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 agentmods add skills/i-stack/ai-coding-kit/cognitive-expansionnpx skills add i-stack/ai-coding-kit --skill cognitive-expansiongit clone --depth 1 https://github.com/i-stack/ai-coding-kitWhat 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 | $0.00059 | $0.01194 |
| Opus 5 | $0.00030 | $0.00597 |
| Sonnet 5 | $0.00012 | $0.00239 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
cognitive-expansion 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 2d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Expansion
强制入口
命中本 skill 时，必须先完整阅读 references/cognitive_expansion.md 并按其中条款执行。
- 不得以 preamble、Cursor 规则摘要或其它二次摘要代替该文件全文。
- Tier 2（认知对手）由 ios-engineer references/cognitive_adversary_mode.md 承载；本 skill 管 Tier 0 / Tier 3 拓展。
- 同步依赖：本 skill 通过相对路径引用
../ios-engineer/references/cognitive_adversary_mode.md；同步到各端时，需确保ios-engineerskill 也同步到同层 skills 目录（如~/.claude/skills/ios-engineer），否则该链接失效。条件性：仅当 ios-engineer 已同步到同层 skills 目录时，Tier 2 链接可用；非 iOS 环境（未同步 ios-engineer）下，本 skill 仅提供 Tier 0 / Tier 3，Tier 2 需用户显式加载 ios-engineer，不得因链接不可达而中断 Tier 0/3。
何时加载
- 门控：Tier 0 认知尾注默认不触发；仅当本次回答含真实判断 / 取舍 / 归因 / 设计选择，且能产出至少 1 条可证伪盲区时才追加，否则静默（判据见详规「触发门控」）。
- 加深：用户写
【深潜】/【拓展】（Tier 3）。 - 跳过：用户明确「只要答案 / 不要延伸」；或门控未命中。
规则索引（owned rule IDs）
本 skill 的契约由下列 CE-NNN 规则承载，真值登记在 references/rule_index.md。形态校准示例（before/after 与退化标本）见 references/examples.md。行为门禁 scripts/validate-skill-behavior.sh 的 Check 2 校验二者 ID 集合双向一致（SKILL.md 声明的 ID 均被定义；rule_index.md 中 active 行均被 SKILL.md 声明）。
- [CE-001] Tier 0 触发门控：双条件（有判断成分 且 能产出≥1 条可证伪盲区）同时成立才追加认知尾注，否则静默不写。
- [CE-002] 重框：把问题提升为更一般判断/学习问题；纯执行任务写「重框略」。
- [CE-003] 盲区（可证伪硬判据）：1 条隐藏假设/遗漏维度/误区，须含（假设 X）+（可观测触发 Y）+（若 Y 则 X 错的否定条件）；写不出整段不写。
- [CE-004] 邻域（机制相关）：1 条相邻领域对照，须与当前问题机制相关，禁同技术栈换词重复主文。
- [CE-005] 带走：1 条可复用自检问句或 if-then 规则，禁鸡汤。
- [CE-006] Tier 0/Tier 2 互斥：认知对手（Tier 2）命中时输出完整校准结构，不再单独写 Tier 0；该互斥同时扩展到 preamble 轻量校准段（CAM 激活时由 CAM 完整结构承载，见 cognitive-calibration 段）。
- [CE-007] 深潜·心智模型：模型名 + 1 句如何用于本问题。
- [CE-008] 深潜·跨域类比：非本技术栈、机制对齐的 1 个类比；须点名被映射机制、禁陈词/换词类比（护栏见 references/cognitive_expansion.md §Tier 3）。
- [CE-009] 深潜·验证动作：7 天内可做的 1 个具体动作。
- [CE-010] 迎合自检：写完过三问（邻域非换词 / 带走非鸡汤 / 盲区可证伪）。
- [CE-011] 跳过条件：用户「只要答案/不要延伸」或门控未命中即不写 Tier 0。
- [CE-012] 邻域对照池：从对照池任选 1 条且须与机制相关。
- [CE-013] 与 L2/L0 去重：同轮 logical-reasoning「逻辑链（可证伪/缺口）」或 problem-analysis「问题分析」已发时，盲区须换维度不得复述。
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- AGENT-BRIEF.md 1.1 KB
- i18n/en-US/references/agent_brief.md 1.5 KB
- i18n/en-US/references/cognitive_expansion.md 7.9 KB
- i18n/en-US/references/examples.md 4.4 KB
- i18n/en-US/references/out_of_scope.md 1.2 KB
- i18n/en-US/references/rule_index.md 3.8 KB
- i18n/en-US/references/skill.md 4.6 KB
- OUT-OF-SCOPE.md 804 B
- references/cognitive_expansion.md 6.4 KB
- references/examples.md 3.6 KB
- references/rule_index.md 3.0 KB
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.
- 2d ago First seen · 43 lines · 59 tokens per session scan A 6c3054aaf612
cognitive-expansion is a skill published in the GitHub repository i-stack/ai-coding-kit (3 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 1,194 once invoked, about $0.0003 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 skills, from other repositories
swiftui-design-consultation
Apple-canon design system for SwiftUI projects: produces DESIGN.md + a Swift Package starter (semantic colors, SF Pro, Liquid Glass, motion, accessibility). Use when starting or refreshing a SwiftUI design system.
e2e-route
Pure dispatcher: picks the right E2E executor for a Swift test request from context (platform × intent × verification kind) and hands off. Routes to the scaffold/MCP-sim/QA/design-review skills.
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
git-safety
Git safety rules. INVOKE WHEN: git push, force push, git reset, git clean, destructive git, push force, reset hard. NEVER force push or do destructive git operations.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.