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/youglin-dev/aha-loop/vision-buildernpx skills add YougLin-dev/Aha-Loop --skill vision-buildergit clone --depth 1 https://github.com/YougLin-dev/Aha-LoopWhat 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 | $0.00040 | $0.01777 |
| Opus 5 | $0.00020 | $0.00889 |
| Sonnet 5 | $0.00008 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00178 |
Grade A, and why
vision-builder 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision Builder Skill
Guide users through an interactive conversation to build a complete, well-structured project vision document.
The Job
- Detect when user has a vague project idea
- Engage in structured dialogue using AskQuestion tool
- Progressively refine the vision through targeted questions
- Generate a complete
project.vision.mddocument - Validate the vision is actionable
When to Use
Activate this skill when user says things like:
- "I have an idea for..."
- "Help me build a project vision"
- "I want to create something that..."
- "Build a project vision for me"
- "I have an idea..."
- Any vague project description without clear structure
Conversation Flow
Phase 1: Project Type
Start by understanding what kind of project this is.
Question: What type of project is this?
Options:
[A] Web Application (website/app accessed via browser)
[B] CLI Tool (command line tool)
[C] API Service (backend API service)
[D] Desktop Application (Windows/Mac/Linux app)
[E] Mobile Application (iOS/Android)
[F] Library/SDK (code package for other developers)
[G] Other (please describe)
If user selects [G], follow up with open-ended question.
Phase 2: Core Problem
Understand the problem being solved.
Question: What problem does this project solve?
Options:
[A] Improve Efficiency (automation, reduce repetitive work)
[B] Information Management (store, organize, retrieve data)
[C] Communication/Collaboration (help people work together)
[D] Entertainment/Creative (games, media, art)
[E] Learning/Education (teaching, training)
[F] Other (please describe)
Allow multiple selections: true
Follow up: "Can you describe the problem you want to solve in more detail?"
Phase 3: Target Users
Identify who will use the product.
Question: Who will use this product?
Options:
[A] Developers/Technical Users
[B] General Consumers/Individual Users
[C] Enterprise/Team Users
[D] Specific Industry Professionals
[E] Personal Use Only
[F] Other
Allow multiple selections: true
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 · 358 lines · 40 tokens per session scan A ecebf5f952cb
vision-builder is a skill published in the GitHub repository YougLin-dev/Aha-Loop (181 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 1,777 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
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.…
speckit-analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
add-sample
Create a SamplesApp sample page with correct theming and attributes. Use when adding UI samples for controls.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
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…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…