skills, 31 agents shipped together

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 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-decision

README.md
[![agentmods](https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-decision.svg)](https://agentmods.dev/skills/timzaak/web-dev-skills/t-decision)
Your own site
<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-decision"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-decision.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,781 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 $0.00022 $0.02781
Opus 5 $0.00011 $0.01391
Sonnet 5 $0.00004 $0.00556
Haiku 4.5 $0.00002 $0.00278

Measured yesterday against content hash d0e965c20287, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

t-decision 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 yesterday.

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-decision/SKILL.md · 213 lines

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.

产品立项决策

契约:${CLAUDE_PLUGIN_ROOT}/protocols/decision-brief-contract.md 跨阶段决策连续性:${CLAUDE_PLUGIN_ROOT}/protocols/decision-continuity-contract.md

/t-decision 位于 /t-tech-research/t-prd 之前,用来判断一个 feature 是否值得进入后续工程流程。它只做产品立项和范围取舍,不写 PRD、不做技术设计、不拆任务、不实现代码。

输出

  • .ai/decision/<feature>.md
  • .ai/decision-log/<feature>.md

Markdown 使用 template.md

参数

  • $ARGUMENTS 必须是 feature 名称
  • 允许中文、英文、数字、空格、下划线、连字符

缺失或非法时终止并提示:/t-decision <feature>

如果 .ai/decision/<feature>.md 已存在,先询问覆盖、更新或终止。

更新已有 Product Decision 时不得复用原 DEC ID 改写历史结论;创建新 DEC、设置 Supersedes,并把旧记录移入 Decision Log 的 Superseded Decisions。

读取上下文

按需读取,缺失则跳过:

  • docs/prd/00-index.md
  • docs/user-stories/00-index.md
  • .ai/user-stories/**/*.md
  • .ai/decision/**/*.md
  • .ai/decision-log/**/*.md
  • .ai/prd/**/*.md
  • docs/prd/**/*.md
  • .ai/tech-research/<feature>.md
  • .ai/design/<feature>.md

可少量搜索代码,用于判断已有能力、替代方案和复用事实;不得展开技术方案。

决策规则

  • 先判断问题,再判断方案。
  • 证据优先:真实行为、付费、业务阻塞、明确成本强于“感兴趣”。
  • 具体性优先:目标用户必须是角色 + 场景 + 后果,不能停在“用户/企业/管理员”。
  • 默认做减法:先找最小可验证价值,再考虑扩展。
  • 高影响、不可逆或会改变承诺的取舍必须问用户。
  • scope 变化必须显式记录,不能静默扩大或缩小。

交互姿态

这一阶段的价值是辅导人类做判断,不是快速生成文档。要帮助用户把模糊想法压成可决策的问题。

保持直接、具体、可验证:

  • 主动重构问题(reframe):锁定 problem statement 前,至少主动提出一个替代问题定义让用户确认或否决,而不是只在心里做代理问题检查。

  • 对每个关键回答都形成判断:支持继续、削弱继续、还是需要更多证据。

  • 不迎合模糊表达。用户说“体验更好”“更智能”“更完整”时,追问到具体场景、指标、行为或后果。

  • 不把“有人觉得有用”当需求证据。行为、付费、业务阻塞、替代方案成本更重要。

  • 不急着推进到 PRD。PRD 是承接已确认方向的产物,不是替用户做方向判断的地方。

  • 可以推荐,但最终 scope 由用户决定。任何扩 scope、砍 scope、暂缓或拒绝都必须显式记录。

避免这些表达:

  • “这听起来不错”但不判断证据。
  • “可以有很多方向”但不给推荐。
  • “建议考虑”但不说明取舍。
  • “后面 PRD 再细化”来逃避当前必须确认的 D0 决策。

六问诘问(必跑)

这是 /t-decision 的诘问主线,但只保留门禁。写 Verdict 前六问必须逐项有结论(或显式写跳过理由);上下文已能回答的直接引用,不重复问;一次只问一个,只问会影响 Verdict、Scope 或成功标准的问题。

  1. 谁在痛、痛到什么程度 — 定位到角色 + 场景 + 可观察后果。强制量化:发生频率、占用时长、涉及人数、花费金钱或业务阻塞强度。给不出数字,证据强度记 Weak,并把该项写入“待量化”。
  2. 这是问题,还是方案 — 把“我要做 X”翻译成“谁在 Y 场景下受困于 Z”。**至少提出一个替代问题定义(reframe)**让用户确认或否决;用户描述若只是方案包装,必须改写成问题。
  3. 用户现在怎么绕 — 现有替代方案是什么,摩擦成本有多大(时间/钱/风险/人工协调)。绕法已经很顺 → 削弱继续;绕法很痛 → 最强需求证据。
  4. 最小楔子是什么 — 区分 MVP(太大)和 wedge(最薄能产生真实学习的切片)。能否在一两天内交付一条窄路径并拿到真实反馈。
  5. 哪个假设错了会致命 — 列出 1-3 个核心假设,标出致命的那个。最小成本如何证伪。Kill criteria:什么结果会让你直接放弃。
  6. 有没有更大、更易讲、更高杠杆的版本 — 当前想法是不是某个更大问题的代理。是否存在一个 10x 版本反而更简单、更值得,或反过来证明当前范围太散。

Read the full file on GitHub · 213 lines

Files

What ships with it

2 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.

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. yesterday Changed · -52 lines d0e965c20287
  2. 6d ago First seen · 265 lines · 22 tokens per session scan A 9c36cbc708a2

Subscribe to this mod's changes

t-decision is a skill published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 2,781 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.