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-tech-research)<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-tech-research"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-tech-research.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 | $0.00036 | $0.02484 |
| Opus 5 | $0.00018 | $0.01242 |
| Sonnet 5 | $0.00007 | $0.00497 |
| Haiku 4.5 | $0.00004 | $0.00248 |
Grade A, and why
t-tech-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
需求技术预研
运行时边界统一参考：${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md
需求来源边界统一参考：${CLAUDE_PLUGIN_ROOT}/protocols/requirement-source-contract.md
跨阶段决策连续性和用户决策暴露统一参考：${CLAUDE_PLUGIN_ROOT}/protocols/decision-continuity-contract.md
目标
基于 Decision Brief、用户需求、已有 PRD / user story（如存在）和现有代码库，评估技术可行性、依赖缺口、代码影响范围和关键风险，生成报告供 /t-prd 创建或更新草稿，或供纯技术方案 /t-design 参考。
决策纪律（全文只在此声明一次）：会影响技术路线、依赖选择、范围边界、兼容性、成本/风险结论、PRD 建议或后续 /t-design 输入的问题，先按 Topic 查 .ai/decision-log/<file-name>.md；仍未解决时用 AskUserQuestion 提问，回答前不得写入报告、给出收敛结论或把它写成 P0/P1 风险、显式假设、"需要更多信息"后继续。用户回答后先更新 Decision Log，再更新 Tech Research。D2 技术取舍由本阶段明确选择并写入 Tech Research；符合 Entry Gate 时才回写 Decision Log。
输出文件：
.ai/tech-research/<file-name>.md（file-name 取自$ARGUMENTS第一个空格前的部分）.ai/decision-log/<file-name>.md（复用上游决策；仅在产生用户决策、问题状态变化或重要 AI 决策时更新）
如果未传 feature 名称，立即终止并提示：
请提供 feature 名称。例如：/t-tech-research user-management
输入与输出
输入：
.ai/decision/<file-name>.md（可选但推荐，来自/t-decision）.ai/decision-log/<file-name>.md（存在时必须在任何提问前读取）- 用户原始需求描述（参数、当前对话或补问获取）
- 现有代码库
- 可选：
.ai/prd/**/*.md、docs/prd/**/*.md、.ai/user-stories/**/*.md、docs/user-stories/**/*.md、.ai/design/**/*.md
输出报告必须包含：
- 需求理解与技术需求提取
- 现有代码库评估（依赖和可复用模块）
- 差距分析
- 库调研与最佳实践（如适用）
- 影响分析
- 可行性判定
- PRD 创建/更新建议
- 纯技术方案设计建议（如不涉及业务逻辑变动）
- 参考资料
参数规则
$ARGUMENTS可包含两部分：<file-name> [补充描述]；第一个空格前的部分作为输出文件名（如rag-otel-metrics），空格后的部分作为额外需求上下文；只传一个词时同时作为文件名和需求主题- 确保
.ai/tech-research/和.ai/decision-log/存在 - 如果
.ai/tech-research/<file-name>.md已存在，先询问是否覆盖
核心约束
- 先分析现有代码和依赖，再评估缺口；不凭空列举库
- 如果存在
.ai/decision/<file-name>.md，必须承接其中 Verdict、Scope Direction、D0/D1 决策和 Handoff，不得用技术预研改写产品立项结论；Verdict 为Needs Clarification、Park或Reject时，除非用户明确要求技术探索，否则停止并提示先回到/t-decision - 如果存在
.ai/decision-log/<file-name>.md，必须承接相关 Active Decision，不得重复询问 Resolved Question 或采用 Superseded Decision - 如果已存在相关
.ai/prd、.ai/user-stories或 published baseline，必须读取并把它们作为候选产品边界与已发布基线；不得用技术结论静默改写产品语义，需要改变时明确交回/t-prd更新 - 依赖评估必须基于真实
Cargo.toml、package.json和 lock 文件（如存在） - 外部搜索只用于库级事实、最佳实践和兼容性信息，不能替代本地代码分析；Context7 优先，WebSearch 只作补充
- 影响分析中的文件路径必须使用仓库真实路径，但只到文件或模块粒度
- 不产出 API 接口设计、数据库设计或任务拆解；报告聚焦于"能否做""需要什么""影响什么"；技术路线只描述方向、集成方式与依赖选择，不给出具体 schema、接口字段、路由路径、代码结构或配置项命名
- 收敛规则：讨论时可多方案，最终报告必须收敛为单一、明确、可执行的技术路线；不保留方案对比、候选排序或"可选/视情况"等开放式描述，被排除方向只写成确定约束或风险。报告中不得留下"待确认"/"需确认"/"待定"/"TBD"等未决项；显式假设只允许用于不影响技术路线、依赖选择、范围边界、兼容性、成本/风险结论和后续交付判断的非阻塞缺口
What ships with it
1 file 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.
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.
- yesterday Changed · -66 lines f7f3e504b8ef
- 7d ago First seen · 200 lines · 36 tokens per session scan A 5f30c1097b2e
t-tech-research is a skill published in the GitHub repository timzaak/web-dev-skills (71 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 2,484 once invoked, about $0.0002 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
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
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-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.