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/visionnpx skills add YougLin-dev/Aha-Loop --skill visiongit 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 | $0.01795 |
| Opus 5 | $0.00020 | $0.00898 |
| Sonnet 5 | $0.00008 | $0.00359 |
| Haiku 4.5 | $0.00004 | $0.00179 |
Grade A, and why
vision 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 — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision Analysis Skill
Parse the project vision document and extract structured requirements for architecture and planning.
Workspace Mode Note
When running in workspace mode, all paths are relative to .aha-loop/ directory:
- Vision file:
.aha-loop/project.vision.md - Analysis output:
.aha-loop/project.vision-analysis.md
The orchestrator will provide the actual paths in the prompt context.
The Job
- Read
project.vision.mdfrom the project root - Validate all required sections are present
- Extract and structure the requirements
- Identify project type and scale
- Output analysis to guide architecture decisions
- Save analysis to
project.vision-analysis.md
Input: project.vision.md
The vision document should contain:
Required Sections
| Section | Purpose |
|---|---|
| What | One-sentence description of the project |
| Why | Motivation and problem being solved |
| Target Users | Who will use this product |
| Success Criteria | Measurable definition of success |
Optional Sections
| Section | Purpose |
|---|---|
| Constraints | Technical, budget, or time limitations |
| Inspirations | Reference products or desired style |
| Non-Goals | What the project explicitly won't do |
Analysis Process
Step 1: Validate Vision Document
Check that project.vision.md exists and contains required sections:
## Validation Checklist
- [ ] What section present and clear
- [ ] Why section explains motivation
- [ ] Target Users defined
- [ ] Success Criteria are measurable
If sections are missing or unclear, document what's needed before proceeding.
Step 2: Identify Project Type
Classify the project:
| Type | Characteristics |
|---|---|
| CLI Tool | Command-line interface, no UI |
| Web App | Browser-based, frontend + backend |
| API Service | Backend only, REST/GraphQL |
| Library | Reusable code package |
| Desktop App | Native desktop application |
| Mobile App | iOS/Android application |
| Full Stack | Complete web application |
| Infrastructure | DevOps, deployment tools |
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 · 337 lines · 40 tokens per session scan A d8eca0e1d9db
vision 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 1,795 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…