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.
npx agentmods add skills/timzaak/web-dev-skills/t-simplifynpx skills add timzaak/web-dev-skills --skill t-simplifygit clone --depth 1 https://github.com/timzaak/web-dev-skillsWrote 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-simplify)<a href="https://agentmods.dev/skills/timzaak/web-dev-skills/t-simplify"><img src="https://agentmods.dev/badge/skills/timzaak/web-dev-skills/t-simplify.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 | $0.00076 | $0.01915 |
| Opus 5 | $0.00038 | $0.00958 |
| Sonnet 5 | $0.00015 | $0.00383 |
| Haiku 4.5 | $0.00008 | $0.00192 |
Grade A, and why
t-simplify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
变更代码清理
t-simplify → 4 个清理审查 agent 并行 → 直接应用修复
运行时边界统一参考：${CLAUDE_PLUGIN_ROOT}/protocols/runtime-boundaries.md
来源说明
本 skill 复刻自 Claude Code 内置 /simplify 命令的提示词。主流程（4 个角度并行只读审查 → 去重后直接修复）与 inline 降级来自 Piebald-AI/claude-code-system-prompts（MIT）对 v2.1.154 slash command 与 v2.1.213 inline 模式的二进制提取；当时四个角度指引还是运行时注入变量、未随提取发布，本插件最初按公开行为还原。后续 v2.1.232 已把角度指引内嵌进二进制，本插件按本机 @anthropic-ai/[email protected] 二进制内嵌字符串逐字校准了四个角度、Phase 0 变更收集（上游区间 + 未提交变更）和 <target> 参数语义，校准结果落在 ${CLAUDE_PLUGIN_ROOT}/protocols/simplify-cleanup-contract.md；并按本插件约定补充分 agent 角色规范、结构化契约和 .ai/quality/ 报告。
目标
- 提升本次变更代码的质量，不是找 bug：从复用、简化、效率、抽象层级四个角度审查并直接修复。
- 不找正确性缺陷——那是
/code-review与各阶段 accept 的职责。 - 修复保持行为不变：改变预期行为的修法一律跳过。
使用方式
/t-tools:t-simplify [<target>]
| 参数 | 说明 |
|---|---|
[<target>] |
可选审查目标（PR 号 / 分支名 / 文件路径）；传入时直接替换默认审查范围，提示词以 Review target: \`` 前缀注入 |
推荐位置：/t-run（或 /t-super-run）完成实现与测试后、/t-push 提交前。
共享契约
审查角度定义、finding 结构、去重/跳过/修复边界和报告结构统一参考：${CLAUDE_PLUGIN_ROOT}/protocols/simplify-cleanup-contract.md
变更收集
按原文 Phase 0 语义收集审查范围：
- 优先
git diff @{upstream}...HEAD；无 upstream 时依次回退git diff main...HEAD、git diff HEAD~1。 - 存在未提交变更、或区间 diff 为空时，追加
git diff HEAD把工作区变更纳入范围（审查常发生在提交前）；untracked 源码文件一并纳入（插件补充）。 - 用户传入
<target>（PR 号 / 分支名 / 文件路径）时，以该目标为审查范围，替换上述默认收集。 - 非 git 仓库或尚无提交：取最近修改的源码文件（排除
.ai/、docs/、构建产物、依赖目录等非源码路径；插件补充）。 - 审查范围为空时返回
NO_CHANGES，不做任何修改。
执行流程
Phase 1 — 审查（4 个清理 agent 并行）
- 按
${CLAUDE_PLUGIN_ROOT}/protocols/subagent-dispatch.md，先 Read${CLAUDE_PLUGIN_ROOT}/agents/simplify-reviewer.md全文（同批次复用，见该协议的 token 优化规则）。 - 通过
Agenttool 在同一条消息里启动 4 个simplify-reviewersub agent，使其并行执行。每个 prompt 包含：- agent 角色规范全文（作为首段角色指令段）
- 一个角度的完整指引（从
${CLAUDE_PLUGIN_ROOT}/protocols/simplify-cleanup-contract.md摘取：Reuse / Simplification / Efficiency / Altitude 各一个，不重复、不遗漏） - 变更文件清单和获取完整 diff 的命令
- 每个 reviewer 返回 findings：
file、line、单行summary、具体cost（什么被重复、浪费或更难维护）。
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.
- 4d ago First seen · 113 lines · 76 tokens per session scan A 7f017f063957
t-simplify is a skill published in the GitHub repository timzaak/web-dev-skills (69 stars, last pushed yesterday), licensed Apache-2.0. It adds 76 tokens to every session and 1,915 once invoked, about $0.0004 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
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。.
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。.
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。.
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。.
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.
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.