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 NimbleBrainInc/upjack --skill upjack-app-buildergit clone --depth 1 https://github.com/NimbleBrainInc/upjackWrote 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/nimblebraininc/upjack/upjack-app-builder)<a href="https://agentmods.dev/skills/nimblebraininc/upjack/upjack-app-builder"><img src="https://agentmods.dev/badge/skills/nimblebraininc/upjack/upjack-app-builder/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/nimblebraininc/upjack/upjack-app-builder"><img src="https://agentmods.dev/badge/skills/nimblebraininc/upjack/upjack-app-builder.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 | $0.00092 | $0.05994 |
| Opus 5.5 | $0.00037 | $0.02398 |
| Sonnet 5.5 | $0.00018 | $0.01199 |
| Haiku 4.5 | $0.00009 | $0.00599 |
Grade A, and why
upjack-app-builder 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 1mo 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 — 706 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upjack App Builder
Generate complete, spec-compliant NimbleBrain Upjack apps from a plain English description. The user says "create me a todo app" and you produce every file needed for a working Upjack app.
Quick Start
User says: "Create me a todo app"
You produce:
todo/
├── manifest.json
├── README.md
├── schemas/
│ ├── task.schema.json
│ ├── project.schema.json
│ └── label.schema.json
├── skills/
│ └── task-management/
│ └── SKILL.md
├── context.md
├── seed/
│ └── sample-tasks.json
└── server.py
References
Read these before generating. They are the source of truth. All paths are relative to the Upjack repo root.
- Upjack spec:
docs/SPEC.md - Entity model:
docs/ENTITY_MODEL.md - Manifest spec:
docs/UPJACK_MANIFEST.md - Manifest schema:
schemas/v1/upjack-manifest.schema.json - Entity base schema:
schemas/v1/upjack-entity.schema.json - CRM example:
examples/crm/ - Research example:
examples/research-assistant/ - Library source:
lib/src/upjack/
Process
Phase 1: Understand the Request
Extract from the user's description:
- App domain: What problem space? (productivity, finance, content, operations, etc.)
- Core entities: What things does the user manage? (tasks, projects, invoices, articles)
- Behaviors: What should the agent do automatically? (prioritize, categorize, alert, summarize)
- Relationships: How do entities connect? (tasks belong to projects, invoices have line items)
- Target location: Where to create files. Default:
examples/{app-name}/
If the request is ambiguous, ask ONE round of clarifying questions. Keep it tight — propose a default and ask if they want changes:
I'll build a todo app with these entities:
- task (the core item — title, description, priority, due date)
- project (groups tasks)
- label (categorization tags)
One skill: task-management (prioritization, overdue detection, daily planning).
Sound right, or should I adjust?
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 706 lines · 92 tokens per session scan A 2aa6b6d11792
upjack-app-builder is a skill published in the GitHub repository NimbleBrainInc/upjack (11 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 5,994 once invoked, about $0.0004 per session on Opus 5.5. 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
kn-implement
Use when implementing a task - follow the plan, check ACs, track progress.
kn-spec
Use when creating a specification document for a feature (SDD workflow).
kn-flow
Use when orchestrating a full Knowns spec or task wave through planning, implementation, review, integration, and verification, optionally using sub-agents when scopes are parallel-safe.
kn-handoff
Use when a feature crosses repository boundaries and one side must hand work to the other - generates a self-contained frontend-to-backend brief or backend-to-frontend API contract.
kn-debug
Use when debugging errors, test failures, build issues, or blocked tasks — structured triage to fix to learn.
kn-plan
Use when creating an implementation plan for a task.