skill-closure-verifier-meta

skill-closure-verifier-meta is a skill for Claude Code, Codex from TashanGKD/tashan-cursor-skills. It costs 136 tokens per session (3,015 once invoked), scanned A, original, MIT.

A system-wide verification workflow for checking whether Skills and related processes can pass information through complete task paths. It compares an expected path with the actual implementation and records evidence.

In plain words
What is it for?
Use it to validate the full Skill system, inspect domain health, and produce evidence-based repair proposals.
Why use it?
It finds missing links, broken inputs or outputs, unreachable end states, and other gaps that local checks may miss.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to validate the full Skill system, inspect domain health, and produce evidence-based repair proposals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tashangkd/tashan-cursor-skills/skill-closure-verifier-meta
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.

Any agent
npx skills add TashanGKD/tashan-cursor-skills --skill skill-closure-verifier-meta
Clone the repo
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skills

Made for: Claude Code, Codex.

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 skill-closure-verifier-meta

README.md
[![agentmods](https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-closure-verifier-meta/github.svg)](https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-closure-verifier-meta)
Your own site
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-closure-verifier-meta"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-closure-verifier-meta/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.

agentmods 80×15 button for skill-closure-verifier-meta

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/skill-closure-verifier-meta"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/skill-closure-verifier-meta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,015 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00136 $0.03015
Opus 5 $0.00068 $0.01507
Sonnet 5 $0.00027 $0.00603
Haiku 4.5 $0.00014 $0.00301

Measured 9d ago against content hash e031c7d41c14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skill-closure-verifier-meta 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 9d 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.

skills/skill-closure-verifier-meta/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

元级闭环验证编排器(skill-closure-verifier-meta)

关系类型:triggers(触发 skill-domain-health-check + skill-domain-self-optimizer) 关系类型:depends-on(依赖 DOMAIN-REGISTRY + NODE-IO-CONTRACTS + 沙盘库) 强绑定 Rule:R2 NO_FABRICATION / R3 READ_FIRST / R6 ARTIFACT_FIRST / R1 EVIDENCE_FIRST


核心设计原则

两阶段分离:Phase 1(预想)必须在不参考现有 Skill 实现细节的情况下完成。这防止了「验证者被被验证的系统污染」的自我确认偏误。

证据链完整:每个 Gap 必须有具体的证据(文件路径 + 步骤描述),不允许模糊归因。

可重复运行:每次运行产出独立的报告文件(含日期),不覆盖旧报告,支持对比演进。


激活后立即执行

Step 1  前置检查(硬性门槛)
        检查以下文件是否存在:
        - _内部总控/skill-system-design/DOMAIN-REGISTRY.md
        - _内部总控/skill-system-design/NODE-IO-CONTRACTS.md
        - _内部总控/skill-system-design/SANDBOX-FORMAT.md
        
        若任一文件不存在:
        → 停止执行,明确告知「元验证所需的形式化描述文档缺失」
        → 说明哪个文件缺失,以及如何创建它
        → 不允许「跳过缺失文件继续执行」
        
        若文件存在但有明显过期迹象(最后修改时间 > 30天):
        → 告知用户「形式化文档可能需要更新」,询问是否继续

Step 2  读取系统全景(R3 READ_FIRST 强制)
        用 explore 子智能体并行完成以下读取:
        
        组A(必须完成后才能进入 Phase 1):
        - DOMAIN-REGISTRY.md:读取五域节点图和终态定义
        - NODE-IO-CONTRACTS.md:读取所有节点的I/O契约
        - .cursor/skills/skill-index/SKILL-INDEX.md:读取现有37个Skill的状态
        
        组B(为 Phase 2 准备):
        - _内部总控/skill-system-design/sandboxes/ 所有子目录中的文件列表
        - .cursor/rules/role-menu.mdc:触发词路由规则

Step 3  Phase 1:预想验证(两阶段的第一阶段)
        
        ⚠️ 重要约束:此阶段不允许打开任何 SKILL.md 文件。
        Phase 1 的标准是「理想系统」,与现有实现无关。
        
        对每个域(5个域),执行以下操作:
        
        3.1 读取该域在 DOMAIN-REGISTRY 中的节点图和终态定义
        3.2 读取该域所有入口节点的 I/O 契约(从 NODE-IO-CONTRACTS)
        3.3 预想:若系统完美,从每个入口节点输入后,应该发生什么?
            - 预想触发链路:[入口] → [中间节点...] → [终态]
            - 预想终态输出:应该产出哪些文档/状态/产物
            - 预想自洽检查点:哪些文档应该相互一致
        3.4 将预想结果记录为「Phase 1 预想记录」(暂存在工作内存,不写文件)
        
