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 tqtuan1201/TTBaseUIKit --skill ttb-skill-refactorgit clone --depth 1 https://github.com/tqtuan1201/TTBaseUIKitWrote 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/tqtuan1201/ttbaseuikit/ttb-skill-refactor)<a href="https://agentmods.dev/skills/tqtuan1201/ttbaseuikit/ttb-skill-refactor"><img src="https://agentmods.dev/badge/skills/tqtuan1201/ttbaseuikit/ttb-skill-refactor/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/tqtuan1201/ttbaseuikit/ttb-skill-refactor"><img src="https://agentmods.dev/badge/skills/tqtuan1201/ttbaseuikit/ttb-skill-refactor.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 | $0.00040 | $0.01421 |
| Opus 5 | $0.00020 | $0.00711 |
| Sonnet 5 | $0.00008 | $0.00284 |
| Haiku 4.5 | $0.00004 | $0.00142 |
Grade A, and why
ttb-skill-refactor 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 10d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ttb-skill-refactor
Enterprise-grade refactoring workflow for TTBaseUIKit apps. Zero Functional Change | TTViewCodable | TTBaseSUI | MVVM-C
Mandatory Preflight Execution Gate
Before this skill generates code, refactors, migrates, modifies files, creates architecture, updates UI/navigation, changes dependencies, updates workflows, or changes business logic, run the shared gate:
ttb-skill-shared/fragments/ttb-preflight-execution-gate.frag.mdttb-skill-shared/fragments/ttb-cross-functional-analysis-gate.frag.mdwhen refactor scope touches feature behavior, UX flow, architecture, or bug preventionttb-skill-shared/templates/ttb-clarification-survey.mdwhen confidence is below threshold
Required phase order: Requirement Analysis -> Context Validation -> Ambiguity Detection -> Missing Information Detection -> Survey / Clarification -> Confidence Evaluation -> Execution Approval.
Execution thresholds:
| Confidence | Action |
|---|---|
90-100 |
Execute directly and state key assumptions |
70-89 |
Execute only with documented low-risk assumptions |
<70 |
Do not execute; ask a concise survey first |
Cap confidence at 69 when target module, architecture direction, UIKit/SwiftUI choice, navigation behavior, API/business logic, localization format, state management, dependency info, or ownership is unclear. Parse English, Vietnamese, mixed-language, diacritic-free Vietnamese, and light typos before scoring.
When refactor scope is tied to feature updates, bug prevention, architecture changes, or user-visible flow changes, analyze as Product Owner, Business Analyst, UX/UI Designer, Solution Architect, Senior Developer, and QA. Compare options across business value, architecture, UI/UX, performance, scalability, maintainability, security, testing, and operations; ask at least 5 value-expansion questions after analysis. If requirements are ambiguous/incomplete, ask at least 6 clarification questions before design/development.
What ships with it
1 file 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.
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.
- 10d ago First seen · 123 lines · 40 tokens per session scan A da0f820f914b
ttb-skill-refactor is a skill published in the GitHub repository tqtuan1201/TTBaseUIKit (23 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,421 once invoked, about $0.0002 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.
Other skills, from other repositories
ax-uikit
UIKit-SwiftUI bridging (UIViewRepresentable, UIHostingController, UIHostingConfiguration), Auto Layout debugging, CAAnimation diagnosis, @Observable shared state, gesture recognizer bridging.
focus-engine
Implement or debug keyboard, directional, and scene-level focus across SwiftUI and UIKit. Use for FocusState, focus restoration and routing, tvOS remote navigation, watchOS crown focus, visionOS input focus, macOS key loops, UIFocusGuide, or UIFocusDebugger.
swiftui-webkit
Embeds and controls web content in SwiftUI with WebKit for SwiftUI, including WebView, WebPage, navigation policies, JavaScript execution, observable page state, link interception, local HTML or data loading, and custom URL schemes. Use when building iOS 26+ article/detail views, help centers, in-app documentation, or…
swiftui-gestures
Builds or reviews SwiftUI tap, press, drag, magnify, and rotate interactions, including gesture composition, transient GestureState, custom gestures, and parent/child conflict resolution. Use for gesture recognition, arbitration, state, migration, or interaction bugs.
swiftui-patterns
Structure and refactor SwiftUI views using Observation, clear state ownership, composition, and deterministic previews. Use for view architecture and data flow; route detailed layout, navigation, animation, performance, and visual effects to their dedicated skills.
swiftui-animation
Implement or diagnose SwiftUI motion, including state animations, transitions, springs, keyframes, matched geometry, navigation zoom, and symbol effects. Use when motion behavior is part of the request; route layout, navigation state, and performance profiling elsewhere.