memradar: Skill for Claude Code

.claude/skills/memtest/SKILL.md

memtest is a skill for Claude Code from on1659/memradar. It costs 97 tokens per session (725 once invoked), scanned A, original, MIT.

A test skill for evaluating how an AI system performs different roles and producing an HTML report.

In plain words
What is it for?
Use it to run evaluation tests, compare results by category and difficulty, and open the generated report.
Why use it?
It turns a collection of role-evaluation samples into accuracy results and makes the findings easier to inspect.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is on1659/memradar's own configuration. It tells Claude Code how to work on memradar itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything memradar configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/radar/Work/memradar.

Reuse

Borrowing it

Nothing to install: this file belongs to on1659/memradar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/on1659/memradar/master/.claude/skills/memtest/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/on1659/memradar

Made for: Claude Code.

Wrote 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.

agentmods badge for memtest

README.md
[![agentmods](https://agentmods.dev/badge/skills/on1659/memradar/memtest.svg)](https://agentmods.dev/skills/on1659/memradar/memtest)
Your own site
<a href="https://agentmods.dev/skills/on1659/memradar/memtest"><img src="https://agentmods.dev/badge/skills/on1659/memradar/memtest.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 725 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.00725
Opus 5 $0.00048 $0.00362
Sonnet 5 $0.00019 $0.00145
Haiku 4.5 $0.00010 $0.00072

Measured 5d ago against content hash 7e9cecd583c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

memtest 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 5d 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.

.claude/skills/memtest/SKILL.md · 86 lines

What it actually says

memtest — AI 역할 평가 실행 스킬

즉시 실행 (Claude에게 지시)

이 스킬이 호출되면 반드시 아래 단계를 순서대로 실행해라:

Step 1: 테스트 스크립트 실행

Bash 도구로 다음 명령을 실행:

cd /Users/radar/Work/memradar && npx tsx scripts/test-eval-and-report.mts

Step 2: 결과 확인

스크립트 출력에서 정확도 수치를 확인하고 사용자에게 요약 보고:

  • 전체 정확도
  • 카테고리별 정확도 (pure/mixed/ambiguous/consistency)
  • 난이도별 정확도 (easy/normal/hard)

Step 3: HTML 리포트 열기

Bash 도구로 리포트 파일을 브라우저에서 열기:

open /Users/radar/Work/memradar/docs/eval-report.html

Step 4: 사용자에게 최종 보고

다음 형식으로 짧게 보고:

✅ 테스트 완료

📊 정확도: X.X% (N/총합)
📄 리포트: docs/eval-report.html (브라우저에서 열림)

주요 발견:
- [카테고리/난이도별 간단 요약]
- [개선 포인트 1-2개]

관련 파일

  • 실행 스크립트: scripts/test-eval-and-report.mts
  • 분류 로직: src/lib/usageProfile.ts
  • 샘플 디렉토리: tests/fixtures/role-eval-samples/ (218개)
  • 출력 HTML: docs/eval-report.html
  • 출력 JSON: docs/eval-results.json
  • 출력 마크다운: docs/AI-ROLE-EVAL-RESULTS.md

에러 처리

  • 샘플 파일 없음: tests/fixtures/role-eval-samples/ 디렉토리 확인 지시
  • tsx 에러: scripts/test-eval-and-report.mts 파일 존재 확인
  • HTML 생성 실패: 에러 메시지 그대로 보고

중요 제약

  • 이 스킬은 스크립트를 실행하는 역할만 한다
  • 코드를 수정하지 마라 (읽기 전용)
  • analyzeUsageTopCategories() 로직을 변경하지 마라
  • 샘플 JSON 파일을 수정하지 마라
Changes

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.

  1. 5d ago First seen · 86 lines · 97 tokens per session scan A 7e9cecd583c7

Subscribe to this mod's changes

memtest is a skill published in the GitHub repository on1659/memradar (11 stars, last pushed 6d ago), licensed MIT. It adds 97 tokens to every session and 725 once invoked, about $0.0005 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 2026-09-02.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens