Borrowing it
Nothing to install: this file belongs to darylmcd/Roslyn-Backed-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/darylmcd/Roslyn-Backed-MCP/main/.claude/skills/promote-tier/SKILL.mdgit clone --depth 1 https://github.com/darylmcd/Roslyn-Backed-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/darylmcd/roslyn-backed-mcp/promote-tier)<a href="https://agentmods.dev/skills/darylmcd/roslyn-backed-mcp/promote-tier"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/promote-tier/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/darylmcd/roslyn-backed-mcp/promote-tier"><img src="https://agentmods.dev/badge/skills/darylmcd/roslyn-backed-mcp/promote-tier.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 | $0.00148 | $0.03854 |
| Opus 5 | $0.00074 | $0.01927 |
| Sonnet 5 | $0.00030 | $0.00771 |
| Haiku 4.5 | $0.00015 | $0.00385 |
Grade A, and why
promote-tier 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 11d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote Tier
You flip the support tier of one MCP tool, resource, or prompt atomically across BOTH source-of-truth sites: the [McpToolMetadata("category", "tier", ...)] attribute (or its resource/prompt equivalent on the catalog entry) AND the matching catalog row. The SurfaceCatalogTests parity check enforces the dual-write contract — an edit that touches one site without the other fails the test, which is the safety net for this skill.
This is a maintainer-side skill (lives at .claude/skills/promote-tier/, NOT skills/promote-tier/). It is invoked by the maintainer at release-cut time after /publish-preflight Step 8 surfaces promotion candidates. It is NOT shipped to plugin consumers.
Quorum requirement (read first)
/publish-preflight Step 8 now feeds this skill from an aggregated scorecard produced by eng/aggregate-promotion-scorecards.ps1, which gathers per-repo _latest-promotion-scorecard.json files from every configured sibling repo and applies a quorum rule before recommending a tier flip:
- A name is surfaced for promotion only when ≥2 sibling repos voted
promoteAND zero sibling repos votedkeep-experimentalordeprecate(the aggregator emitsverdict: "promote: ready"). - Single-workspace anomalies no longer drive tier decisions. A tool that worked cleanly on one workspace but failed on another stays experimental.
Maintainer override. If a strong single-repo signal warrants flipping a tier without quorum (e.g. a tool whose only meaningful exercise repo is the one that audited it), the maintainer may invoke this skill directly with the name + target tier. There is no flag that bypasses the quorum gate at the aggregator layer — the override is simply "skip Step 8's surface and call /promote-tier <name> <tier> manually." Document the override rationale in the commit message or release notes so future audits can correlate the flip with its evidence.
This skill itself does NOT enforce quorum — it is a mechanical two-site flip. Quorum is /publish-preflight Step 8's contract; this skill is invoked after Step 8 has either surfaced a quorum-passing candidate or the maintainer has chosen to override.
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.
- 11d ago First seen · 234 lines · 148 tokens per session scan A 9f2436ea344c
promote-tier is a skill published in the GitHub repository darylmcd/Roslyn-Backed-MCP (1 stars, last pushed today), licensed MIT. It adds 148 tokens to every session and 3,854 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…