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 UI5/plugins-coding-agents --skill ui5-best-practices-mdcgit clone --depth 1 https://github.com/UI5/plugins-coding-agentsWrote 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/ui5/plugins-coding-agents/ui5-best-practices-mdc)<a href="https://agentmods.dev/skills/ui5/plugins-coding-agents/ui5-best-practices-mdc"><img src="https://agentmods.dev/badge/skills/ui5/plugins-coding-agents/ui5-best-practices-mdc/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/ui5/plugins-coding-agents/ui5-best-practices-mdc"><img src="https://agentmods.dev/badge/skills/ui5/plugins-coding-agents/ui5-best-practices-mdc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 17 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 107 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00248 | $0.02226 |
| Opus 5.5 | $0.00099 | $0.00890 |
| Sonnet 5.5 | $0.00050 | $0.00445 |
| Haiku 4.5 | $0.00025 | $0.00223 |
Grade A, and why
ui5-best-practices-mdc 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI5 MDC Controls Best Practices
Apply these guidelines whenever generating, reviewing, or troubleshooting MDC control code in freestyle applications using OData V4 services.
UI5 version baseline: SAPUI5 1.136+ LTS. All features mentioned are available from this version unless noted.
When to load each reference
| Trigger | Load |
|---|---|
Working on or planning a sap.ui.mdc.FilterBar |
references/mdc-filter-bar.md |
Working on or planning a sap.ui.mdc.Chart |
references/mdc-chart.md |
Working on or planning a sap.ui.mdc.Field |
references/mdc-field.md |
Working on or planning a sap.ui.mdc.FilterField |
references/mdc-filter-field.md |
Working on or planning a sap.ui.mdc.ValueHelp |
references/mdc-value-help.md |
Working on or planning a sap.ui.mdc.Link |
references/mdc-link.md |
Working on or planning a sap.ui.mdc.MultiValueField |
references/mdc-multi-value-field.md |
| Using MDC controls with JSON model (non-OData) | references/mdc-json-delegates.md |
What ships with it
8 files 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 · 137 lines · 248 tokens per session scan A dc9fcf338a36
ui5-best-practices-mdc is a skill published in the GitHub repository UI5/plugins-coding-agents (41 stars, last pushed 2d ago), licensed Apache-2.0. It adds 248 tokens to every session and 2,226 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
wordpress-plugin-fundamentals
Modern WordPress plugin development with PHP 8.3+, OOP architecture, hooks system, database interactions, and Settings API.
api-rate-limit-handler
Implement bounded, idempotency-aware API throttling, backoff, and retry handling for 429 and transient 5xx responses.
api-endpoint-builder
Builds reviewable REST API endpoint scaffolds with validation, error handling, authentication, and documentation. Follows best practices for security and scalability.
cohesivity
Use Cohesivity for a project backend only after the user explicitly chooses Cohesivity. Installing or reading this optional skill does not authorize bootstrap, deployment, global installs, or feedback.
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.