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 SW-in-beta/simon-skills --skill simon-healthcheckgit clone --depth 1 https://github.com/SW-in-beta/simon-skillsWrote 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/sw-in-beta/simon-skills/simon-healthcheck)<a href="https://agentmods.dev/skills/sw-in-beta/simon-skills/simon-healthcheck"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-healthcheck/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/sw-in-beta/simon-skills/simon-healthcheck"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-healthcheck.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 | $0.00105 | $0.02579 |
| Opus 5 | $0.00053 | $0.01290 |
| Sonnet 5 | $0.00021 | $0.00516 |
| Haiku 4.5 | $0.00011 | $0.00258 |
Grade B, and why
simon-healthcheck scanned grade B with 1 finding 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls -d ~/.claude/skills/simon*/ ~/.claude/skills/simon-company/ ~/.claude/skills/simon-presenter/ ~/.claude/skills/_shared/ 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
simon-healthcheck
simon 패밀리 전체의 구조적 건강 상태를 검증하고 대시보드로 출력한다.
Instructions
Step 1: 대상 스킬 탐색
~/.claude/skills/ 하위에서 simon 패밀리 스킬을 탐색한다:
ls -d ~/.claude/skills/simon*/ ~/.claude/skills/simon-company/ ~/.claude/skills/simon-presenter/ ~/.claude/skills/_shared/ 2>/dev/null
Step 2: 스킬별 검증
각 스킬 디렉토리에 대해 아래 항목을 검증한다:
2-A: SKILL.md 기본 검증
- 존재 여부: SKILL.md 파일이 있는가
- YAML frontmatter: name, description 필드가 존재하는가
- 줄 수: 500줄 이내인가 (경계: 450-500줄이면 WARNING)
- description 트리거: "Use when:" 패턴이 포함되어 있는가
- 라우터 Registry 대조 (전역 1회 — 스킬별 총점 아닌 "전역 검증" 섹션에 보고):
ls ~/.claude/skills/simon*/SKILL.md결과(SKILL.md 없는 workspace 디렉토리 제외)와 simon/SKILL.md Registry 표의 스킬명을 대조 — 스킬이 있는데 Registry에 없으면 FAIL (라우터 도달 불가 스킬) - CLAUDE.md 참조 실존 (전역 1회 — "전역 검증" 섹션에 보고):
~/.claude/CLAUDE.md가 언급하는 simon-* 스킬명이 실제 디렉토리에 존재하는지 대조 — 유령 참조 발견 시 FAIL
2-B: Reference 검증
- 참조 경로: SKILL.md의 실제 Markdown 링크
[text](references/file.md)또는 명시적 read 지시문(read references/file.md)에서 참조하는 경로가 실제로 존재하는가. 오탐 제외 규칙: ① 코드블록(```) 내부의 예시 경로, ② 타 스킬 절대경로(~/.claude/skills/다른스킬/references/...), ③ 예시 텍스트 내 언급 — 이 세 가지는 검증 대상에서 제외한다. - 300줄 초과 TOC: 300줄 초과 reference 파일에 TOC(
## 목차또는## Table of Contents)가 있는가 - 미참조 파일: references/ 디렉토리에 있지만 SKILL.md에서 Markdown 링크로 한 번도 참조하지 않는 파일이 있는가
- 인라인 프롬프트 길이: SKILL.md 본문 내 subagent spawn 프롬프트 블록이 20줄을 초과하면 references/ 분리 권장 (WARN)
2-C: Script/Asset 경로 검증
SKILL.md와 references/*.md에서 참조하는 스크립트·자산 경로가 실제 존재하는지 검증한다.
추출 대상 패턴:
- 절대 경로:
~/.claude/skills/*/scripts/*.sh,~/.claude/skills/*/assets/*등 - 상대 경로:
scripts/foo.sh,workflow/scripts/bar.sh,assets/template.html등 - bash/python 실행문:
bash scripts/...,python3 scripts/...,nohup python3 ~/.claude/skills/...
오탐 제외 규칙 (2-B와 동일):
① 코드블록(```) 내부에서 패턴 예시로만 사용된 경로 (실제 실행 커맨드는 코드블록 안이라도 검증 대상)
② 예시 텍스트 내 언급 ("예: scripts/deploy/" 같은 설명용)
검증 항목:
- 경로 존재: 참조된 스크립트/자산 파일이 실제로 존재하는가
- 실행 권한:
.sh파일이 실행 권한(chmod +x)을 갖고 있는가 - 미참조 스크립트: scripts/ 디렉토리에 있지만 SKILL.md나 references/에서 한 번도 참조하지 않는 파일이 있는가
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 · 154 lines · 105 tokens per session scan B d55bc1b79d7c
simon-healthcheck is a skill published in the GitHub repository SW-in-beta/simon-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 2,579 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.