        本步骤预计输出:5域 × N个入口节点 × 预想链路记录

Step 4  Phase 2:实际验证(两阶段的第二阶段)
        
        ⚠️ 注意:此阶段需要读取实际的 SKILL.md 文件,与 Phase 1 的预想对比。
        
        对每个域的每个沙盘文件(sandboxes/[域]/*.md):
        
        4.1 读取沙盘的「Phase 2 实际验证」部分
            - 若状态为 "validated"(无Gap):记录为通过,无需额外验证
            - 若状态为 "gap-found":提取Gap列表
            - 若状态为 "draft"(Phase 2未完成):对该沙盘执行实际验证
        
        4.2 对 "draft" 状态的沙盘,补全 Phase 2:
            读取该沙盘中涉及的每个节点的 SKILL.md(此时才读Skill文件)
            逐节点验证:触发了吗 / 输出了吗 / 触发下游了吗
            更新沙盘文件状态(draft → validated 或 gap-found)
        
        4.3 对照 Phase 1 预想:
            Phase 1 预想链路 vs Phase 2 实际链路 → 差异 = Gap 候选
            仅保留有沙盘证据支持的 Gap(无证据的不记录)

Step 5  Gap 汇总与分级
        汇总所有域的 Gap:
        
        5.1 合并来源:沙盘 Gap + Phase 1 vs Phase 2 对比差异
        
        5.2 为每个 Gap 分级:
            P0:传播完全断裂 / 缺失关键节点(Skill文件不存在)/ 系统无法自洽
            P1:触发条件缺失 / I/O不匹配 / 部分传播路径断裂
            P2:边界盲区 / 体验优化项(闭环完整但不够流畅)
        
        5.3 去重:相同根因的 Gap 合并为一条
        
        5.4 为每条 Gap 确认证据:
            - 沙盘文件路径(sandbox-ID + Gap行号)
            - 相关 Skill 文件路径
            - 具体说明(R2 NO_FABRICATION:无法找到具体证据的Gap不记录)

Step 6  调用 skill-domain-health-check(各域)
        对每个域调用 skill-domain-health-check,传入域名:
        
        → 等待各域健康报告生成
        → 将传播完备性检查结果纳入总报告
        
        若某域的健康报告已存在且日期为今天,跳过重复生成。

Step 7  调用 skill-domain-self-optimizer(有Gap的域)
        对 Step 5 中识别出有 P0 或 P1 Gap 的域:
        
        → 调用 skill-domain-self-optimizer,传入域名
        → 等待优化建议报告生成
        → 将行动建议纳入总报告的「整改计划」部分

Step 8  输出总验证报告(R6:必须写文件)
        写入:_内部总控/skill-system-design/validation-report-YYYYMMDD.md
        
        格式(见下方「总报告格式」)

Step 9  呈现摘要与下一步建议
        在对话中输出:
        - 验证覆盖范围(几个域/几个沙盘/几个节点)
        - 发现的总 Gap 数(P0: x, P1: y, P2: z)
        - 最高优先级的行动建议(P0项)
        - 是否建议立即执行修复

Read the full file on GitHub · 253 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. 9d ago First seen · 253 lines · 136 tokens per session scan A e031c7d41c14

Subscribe to this mod's changes

skill-closure-verifier-meta is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 136 tokens to every session and 3,015 once invoked, about $0.0007 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 2026-09-03.

Related

Other skills, from other repositories

android-preflight

Final verification checklist to run before declaring Android work finished — build, both themes, string resources, lifecycle and leak risks, registered permissions and components, resource parity between values and values-night, and honest reporting of what was and was not verified. Use at the end of any feature, fix…

orbitalsonic/AndroidPilot · 79 tokens

qa

QA lead testing mode with browser automation. Tests affected pages, fills forms, takes screenshots. Use when user says /qa, wants to test the app, needs QA verification, or wants browser-based testing.

Himanshu-Sangshetti/cursor-stack · 43 tokens

chaos

Failure injection — stress test implementations under hostile conditions before shipping.

Jkudjo/oh-my-cursor · 14 tokens

qa

Systematic QA pass — test the feature, find bugs, report with repro steps.

Jkudjo/oh-my-cursor · 18 tokens

android-feature

Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…

orbitalsonic/AndroidPilot · 72 tokens

template-helpers

Catalog of the reusable building blocks shipped with this Android template — BaseActivity/BaseFragment, the helpers/ extension files (navigation, lifecycle, toast, snackbar, dialogs, images, permissions, theme, locale, settings intents, date, delay), common/ (Firebase, network, observers), and…

orbitalsonic/AndroidPilot · 92 tokens