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 GCWing/Sparo-OS --skill product-app-runtime-componentgit clone --depth 1 https://github.com/GCWing/Sparo-OSWrote 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/gcwing/sparo-os/product-app-runtime-component)<a href="https://agentmods.dev/skills/gcwing/sparo-os/product-app-runtime-component"><img src="https://agentmods.dev/badge/skills/gcwing/sparo-os/product-app-runtime-component.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00340 |
| Opus 5 | $0.00026 | $0.00170 |
| Sonnet 5 | $0.00010 | $0.00068 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade A, and why
product-app-runtime-component 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.
What it actually says
Product App Runtime Component Skill
Use this skill only when the Product App needs special execution or hosting behavior beyond the default Product App runtime host. A Runtime Component describes app-private runtime requirements; the runtime instance is the actual running app after launch.
Development Boundary
- Start from the current package facts and generated Runtime scaffold. If the runtime component is missing, create it with
CreateProductAppComponentusing kindruntime. - Edit
source/runtime.jsonand related generated docs/source only for special host requirements that the default Product App runtime host does not cover. - Keep ordinary UI, AI behavior, integration actions, and structured callable tools in Surface, Agent, Bridge, or Tool Components instead.
- Do not introduce a Runtime Component just to describe normal launch policy, permissions, or package metadata.
Runtime Vs Runtime Component
- Runtime is the platform execution environment and actual running instance of a Product App.
- A Runtime Component is an app-private package component that declares or implements special runtime host requirements for that Product App.
- The Runtime Component may depend on platform runtime capabilities, but it is not the runtime itself.
Validation
- Refresh the Product App lock after package or component graph changes.
- Run Product App package validation.
- Verify that the Product App still launches with the declared runtime definition.
- Report any unobserved runtime behavior clearly; package validation alone is not enough for runtime changes.
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 · 29 lines · 52 tokens per session scan A a828a4d29934
product-app-runtime-component is a skill published in the GitHub repository GCWing/Sparo-OS (20 stars, last pushed 27d ago), licensed MIT. It adds 52 tokens to every session and 340 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 2026-08-30.
Other skills, from other repositories
memory-consolidation
Weekly synthesis of accumulated notes and memory optimization.
systematic-debug
4-phase root cause analysis and debugging.
backup-skill
Creates and manages backup snapshots.
brainstorming
Socratic design refinement and ideation.
code-review
Automated code review with checklist and quality gates.
content-draft
Blog/newsletter/content writing skill.