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 skills add TashanGKD/tashan-cursor-skills --skill cognitive-work-alignment-checkgit clone --depth 1 https://github.com/TashanGKD/tashan-cursor-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/tashangkd/tashan-cursor-skills/cognitive-work-alignment-check)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/cognitive-work-alignment-check"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/cognitive-work-alignment-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/skills/tashangkd/tashan-cursor-skills/cognitive-work-alignment-check"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/cognitive-work-alignment-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 | $0.00168 | $0.02228 |
| Opus 5 | $0.00084 | $0.01114 |
| Sonnet 5 | $0.00034 | $0.00446 |
| Haiku 4.5 | $0.00017 | $0.00223 |
Grade A, and why
cognitive-work-alignment-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 8d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
认知-工作对齐检查（cognitive-work-alignment-check）
关系类型：depends-on（依赖 DOMAIN-REGISTRY + L0大脑总地图 + L1.5底层原则库） 关系类型：triggers（报告被 skill-closure-verifier-meta 消费；修复建议触发 cognitive-update-knowledge / cognitive-extract-principle） 强绑定 Rule：R2 NO_FABRICATION / R3 READ_FIRST / R6 ARTIFACT_FIRST / R1 EVIDENCE_FIRST
核心检查目标
每个工作域的核心产出，是否能在 L1.5 原则库（包含候选原则）或 L1 文档（18篇，6个维度）中找到对应的认知根？
追溯标准：必须找到命题级别的语义对应，不是词语重叠。
- ✅ 可追溯：有明确对应的原则/文档
- ⚠️ 弱追溯：有关联但关系牵强，需加强映射
- ❌ 漂浮：找不到任何对应认知根
激活后立即执行
Step 1 读取检查依据（R3 READ_FIRST — 读完再分析）
并行读取：
A. _内部总控/skill-system-design/DOMAIN-REGISTRY.md
→ 提取五个工作域的「终态输出定义」
B. _内部总控/认知结构/L0_大脑总地图.md
→ 获取 L1 文档列表（18篇，6个维度）
C. _内部总控/认知结构/L1.5_底层原则层/底层原则库.md
→ 获取已确认原则（P1/P2）+ 全部候选原则（P4?/P5?/P6?/P7?/P8?）
⚠️ 候选原则也是有效认知根（标注为「候选级追溯」）
若任一文件不存在：
→ 停止执行，告知「[文件名] 缺失，无法完成对齐检查」
→ 不猜测，不用记忆中的内容代替
Step 2 确认检查范围
- 默认：检查全部五域（产品开发/认知结构/公司运营/内容宣传/Skill体系）
- 用户指定单域 → 只检查该域
- skill-closure-verifier-meta 调用时 → 从调用参数读取范围
Step 3 对每个工作域执行对齐检查
对每个域：
3.1 从 DOMAIN-REGISTRY.md 读取该域的「终态输出定义」
（该域完成闭环后最终产出什么？）
3.2 追溯检查（命题级别，不是词语级别）：
该域核心产出是否能追溯到以下任一：
- L1.5 原则：P1/P2 已确认 or P4?/P5?/P6?/P7?/P8? 候选
- L1 文档（18篇）中的某篇
追溯路径格式（仅供理解格式，非实际结论）：
「[域名]核心产出 ←根植于→ [原则编号] [原则名]（[一句理由]）
+ [文档编号] [文档名]（[一句理由]）」
3.3 判断等级：
✅ 可追溯：找到明确对应，给出追溯路径
⚠️ 弱追溯：有关联但映射牵强，说明「关系较弱，建议加强」
❌ 漂浮：无法找到认知根，给出「建议锚定到 [X]，因为 [理由]」
3.4 自我检查（防止过度乐观）：
若所有域都标✅ → 触发自我审查：逐一检查每条追溯路径是否真正命题级
→ 若有任何追溯路径是「词语重叠而非命题对应」→ 降级为⚠️
→ 若确认每条路径都是命题级追溯 → 可以全部✅，在报告中说明「已自我审查，确认命题级对应」
Step 4 输出对齐报告（R6：必须写文件）
Write: _内部总控/skill-system-design/cognitive-alignment-report-YYYYMMDD.md
报告格式：
─────────────────────────────────────────────────────
# 认知-工作对齐报告（第四维健康检查）
检查日期：YYYY-MM-DD
检查范围：[N个域]
## 对齐矩阵
| 工作域 | 核心产出 | 追溯状态 | 追溯到 | 追溯强度 |
|---|---|---|---|---|
| 产品开发 | [终态产出] | ✅/⚠️/❌ | [P?/文档名] | 强/弱/无 |
| 认知结构 | ... | ... | ... | ... |
| 公司运营 | ... | ... | ... | ... |
| 内容宣传 | ... | ... | ... | ... |
| Skill体系 | ... | ... | ... | ... |
## 漂浮任务（若有）
- [域名]：无法追溯到认知根。
建议锚定方向：[P?候选] 或 [文档名]，因为 [1句理由]
## 整体结论
ALIGNED / PARTIALLY-ALIGNED / UNALIGNED
─────────────────────────────────────────────────────
Step 5 路由后续建议
✅ ALIGNED：「认知-工作体系自洽，无需立即行动。建议定期重跑（认知体系重大更新后）」
⚠️ PARTIALLY-ALIGNED：「建议为 [域] 补充认知映射，说「更新[文档名]」触发 cognitive-update-knowledge」
❌ UNALIGNED（有漂浮）：「建议重新审视 [域] 的必要性，
或说「提炼原则」触发 cognitive-extract-principle 建立缺失的认知根」
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.
- 8d ago First seen · 154 lines · 168 tokens per session scan A cefd253ea0e4
cognitive-work-alignment-check is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 168 tokens to every session and 2,228 once invoked, about $0.0008 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.
Other skills, from other repositories
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…
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…
android-new-project
Workflow for turning a fresh copy of this Android template into a new app — renaming the package/namespace/applicationId, branding (icons, splash, palette, fonts), Firebase setup, signing config, stripping unused sample screens, and verifying the foundation. Use when the user says they are starting a new app…
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…
android-upgrade
Workflow for changing an existing working Android project — upgrading dependencies, AGP/Gradle or SDK levels, migrating deprecated APIs, refactoring, and fixing bugs, without breaking what already works. Covers baseline verification, scoping the diff, targetSdk behaviour changes, SharedPreferences/Room data…
android-build-config
Gradle and build configuration rules for this template — AGP 9 / Gradle 9 DSL (built-in Kotlin, compileSdk block, optimization block instead of minify/proguard), the gradle/libs.versions.toml version catalog, R8 keep rules in keepRules/.keep, gradle.properties defaults, and manifest registration. Use when editing…