Borrowing it
Nothing to install: this file belongs to sassoftware/sas-score-mcp-serverjs. 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/sassoftware/sas-score-mcp-serverjs/main/.skills/skills/score-cas/SKILL.mdgit clone --depth 1 https://github.com/sassoftware/sas-score-mcp-serverjsWrote 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/sassoftware/sas-score-mcp-serverjs/score-cas)<a href="https://agentmods.dev/skills/sassoftware/sas-score-mcp-serverjs/score-cas"><img src="https://agentmods.dev/badge/skills/sassoftware/sas-score-mcp-serverjs/score-cas/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/sassoftware/sas-score-mcp-serverjs/score-cas"><img src="https://agentmods.dev/badge/skills/sassoftware/sas-score-mcp-serverjs/score-cas.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 | $0.00066 | $0.00944 |
| Opus 5 | $0.00033 | $0.00472 |
| Sonnet 5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
score-cas 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 8d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Score CAS Program / CAS Model
When to use this skill
- Model type is
.casl(CAS Program — inline src code) - User references a CAS model table (
casmodelinlib.tableform, with optionalname) - User says "run cas program", "execute casl", "score cas model"
Model Forms
The tool sas-score-cas-program-score accepts two mutually exclusive model forms:
| Form | Params | When to use |
|---|---|---|
| Inline src code | src (required), no casmodel |
User provides CASL code directly |
| CAS model table | casmodel (required), name (optional) |
User references a persisted CAS model table |
If both
srcandcasmodelare provided,casmodeltakes precedence.
Tool
| Type | Verify | Score |
|---|---|---|
| CAS Program (inline) | (no pre-check) | sas-score-cas-program-score |
| CAS Model (table) | (no pre-check) | sas-score-cas-program-score |
Inline Src Code Scoring
Score CASL source code directly (no casmodel):
sas-score-cas-program-score({ src, scenario, output, limit })
src— CASL/CAS program code to execute verbatimscenario— input parameters as string ("x=1, y=2") or object ({ x: 1, y: 2 })output— optional CAS table name to return in responselimit— max rows to return (default 100)
CAS Model Table Scoring
Score using a persisted CAS model table:
sas-score-cas-program-score({ casmodel, name, scenario, output, limit })
casmodel— CAS model table inlib.tableform (e.g.,mylib.mymodel)name— optional model name if different from the table namescenario— input parametersoutput/limit— same as above
Routing Examples
| User says | Params |
|---|---|
"run cas program action echo" |
{ src: "action echo" } |
"execute casl action simple.summary with table=a.b" |
{ src: "action simple.summary", scenario: { table: "a.b" } } |
"score cas model mylib.abc with x=1, y=2" |
{ casmodel: "mylib.abc", scenario: "x=1, y=2" } |
"score cas model mylib.abc using model name mymodel" |
{ casmodel: "mylib.abc", name: "mymodel", scenario: ... } |
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.
- 8d ago First seen · 96 lines · 66 tokens per session scan A 98c88b1e5d3f
score-cas is a skill published in the GitHub repository sassoftware/sas-score-mcp-serverjs (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 944 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 2026-08-31.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…