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 modernize-flp-sandboxgit 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/modernize-flp-sandbox)<a href="https://agentmods.dev/skills/ui5/plugins-coding-agents/modernize-flp-sandbox"><img src="https://agentmods.dev/badge/skills/ui5/plugins-coding-agents/modernize-flp-sandbox/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/modernize-flp-sandbox"><img src="https://agentmods.dev/badge/skills/ui5/plugins-coding-agents/modernize-flp-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 274 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00058 | $0.05004 |
| Opus 5.5 | $0.00023 | $0.02002 |
| Sonnet 5.5 | $0.00012 | $0.01001 |
| Haiku 4.5 | $0.00006 | $0.00500 |
Grade A, and why
modernize-flp-sandbox 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Sandbox Migration Skill
Migrate a UI5 application from the legacy FLP sandbox to New Sandbox. You analyze, transform, verify, and report. The skill is fully automatic for the core migration; for adjacent concerns (see scope below) it asks the consumer before acting.
Read references/operations.md now — it is the operational reference for
all HTML / JSON / hook-module transformations.
Read references/sandbox-config-surface.md now — it is the ground-truth
description of what New Sandbox allows, blocks, and silently overrides.
All §6 rules cite this file rather than restating constraints inline.
Scope — three layers
-
Core migration — actions necessary for the app to boot under New Sandbox. Performed unconditionally; fails migration if impossible. Triggers: §6a, §6b, §6c, §6f.
-
Test infrastructure — gets the test suite running again without changing test semantics. Safe rewrites applied unconditionally (resource-root rebind, OPA bootstrap extraction). Anything touching test logic: detect, report, offer on request. Triggers: §6d, §6e, §6g, §6h, §6j, §6l.
-
Adjacent migrations & advisories — concerns surfaced by the migration but not part of it. Detect and report only; no rewrites applied.
- QUnit 1.x → 2.x patterns (§6i) — advisory.
- Shell-feature tests (§6j, §6l) — advisory.
- Deprecated ushell services (§6k) — detected in core pass, reported as "Manual action required" (hard runtime block).
1. Detect App Root
If the user provided a path argument, use it. Otherwise, detect from CWD:
- Look for
package.json+webapp/in CWD and parent directories - If not found, tell the user: "Could not detect a UI5 app root. Please run from inside
the app directory or provide a path:
/modernize-flp-sandbox ~/path/to/app"
Set APP_ROOT to the resolved absolute path.
2. Ensure Clean State (Pre-Migration)
Before touching any files, secure a rollback point.
If git repository detected:
cd $APP_ROOT
git stash push -m "modernize-flp-sandbox: pre-migration backup $(date +%Y%m%d-%H%M%S)"
Save the stash ref for rollback. If nothing to stash, the tree is already clean.
What ships with it
3 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 · 356 lines · 58 tokens per session scan A 73cbe7f6a0b2
modernize-flp-sandbox is a skill published in the GitHub repository UI5/plugins-coding-agents (41 stars, last pushed 4d ago), licensed Apache-2.0. It adds 58 tokens to every session and 5,004 once invoked, about $0.0002 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
plugin-init
A project starter for creating Zhin.js plugins, which are installable packages that extend the Zhin.js bot framework. It sets up the required files, folders, package metadata, entry point, and documentation.
plugin-publish
A release guide for publishing Zhin.js plugins to npm, the JavaScript package registry, and to the Zhin plugin marketplace. It covers package metadata, versioning, release checks, and submission requirements.
plugin-develop
A development guide for adding features to Zhin.js plugins, such as chat commands, AI tools, middleware, scheduled tasks, and console pages. Zhin.js is the plugin system it targets.
wordpress-plugin-fundamentals
Modern WordPress plugin development with PHP 8.3+, OOP architecture, hooks system, database interactions, and Settings API.
plugin-authoring
Create or extend a Cognia plugin through the current CLI contract and public SDK surfaces.
mcp-builder
MCP server development guide — build, test, and deploy MCP servers.