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 sandervanscheepen/silverstripe-mcp --skill silverstripe-devgit clone --depth 1 https://github.com/sandervanscheepen/silverstripe-mcpWrote 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/sandervanscheepen/silverstripe-mcp/silverstripe-dev)<a href="https://agentmods.dev/skills/sandervanscheepen/silverstripe-mcp/silverstripe-dev"><img src="https://agentmods.dev/badge/skills/sandervanscheepen/silverstripe-mcp/silverstripe-dev/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/sandervanscheepen/silverstripe-mcp/silverstripe-dev"><img src="https://agentmods.dev/badge/skills/sandervanscheepen/silverstripe-mcp/silverstripe-dev.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 | $0.00000 | $0.00541 |
| Opus 5.5 | $0.00000 | $0.00216 |
| Sonnet 5.5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
silverstripe-dev 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 2mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Silverstripe 6 Development Skill
You are skilled in Silverstripe CMS 6 development. Use this knowledge when working with Silverstripe PHP projects.
Key Silverstripe 6 Changes
Reference: https://docs.silverstripe.org/en/6/changelogs/6.0.0/
Namespace Changes
Many core classes moved namespaces in SS6:
| Class | Old (SS5) | New (SS6) |
|---|---|---|
| ArrayList | SilverStripe\ORM\ArrayList |
SilverStripe\Model\List\ArrayList |
| ArrayData | SilverStripe\View\ArrayData |
SilverStripe\Model\ArrayData |
| ViewableData | SilverStripe\View\ViewableData |
SilverStripe\Model\ModelData |
| PaginatedList | SilverStripe\ORM\PaginatedList |
SilverStripe\Model\List\PaginatedList |
| ValidationResult | SilverStripe\ORM\ValidationResult |
SilverStripe\Core\Validation\ValidationResult |
BuildTask Pattern
SS6 BuildTasks use Symfony Console:
// SS6 BuildTask pattern
use SilverStripe\Dev\BuildTask;
use SilverStripe\PolyExecution\PolyOutput;
use Symfony\Component\Console\Command\Command;
use Symfony\Component\Console\Input\InputInterface;
class MyTask extends BuildTask
{
protected static string $commandName = 'my-task';
protected static string $description = 'Task description';
protected function execute(InputInterface $input, PolyOutput $output): int
{
$output->writeln('Output goes here');
return Command::SUCCESS;
}
}
Do NOT use:
run(HTTPRequest $request)methodechofor outputprivate static $segment
Extension Hooks
Extension hook methods should be protected, not public:
// Correct in SS6
protected function updateCMSFields(FieldList $fields): void
protected function onBeforeWrite(): void
protected function onAfterWrite(): void
MCP Tools Available
When the Silverstripe MCP server is connected, use these tools:
- ss-validator - ALWAYS validate PHP code before presenting to user
- list-sections - Discover available SS6 changelog sections
- get-documentation - Fetch specific changelog sections
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.
- 2mo ago First seen · 78 lines · 0 tokens per session scan A a19ec7d0cf9c
silverstripe-dev is a skill published in the GitHub repository sandervanscheepen/silverstripe-mcp (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 541 tokens. 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.
silverstripe-dev compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| silverstripe-devsandervanscheepen/silverstripe-mcp | Skill | 5 | 8mo ago | MIT | A | 0 | Claude Code, Codex |
| add-exportcyanheads/mcp-ts-core | Skill | 153 | yesterday | Apache-2.0 | A | 50 | Claude Code, Codex |
| quantum-vqexi-zhao/OpenQuantum | Skill | 72 | today | MIT | A | 53 | Claude Code, Codex |
| quantum-vqlsxi-zhao/OpenQuantum | Skill | 72 | today | MIT | A | 56 | Claude Code, Codex |
| qsyn-compilationxi-zhao/OpenQuantum | Skill | 72 | today | MIT | A | 47 | Claude Code, Codex |
| typescript-lspyoudotcom-oss/dx-toolkit | Skill | 25 | 1mo ago | MIT | A | 51 | Claude Code |
| Laravel Migration Safety Reviews977043/river-review | Skill | 7 | today | MIT | A | 32 | Claude Code |