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.
/plugin marketplace add timzaak/web-dev-skills/plugin install t-toolsWrote 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/timzaak/web-dev-skills/t-prd-check)<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-prd-check"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-prd-check.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00825 |
| Opus 5 | $0.00012 | $0.00413 |
| Sonnet 5 | $0.00005 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
t-prd-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
PRD 草稿与 User Story Quality Check
运行时边界：${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md（判断产物写入位置或脚本入口与插件默认冲突时读）
需求来源边界：${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md（区分草稿与已发布需求来源或处理两者冲突时读）
决策连续性和用户决策暴露：${CLAUDE_PLUGIN_ROOT}/protocols/decision-continuity-contract.md（提问、更新决策账本或处理决策暴露门禁时读）
评估目标、评分维度、问题分级与报告结构：${CLAUDE_PLUGIN_ROOT}/protocols/prd-check-rubric.md（评分或分级前读）
本检查为可选质量检查：未运行或未通过不阻断 /t-design，但报告必须明确继续下游的已知风险。
输入范围
- PRD 草稿：
.ai/prd/**/*.md - 决策账本：
.ai/decision-log/<feature>.md（存在时必须读取） - 已发布 PRD 基线：
docs/prd/**/*.md - Draft 用户故事：
.ai/user-stories/**/*.md - 已发布用户故事：
docs/user-stories/**/*.md
执行流程
1. 确定检查范围
- 单功能优先按文件名匹配
.ai/prd/**/*.md草稿；无草稿则检查docs/prd/**/*.md正式 PRD（发布后质量检查）；都不存在时提示检查功能名称或先运行/t-prd [feature] --all默认检查全部草稿；无草稿时再检查全部正式 PRD- 用
Glob发现目标文件并排除特殊文件
2. 读取角色定义
读取 docs/user-stories/_roles.md，解析角色名称和技术标识，用于校验故事中的角色引用。
3. 评分与问题分级
全部按 ${CLAUDE_PLUGIN_ROOT}/protocols/prd-check-rubric.md 执行：
- 先过 Decision Closure Gate：运行
check-decision-closure.py，needs_user_answer未解决时用AskUserQuestion阻塞提问；用户回答写入 Decision Log 后，先由/t-prd [feature]更新 PRD，重新扫描通过后再继续检查 - 按 PRD Score / User Story Score 维度表逐项检查，并执行一致性门禁
- 对
.ai/user-stories与docs/user-stories分别标注 draft / published 来源 - draft 与已发布基线的差异分类：补充新场景且不冲突记为 publish 候选；修改已发布语义必须识别差异性质；严重度按 rubric 的 P0/P1 定义
4. 输出
- 控制台摘要与详细报告结构按 rubric 的 Output Requirements；报告写入
.ai/quality/prd-check-[YYYYMMDD-HHMMSS].md - 通过时建议下一步
/t-design [feature]；未通过或修复后建议重新运行/t-prd-check [feature]
失败处理
- 文件解析错误：记录错误并继续其他文件
- 报告目录不存在：使用
Bash创建.ai/quality/
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 Changed · -49 lines 9aef4126a3aa
- 8d ago First seen · 110 lines · 23 tokens per session scan A 87c8be589e44
t-prd-check is a skill published in the GitHub repository timzaak/web-dev-skills (71 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 825 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-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
workflow-runner
A procedure for running agency-orchestrator YAML workflows directly inside Claude Code, OpenClaw, or Cursor. The current AI session performs each named role, so no separate API key is needed.
build-executor
Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.