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 Sudiddii/build-DNA --skill build-dnagit clone --depth 1 https://github.com/Sudiddii/build-DNAWrote 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/sudiddii/build-dna/build-dna)<a href="https://agentmods.dev/skills/sudiddii/build-dna/build-dna"><img src="https://agentmods.dev/badge/skills/sudiddii/build-dna/build-dna/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/sudiddii/build-dna/build-dna"><img src="https://agentmods.dev/badge/skills/sudiddii/build-dna/build-dna.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 | $0.00199 | $0.03757 |
| Opus 5 | $0.00100 | $0.01878 |
| Sonnet 5 | $0.00040 | $0.00751 |
| Haiku 4.5 | $0.00020 | $0.00376 |
Grade A, and why
build-dna 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build-DNA
Turn who you are → into what to build → into how to sell it.
Build-DNA runs in three phases. Move through them in order. Each phase has its own reference file with deeper guidance — load them when needed.
Phase 1: DNA Scan (Adaptive Intake)
Goal: Build a rich personal profile so the idea generation is specific to this person, not generic.
Ask questions adaptively — never dump all questions at once. Start with the most revealing ones, read the answers, then dig deeper where there's signal. Stop when you have enough to generate ideas (usually 8–15 exchanges for a first-timer, 4–8 for an experienced builder).
Core question areas (pick the highest-signal ones based on context):
Identity & Strengths
- What do you do better than most people you know?
- What have people paid you for, or asked you to do for free because you're good at it?
- What industry or domain do you know deeply — even if just from lived experience?
- What languages do you speak? Where have you lived or traveled?
Interests & Obsessions
- What do you spend time on when nobody's watching?
- What topics do you go deep on — YouTube rabbit holes, books, forums?
- What communities are you part of (online or offline)?
Resources & Unfair Advantages
- What tools, software, or equipment do you already own?
- What's your rough time budget? (hours/week, and for how long)
- What's your rough money budget to start?
- Do you have an audience, a newsletter, followers, or a network in any niche?
Your Circle (First Customers)
- Who are your 10–50 closest people — friends, family, colleagues, online connections?
- What problems do they complain about most?
- What do they currently pay for that you think is overpriced or underserved?
Desires & Motivation
- What's the real reason you want to build something? (freedom, money, impact, status, boredom?)
- What does success look like in 12 months?
- What type of work do you not want to do?
Context Clues
- Where are you based? (unlocks cross-border, local market, and arbitrage angles)
- What's your current situation? (student, employed, freelancer, unemployed, parent?)
- Have you tried building anything before? What happened?
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 · 361 lines · 199 tokens per session scan A 0d8ab5e9feec
build-dna is a skill published in the GitHub repository Sudiddii/build-DNA (4 stars, last pushed 3mo ago), licensed MIT. It adds 199 tokens to every session and 3,757 once invoked, about $0.0010 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
relay
Capture the full context of the CURRENT Claude chat into a complete, portable briefing the user can paste into a NEW chat to continue seamlessly. Use ONLY when the user explicitly asks — e.g. "relay", "relay this", "handover", "hand off", "handoff", "continue in a new chat", "this chat is getting long", "carry this…
data-craft
Generate beautiful themed HTML data displays. Six visual idioms with matched voices, rendered as self-contained HTML files. Use when the user asks for charts, dashboards, reports, tearsheets, briefings, data visualizations, or any data-driven document.
claude-students
Transforma una carpeta cruda de material de un parcial universitario (PDFs, DOC/DOCX, PPT, audios .ogg de WhatsApp, capturas) en un material de estudio polished y completo — HTML SOTA autocontenido + paquete de artefactos de NotebookLM (podcast en español, infografía, guía de estudio, briefing doc, mind map, quiz…
laravel-13-expert
Comprehensive Laravel 13.x expert skill covering the entire framework — installation, configuration, routing, controllers, middleware, Blade views, Eloquent ORM, migrations, queues, jobs, events, mail, notifications, caching, Redis, scheduling, service container, service providers, authentication, authorization, AI…
context-summary
Produces a lean, paste-ready session handoff so work can continue in a new conversation without re-paying the cost of the full chat. Emits a seven-block skeleton optimized for re-entry, not archival. Trigger this skill whenever the user says any of the following (exact or close paraphrase): "context summary"…
foreman
A supervisor skill that explains another skill in plain language and manages its execution while showing progress and asking for decisions at important points.