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 how-nexus-worksgit 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/how-nexus-works)<a href="https://agentmods.dev/skills/dorianschlede/nexus-template/how-nexus-works"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/how-nexus-works/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/how-nexus-works"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/how-nexus-works.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 | $0.00019 | $0.01852 |
| Opus 5 | $0.00010 | $0.00926 |
| Sonnet 5 | $0.00004 | $0.00370 |
| Haiku 4.5 | $0.00002 | $0.00185 |
Grade A, and why
how-nexus-works 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How Nexus Works
Quick 7-minute tour of Nexus concepts and workflows.
Purpose
Help users understand the core architecture of Nexus: what BUILDs and SKILLs are, how memory and workspace work, and how to use the system effectively.
Time Estimate: 7 minutes
Workflow
Part 1: BUILDs (2 min)
Display:
----------------------------------------------------
🏗️ PART 1: BUILDs
----------------------------------------------------
A BUILD is finite work with a clear beginning, middle, and end.
**Examples**:
[OK] Research competitor landscape → Report
[OK] Design brand strategy → Framework
[OK] Create onboarding docs → Documentation
[OK] Plan marketing campaign → Strategy
**NOT a BUILD**:
[FAIL] Weekly status reports (repeating task)
[FAIL] Daily standup notes (ongoing workflow)
[FAIL] Code formatting (repeating automation)
**Rule**: If it ENDS, it's a BUILD. If it REPEATS, it's a SKILL.
**BUILD Structure**:
02-builds/ID-name/
├── 01-planning/ # Think before you execute
├── 02-resources/ # Research & materials
├── 03-work-in-progress/# Drafts & iterations
└── 04-outputs/ # Final deliverables
**Lifecycle**:
1. 'plan build' → Define what you want
2. Planning phase → Answer discovery questions
3. 'execute build' → Work through phases
4. Completion → Deliverables in 04-outputs/
5. Archive → Moves to 02-builds/complete/
**Example**: "Research Competitors"
When you say "build competitor research", Nexus:
1. Asks: Who are your competitors? What do you want to know?
2. Creates: Planning document with research questions
3. Executes: Searches, analyzes, compiles findings
4. Delivers: competitor-analysis.md in 04-outputs/
5. Archives: Project moves to 02-builds/complete/ when done
Ask: "Do you have any questions about BUILDs so far?"
Wait for response. If user asks questions, answer them. If not, continue.
Part 2: SKILLs (2 min)
Display:
----------------------------------------------------
⚡ PART 2: SKILLs
----------------------------------------------------
A SKILL is a repeatable workflow you can execute anytime.
**Examples**:
[OK] 'close session' → Save progress, create report
[OK] 'list skills' → Show available workflows
[OK] 'mental models' → Apply thinking frameworks
[OK] Integration skills (if you add Slack, Airtable, etc.)
**When to create a SKILL**:
- You'll do this task more than once
- It's a standardized workflow
- Others might reuse it
**When to create a BUILD**:
- It's one-off work with deliverables
- You want structured planning & outputs
- It has a clear completion point
**Decision Tree**:
┌─ Does it repeat?
│ ├─ YES → SKILL
│ └─ NO ┐
│ └─ Does it have deliverables?
│ ├─ YES → BUILD
│ └─ NO → Just do it (no structure needed)
**How to load skills**:
- Type the skill name: 'close session', 'mental models'
- Or browse: 'list skills'
Nexus has 50+ built-in skills, and you can create your own.
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 · 303 lines · 19 tokens per session scan A 4d000c70b3f7
how-nexus-works is a skill published in the GitHub repository DorianSchlede/nexus-template (8 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 1,852 once invoked, about $0.0001 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.