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-tool-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-tool-component)<a href="https://agentmods.dev/skills/gcwing/sparo-os/product-app-tool-component"><img src="https://agentmods.dev/badge/skills/gcwing/sparo-os/product-app-tool-component/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/gcwing/sparo-os/product-app-tool-component"><img src="https://agentmods.dev/badge/skills/gcwing/sparo-os/product-app-tool-component.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 | $0.00054 | $0.00390 |
| Opus 5 | $0.00027 | $0.00195 |
| Sonnet 5 | $0.00011 | $0.00078 |
| Haiku 4.5 | $0.00005 | $0.00039 |
Grade A, and why
product-app-tool-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 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.
What it actually says
Product App Tool Component Skill
Use this skill when the Product App needs a structured callable capability that can be invoked by the app or its app-private Agent. A Tool Component is an app-private tool contract for one Product App unless the user explicitly asks for a reusable shared capability outside App Builder's default delivery boundary.
Development Boundary
- Start from the current package facts and generated Tool scaffold. If the tool is missing, create it with
CreateProductAppComponentusing kindtool. - Define the contract in
source/tool.schema.json: name, description, input schema, and output schema. - Implement behavior in
source/tool.js, keeping outputs structured and stable. - Keep visible UI rendering in app-private surfaces and broad integration/service-action boundaries in Bridge Components.
- Keep permissions limited to the tool's declared behavior and callers.
Key Decisions
- Use a Tool Component when callers need a typed function-like capability, not when they need a visible screen or a long-running integration boundary.
- Design schemas from caller needs: required fields, result shape, error shape, and deterministic examples.
- Keep side effects explicit. If the tool writes files, runs shell commands, or calls network services, that must be reflected in permissions and validation.
- Use
product-app-apiwhen wiring the tool to Product App backend calls, permissions, or runtime evidence.
Validation
- Refresh the Product App lock after package or component graph changes.
- Run Product App package validation.
- Execute a capability preview or concrete fixture when allowed.
- If execution is not allowed or no fixture exists, validate the contract and report that behavior execution remains unverified.
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 · 31 lines · 54 tokens per session scan A b329f40006d5
product-app-tool-component is a skill published in the GitHub repository GCWing/Sparo-OS (20 stars, last pushed 29d ago), licensed MIT. It adds 54 tokens to every session and 390 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
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.
cost-analytics
Tracks token usage and API costs across all providers.