full-node-audit

full-node-audit is a cursor rule for Cursor from TashanGKD/tashan-cursor-skills. It costs 73 tokens per session (2,600 once invoked), scanned A, original, MIT.

A rule requiring a critical review before the agent delivers newly produced content, designs, code, or other project output. The review checks the result from the user’s viewpoint, tests possible counterexamples, and looks for omissions.

In plain words
What is it for?
Auditing articles, product designs, technical plans, code, skills, decisions, and other newly created outputs before delivery.
Why use it?
It helps catch unclear explanations, overlooked edge cases, and missing information before the output is shared or saved.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Install

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.

agentmods
npx agentmods add rules/tashangkd/tashan-cursor-skills/full-node-audit
Clone the repo
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skills

Made for: Cursor.

Wrote 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.

agentmods badge for full-node-audit

README.md
[![agentmods](https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/full-node-audit.svg)](https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/full-node-audit)
Your own site
<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/full-node-audit"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/full-node-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,600 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.02600
Opus 5 $0.00036 $0.01300
Sonnet 5 $0.00015 $0.00520
Haiku 4.5 $0.00007 $0.00260

Measured 6d ago against content hash 12e8a4c3c268, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

full-node-audit 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

rules/full-node-audit.mdc · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

全节点审核规则(full-node-audit)

认知根:F-022(全节点审核机制原则)/ L1.5候选 P10? 关系类型:extends(是 P1「验证优先于感受」在系统架构层的强制实施版本) 与其他 Rule 的关系:auto-experience-hook 关注「执行后沉淀」;本 Rule 关注「输出前审核」


核心原则

任何生产节点,在最终输出给用户或写入文件之前,必须内置至少一次挑战者反思。

创作者(无论是 AI 还是人)在单一视角下有系统性盲区——自以为正确的设计,对使用者/读者/系统可能有明显问题。挑战者视角是发现这类盲区的最低成本机制。


适用范围:什么是「生产节点」

以下类型的输出步骤属于生产节点,适用本 Rule:

生产节点类型 示例
内容生产 生成文章草稿、段落、标题
产品设计 输出产品定义、功能设计、用户流
技术设计 输出技术架构、API规范、数据模型
代码生产 完成一个功能模块、接口、组件
Skill/Rule 设计 完成 Skill 初稿、Rule 内容
认知更新 向认知结构写入新内容(碎片/原则/整合)
决策输出 给出方案建议、做出选择

不适用(不需要挑战者反思的步骤):

  • 纯读取/信息整理步骤(没有新输出)
  • 已经是审核者角色的步骤本身(如关卡A/B/C)
  • 日志记录、索引更新等机械性写入

最低挑战者反思要求

每个生产节点完成后,在输出/提交前,执行以下最低程度的挑战者反思:

挑战者检查(最多3条,针对当前输出最可能的盲区):

1. 使用者/读者视角:这个输出对最终使用它的人来说,有什么不清楚或有误导的地方?

2. 反例视角:有没有一个具体情况,这个输出会失效或造成问题?

3. 遗漏视角:这里省略了什么本应包含但被我无意识跳过的内容?

要求

  • 3 条检查都需要给出具体答案(不能全部回答"无")
  • 如果发现问题 → 修改后再输出
  • 如果3条均无重大问题 → 可以输出,但必须有至少1条"尚可接受的小问题"(如果全部"完美"则说明挑战视角不够认真)

各节点类型的挑战者视角重点

不同类型的生产节点,挑战的重点不同:

节点类型 挑战重点1 挑战重点2 挑战重点3
内容生产 读者第一次读到这里会理解错什么? 是否有「AI腔」或空话? 标题/结论是否能独立成立?
产品设计 挑剔用户会在哪一步卡住或放弃? 有没有假设用户知道某个前提? 边界情况(用户做了意外操作)怎么处理?
技术设计 这个架构在最高负载/极端输入时会在哪里崩溃? 有没有单点故障? 6个月后新开发者能从文档独立理解吗?
代码生产 这个函数在输入为null/空/超大时会怎样? 有没有隐藏的副作用? 有没有已有代码可以复用而未复用?
Skill/Rule设计 AI执行者读完会有哪3个歧义点? 这个规则和已有规则有没有冲突? 触发条件是否过宽(会误触)或过窄(会漏触)?
认知更新 这个内容和已有认知结构的哪里可能矛盾? 置信度标注是否诚实(是推断还是确认)? 有没有应该同步更新但没有更新的关联文档?

与各关卡的关系

本 Rule 的挑战者反思是节点内的小闭环,不替代以下大闭环审核机制:

审核机制 层级 关系
本 Rule(挑战者反思) 节点内,自我审核 生产者自己从挑战者视角快速检查
关卡A(用户模拟) 产品定义→代码之间 独立审核者,全面模拟用户路径
关卡B(系统破坏) 架构→代码之间 独立审核者,从破坏者视角找漏洞
关卡C(测试工程师) 代码写完→上线之前 独立审核者,按验收标准全面测试

层级关系:本 Rule(节点内 ⊂ 小闭环)→ 关卡A/B/C(大闭环)→ 元验证(全系统闭环)


与全量搜索原则的关系(F-021)

F-021 要求全量搜索,F-022 要求全节点审核——两者共同构成大闭环:

产品设计阶段:
  生产节点(产品定义输出)
    → [本 Rule] 挑战者反思(节点内)
    → 关卡A(全路径用户模拟 × 全量搜索)← F-021 在这里作用

技术架构阶段:
  生产节点(架构输出)
    → [本 Rule] 挑战者反思(节点内)
    → 关卡B(全覆盖破坏性测试 × 全分支)← F-021 在这里作用
    
代码阶段:
  生产节点(每个功能模块输出)
    → [本 Rule] 挑战者反思(节点内)
    → 关卡C(全覆盖功能验证 × 全路径)← F-021 在这里作用

Read the full file on GitHub · 172 lines

Changes

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.

  1. 6d ago First seen · 172 lines · 73 tokens per session scan A 12e8a4c3c268

Subscribe to this mod's changes

full-node-audit is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 73 tokens to every session and 2,600 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.