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/Peiiii/nextclawWrote 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/rules/peiiii/nextclaw/code-citation-clickable)<a href="https://agentmods.dev/rules/peiiii/nextclaw/code-citation-clickable"><img src="https://agentmods.dev/badge/rules/peiiii/nextclaw/code-citation-clickable/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/rules/peiiii/nextclaw/code-citation-clickable"><img src="https://agentmods.dev/badge/rules/peiiii/nextclaw/code-citation-clickable.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 | $0.00993 | $0.00993 |
| Opus 5.5 | $0.00397 | $0.00397 |
| Sonnet 5.5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
code-citation-clickable 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 1mo 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
可点击代码引用
在解释实现、走查链路或回答「代码在哪」时，优先给出带路径与行号的引用，便于在 Cursor 里打开文件并跳到行号；同时需知：并非所有界面都会把代码块变成可点击链接。
为何「很多不能跳转」（预期内限制）
- 渲染通道不同：助手回复里手打的
```start:end:path围栏，在部分会话/预览里只会语法高亮，不保证出现可点击 chip；能否跳转依赖 Cursor 当前面板实现与版本。 - 缩进代码块不算：围栏前若有列表缩进或整段被缩进成「indented code block」，通常不会按
行:行:路径解析，应视为不可跳转。 - 路径必须落在当前工作区：相对路径需相对已打开的仓库根；路径错、文件不在本 workspace、或复制到外部工具查看时，都无法跳转。
- 格式必须干净：起始行只能是
```数字:数字:路径，单独一行；不要- ```...同列一行、不要在反引号与行号之间插空格、不要用 HTML 转义路径。
首选：带行号的代码围栏（助手侧写法）
使用单独一行、无列表前缀、无整段缩进的起始围栏：```起始行:结束行:相对仓库根路径，下一行起为代码，最后一行单独 ``` 结束。
- 路径使用相对仓库根，例如
packages/nextclaw/src/cli/commands/plugins.ts。 - 引用取最小连续区间；无关行用
...占位。 - 反例：正文里只写裸文件名、无路径也无行号。
行内代码引用与模块引用
行内（句子里的文件/符号）反引号往往不可点；在需要「一点就开」时，应用 Markdown 链接，路径仍相对仓库根：
- 文件：
[plugin.controller.ts](packages/nextclaw-server/src/ui/router/marketplace/plugin.controller.ts)；若需精确定位，在链接后加纯文本行号，如「见上文 L127–178」或单独再给一行号围栏。 - 目录：链到该目录下的
README.md或代表性入口文件，避免链到裸目录（部分渲染器不支持）。 - Workspace 包 / 模块名（如
@nextclaw/server）：链到本次讨论最相关的一个源码文件（例如正在改的*.ts）；若无单一文件，再退到该包package.json或包内README.md（仅当文件存在时再写链接，避免死链）。 - 外部 npm 包（非本仓库）：用
https://链到 registry、文档或源码仓库；不要随意写成指向本仓库的假路径。
行内链接与行号围栏互补：链接负责「打开对的文件」，围栏负责「锁定行区间」。
用户侧最稳打开方式
- 用 Quick Open（
Cmd+P/Ctrl+P）粘贴路径，打开后再Cmd+G跳行号。 - 在 Chat 里用
@引用文件 让 Cursor 绑定工作区文件，再结合助手给出的行号跳转。
次选补充
- 同一文件多段逻辑：拆成多个上述代码块，或第一段给全路径+行号，后续在同文件可用「同上文件」+ 行号范围；行内再次提到该文件时用 Markdown 链接缩短阅读路径。
避免
- 大段粘贴无路径无行号的裸代码。
- 用 HTML 实体代替
<、&等（围栏内保持字面量）。
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.
- 1mo ago First seen · 49 lines · 993 tokens per session scan A 0f4427980df4
code-citation-clickable is a cursor rule published in the GitHub repository Peiiii/nextclaw (262 stars, last pushed today), licensed MIT. It adds 993 tokens to every session, about $0.0040 per session on Opus 5.5. 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
shared-plane-packages
Pattern for creating shared plane packages that serve both migration and runtime planes.