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.
git clone --depth 1 https://github.com/maysunAI/T00-zhWrote 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/commands/maysunai/t00-zh/t00-perf-check)<a href="https://agentmods.dev/commands/maysunai/t00-zh/t00-perf-check"><img src="https://agentmods.dev/badge/commands/maysunai/t00-zh/t00-perf-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/maysunai/t00-zh/t00-perf-check"><img src="https://agentmods.dev/badge/commands/maysunai/t00-zh/t00-perf-check.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.00667 |
| Opus 5 | $0.00015 | $0.00333 |
| Sonnet 5 | $0.00006 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
t00-perf-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 12d 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
用户说「/t00-perf-check」时，执行以下检查并输出报告：
Step 0：Context 用量估算
基于已加载内容估算 token 使用量：
- 计算公式：
行数 × 15 tokens/行（中英混合平均值） - Claude Sonnet 有效工作区间：≤ 150k tokens（总 200k，留 50k 给对话）
- 自动加载内容目标：≤ 5k tokens（约 333 行）
输出：
📊 Context 估算
自动加载：约 XXX tokens（占总量 X%）
状态：✅ 正常 / ⚠️ 偏多（> 5k tokens）/ 🔴 过多（> 10k tokens）
Step 1：统计自动加载量
读取以下文件，统计 @include 数量和对应文件行数：
F:\T00\CLAUDE.mdF:\T00\AI00_Common\CLAUDE.md
对每个 @include 文件，读取并统计行数。汇总「自动加载总行数」。
Step 2：列出所有 Skills
扫描 F:\T00\AI00_Common\.claude\commands\ 下的所有 .md 文件，列出：
- 文件名（= 命令名）
- frontmatter 里的 description
Step 3：列出所有 Hooks
读取 F:\T00\.claude\settings.local.json，列出所有配置的 hooks（类型 + 触发条件）。
若无 hooks，注明「⚠️ 未配置任何 hook」。
Step 4：输出报告
格式：
=== Claude 效率配置报告 ===
📦 自动加载（每次会话）
@include 数量：X 个
总行数：约 XXX 行
明细：
- [文件名]：XX 行
- ...
⚡ Skills（按需加载，共 X 个）
/命令名 — 描述
...
🪝 Hooks（自动执行，共 X 个）
PostToolUse / Write → [描述]
...（若无：⚠️ 未配置）
💡 优化建议
- [如有问题列出，如「XX 文件 XX 行可移至 skill」]
- [若无问题：「✅ 配置正常」]
判断逻辑（优化建议）
- 自动加载 > 333 行（5k tokens）→ 提示「建议精简 @include 或拆到 skill」
- 自动加载 > 667 行（10k tokens）→ 🔴 「严重过多，影响工作效率」
- hooks 为 0 → 提示「建议添加备份检查和HTML更新 hook」
- 发现重复内容（某 @include 与某 skill 内容重叠）→ 指出
- rules/ 目录有文件 → 列出路径作用域规则
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.
- 12d ago First seen · 74 lines · 29 tokens per session scan A 06e76bfb072f
t00-perf-check is a command published in the GitHub repository maysunAI/T00-zh (2 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 667 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 2026-08-31.
Other commands, from other repositories
aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
cpp-test
Enforce TDD workflow for C++. Write GoogleTest tests first, then implement. Verify coverage with gcov/lcov.
flutter-build
Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.
cost-report
Generate a local Claude Code cost report from the ECC cost-tracker metrics log.
cpp-review
Comprehensive C++ code review for memory safety, modern C++ idioms, concurrency, and security. Invokes the cpp-reviewer agent.
e2e
Generate and run E2E tests with Playwright.