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 DorianSchlede/nexus-template --skill learn-buildsgit clone --depth 1 https://github.com/DorianSchlede/nexus-templateWrote 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/dorianschlede/nexus-template/learn-builds)<a href="https://agentmods.dev/skills/dorianschlede/nexus-template/learn-builds"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/learn-builds/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/dorianschlede/nexus-template/learn-builds"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/learn-builds.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 | $0.00053 | $0.01209 |
| Opus 5 | $0.00026 | $0.00605 |
| Sonnet 5 | $0.00011 | $0.00242 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
learn-builds 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 8d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[TARGET] Build-First Onboarding (CONTEXTUAL SUGGESTION)
This is a learning skill. With Build-First onboarding, suggest AFTER first build, not before.
Auto-Complete via Checkpoint
# In user-config.yaml
build_first.checkpoints.first_build_created: true → learn_builds auto-completed!
When user creates their first build, learn_builds is automatically marked complete via auto_complete_map. They learned by DOING.
When to Proactively Suggest (Post-Experience)
Check both:
learning_tracker.completed.learn_builds- explicit completionbuild_first.checkpoints.first_build_created- auto-completion
PROACTIVELY SUGGEST when user:
- AFTER first build - asks "how does this build system work?" (wants deeper understanding)
- Expresses confusion about builds vs skills (after having used builds)
- Starts creating multiple similar "builds" (anti-pattern detection)
- Explicitly asks to learn/understand builds
Suggestion Pattern (Post-Experience):
💡 You've already created a build! Want to understand the system more deeply?
'learn builds' covers:
- When to use builds vs skills (avoid anti-patterns)
- Build lifecycle and best practices
- How to track progress effectively
Say 'learn builds' for the deep-dive (8 min), or continue working.
If user already created build, acknowledge it:
You've got practical experience now! This tutorial will deepen your understanding
of WHY the system works this way.
DO NOT suggest if:
- User is creating their FIRST build (let them DO first)
- User explicitly says "skip" or dismisses
- User is mid-task and focused
Learn Builds
Teach how Nexus builds work through examples and decision framework.
Purpose
Help user understand when to create builds vs skills, how builds are structured, and the build lifecycle. Uses concrete examples before abstract concepts.
Time Estimate: 8-10 minutes
Workflow
Step 1: Concrete Examples
Show what IS and ISN'T a build:
[OK] BUILDS:
- Build client proposal for Acme Corp
- Research competitors and write analysis
- Create onboarding docs for new hires
[ERROR] NOT BUILDS (these are skills):
- Generate weekly status reports (repeating)
- Qualify incoming leads (repeating)
- Format documents (repeating)
Pattern: Builds END. Skills REPEAT.
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.
- 8d ago First seen · 197 lines · 53 tokens per session scan A 09ad84e3eba0
learn-builds is a skill published in the GitHub repository DorianSchlede/nexus-template (8 stars, last pushed 7mo ago), licensed MIT. It adds 53 tokens to every session and 1,209 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.