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-boost-reviewgit 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-boost-review)<a href="https://agentmods.dev/skills/sw-in-beta/simon-skills/simon-boost-review"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-boost-review/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-boost-review"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-boost-review.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 | $0.00154 | $0.01909 |
| Opus 5 | $0.00077 | $0.00955 |
| Sonnet 5 | $0.00031 | $0.00382 |
| Haiku 4.5 | $0.00015 | $0.00191 |
Grade B, and why
simon-boost-review 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 10d 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.
> **Reference Loading**: 분석 대상 목록은 `~/.claude/skills/_shared/boost-target-skills.md`를 읽는다 — 실제 대상은 `ls ~/.claude/skills/simon*/SKILL.md` 스캔이 SSoT다 (simon-boost/auto-boost와 동일, 수동 목록 drift 방지). How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
simon-boost-review
simon-boost-capture로 축적된 스킬 개선 인사이트를 리뷰하고 적용하는 스킬.
캡처 단계에서 이미 분석이 완료된 인사이트를 사용자와 함께 검토하고, 승인된 개선안을 실제 스킬 파일에 반영한다. 전문가 패널 분석 없이, 이미 분석된 리포트 기반으로 빠르게 진행한다.
Expert Panel: 이 스킬은 전문가 패널을 직접 실행하지 않는다 (capture 단계에서 분석 완료). 패널 구성 상세는
~/.claude/skills/_shared/expert-panel-boost.md참조.
Insights 경로
~/.claude/boost/insights/ — simon-boost-capture와 공유하는 경로.
Insight 파일 형식
capture가 생성하는 리포트의 구조. 이 형식을 기준으로 파싱한다.
파일명: {YYYY-MM-DD}-{HHmm}-{slug}.md
Frontmatter (필터링·대시보드에 사용):
---
status: pending # pending | applied | rejected | deferred
severity: HIGH # CRITICAL | HIGH | MEDIUM | LOW
target_skill: simon # 대상 스킬 이름
target_section: Step 5 # 대상 단계/섹션
captured_at: 2025-01-15T14:30:00+09:00
---
severity 판정 기준: ~/.claude/skills/_shared/expert-panel-boost.md의 Proposal Severity Rubric을 따른다.
본문 섹션:
| 섹션 | 용도 |
|---|---|
# {제목} |
대시보드 표시용 제목 |
## 관찰 |
세션에서 발생한 구체적 상황 |
## 현재 스킬 코드 분석 |
문제가 되는 스킬 코드, 파일 경로·섹션 명시 |
## 개선 제안 |
before/after 포함 구체적 변경안 |
## 기대 효과 |
변경 시 예상되는 개선 |
## 영향 범위 |
다른 스킬·워크플로에 미치는 영향 |
Step별 참조 방식:
- Step 1 (로딩): frontmatter의
status로 필터링 - Step 2 (대시보드): frontmatter의
severity,target_skill,captured_at+ 본문# 제목 - Step 3 (리뷰): 본문 전체 (
관찰~영향 범위) - Step 4 (적용):
현재 스킬 코드 분석의 파일 경로 +개선 제안의 변경안
Target Skills
Reference Loading: 분석 대상 목록은
~/.claude/skills/_shared/boost-target-skills.md를 읽는다 — 실제 대상은ls ~/.claude/skills/simon*/SKILL.md스캔이 SSoT다 (simon-boost/auto-boost와 동일, 수동 목록 drift 방지).
references/ 디렉토리의 하위 파일들과 _shared/*.md도 대상에 포함.
Step 1: Pending Insights 로딩
~/.claude/boost/insights/에서 리포트를 읽는다.
status: pending우선status: deferred도 포함 (이전에 보류한 것)status: applied/rejected는 제외
인사이트가 없으면:
처리할 인사이트가 없습니다. 작업 중 개선점을 발견하면 simon-boost-capture로 기록해주세요.
Step 2: 인사이트 대시보드
전체 현황을 제시:
## Pending Insights ({N}건)
| # | 심각도 | 대상 스킬 | 제목 | 캡처일 |
|---|--------|-----------|------|--------|
| 1 | HIGH | simon | Step 5 테스트 탐색 실패 반복 | 2025-01-15 |
| 2 | MEDIUM | simon-pm | 태스크 분해 기준 모호 | 2025-01-14 |
어떤 인사이트부터 검토할까요? (전체 순서대로 / 번호 선택 / 심각도 높은 순)
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.
- 10d ago First seen · 180 lines · 154 tokens per session scan B 666a5c6ebb7f
simon-boost-review is a skill published in the GitHub repository SW-in-beta/simon-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 1,909 once invoked, about $0.0008 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
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…