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 alivirgo/Major-AI-Skills --skill iterate-step-by-stepgit clone --depth 1 https://github.com/alivirgo/Major-AI-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/alivirgo/major-ai-skills/iterate-step-by-step)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/iterate-step-by-step"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/iterate-step-by-step/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/alivirgo/major-ai-skills/iterate-step-by-step"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/iterate-step-by-step.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 | $0.00037 | $0.00991 |
| Opus 5 | $0.00018 | $0.00495 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
iterate-step-by-step 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 7d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iterate Step-by-Step (Conversational Scaffolding) (AI Skill)
Overview
Expecting an AI to produce a finished, 10/10 masterpiece in a single massive prompt ("Write a complete multi-chapter marketing strategy and all ad copy") is a recipe for disappointment. The model spreads its attention across too many variables, producing shallow text and skipped details.
The Conversational Scaffolding Protocol breaks production into a 4-Turn Agile Loop: scaffold the outline $\rightarrow$ build the core engine $\rightarrow$ harden edge cases $\rightarrow$ polish the final output.
The 4-Turn Scaffolding Pipeline
┌─────────────────────────────────────────────────────────────┐
│ 4-Turn Scaffolding Pipeline │
│ │
│ [ TURN 1: Wireframe / Skeleton ] ──► Agree on structure │
│ │ │
│ [ TURN 2: Core Drafting / Build ] ──► Generate meat │
│ │ │
│ [ TURN 3: Stress-Test & Edges ] ──► Catch flaws & bugs │
│ │ │
│ [ TURN 4: Surgical Polish ] ──► Voice, SEO, & CTA │
└─────────────────────────────────────────────────────────────┘
Master Iteration Prompt Templates
Pattern 1: The 4-Turn Execution Script
Use when building a complex deliverable (e.g. business plan, landing page, software module):
<!-- TURN 1: The Skeleton -->
"We are going to build [PROJECT]. Do NOT write the content yet.
Give me a 5-point structural outline. I will review and adjust."
<!-- TURN 2: The Core Build (After adjusting Turn 1) -->
"The outline is locked. Now write Section 1 and Section 2 ONLY.
Follow our agreed constraints and focus on high depth."
<!-- TURN 3: Edge-Case Hardening -->
"Now review what we have so far. Where are the weak points or missing scenarios?
Suggest 3 specific additions."
<!-- TURN 4: The Final Polish -->
"Apply the additions from Turn 3 and output the polished, production-ready version."
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.
- 7d ago First seen · 87 lines · 37 tokens per session scan A 202fb53dd365
iterate-step-by-step is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 991 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 2026-09-05.
Other skills, from other repositories
Cursor Workflow Optimizer
Master Cursor IDE with optimal configurations, custom rules, MCP integrations, and workflow patterns that 10x developer productivity.
cli-builder
Professional CLI Builder skill. Improve code delivery speed and developer workflows through automation and modern tooling.
developer-portal
Professional Developer Portal Expert skill. Improve code delivery speed and developer workflows through automation and modern tooling.
formatter-setup
Professional Formatter Setup Expert skill. Improve code delivery speed and developer workflows through automation and modern tooling.
linting-configurator
Professional Linting Configurator Expert skill. Improve code delivery speed and developer workflows through automation and modern tooling.
readme-master
Professional Readme Master skill. Improve code delivery speed and developer workflows through automation and modern tooling.