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-boostgit 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)<a href="https://agentmods.dev/skills/sw-in-beta/simon-skills/simon-boost"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-boost/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"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-boost.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 | $0.00168 | $0.03853 |
| Opus 5 | $0.00084 | $0.01927 |
| Sonnet 5 | $0.00034 | $0.00771 |
| Haiku 4.5 | $0.00017 | $0.00385 |
Grade B, and why
simon-boost 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 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.
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 (SKILL.md 없는 workspace 디렉토리 제외, 수동 목록 drift 방지). How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
simon-boost
외부 자료에서 인사이트를 추출하여 simon 계열 스킬을 강화하는 스킬.
링크 하나가 simon 패밀리 전체의 부스터가 됩니다.
Instructions
You are executing simon-boost. 사용자가 제공한 링크의 내용을 전문가 패널이 분석하고, simon 계열 스킬들의 구체적인 개선안을 도출한 뒤, 사용자 확인 후 적용합니다.
Target Skills
Reference Loading: 분석 대상 목록은
~/.claude/skills/_shared/boost-target-skills.md를 읽는다 — 실제 대상은ls ~/.claude/skills/simon*/SKILL.md스캔이 SSoT다 (SKILL.md 없는 workspace 디렉토리 제외, 수동 목록 drift 방지).
references/ 디렉토리의 하위 파일들과 _shared/*.md도 분석 대상에 포함.
Step 0: Input Collection
0-A: 링크 수집
사용자가 이미 링크를 제공했으면 바로 진행. 아직이면 AskUserQuestion:
분석할 링크를 알려주세요. (블로그, GitHub, 논문, 아티클 등 모두 가능)
여러 링크도 가능 — 각각 분석 후 통합.
0-B: 관심사 확인 (선택)
사용자가 특별히 관심 있는 영역이 있는지 확인:
특별히 관심 있는 개선 영역이 있나요? (없으면 전방위 분석합니다)
- 워크플로 구조 (단계 추가/제거/순서)
- 프롬프트/지시문 품질
- 새로운 기법/도구 도입
- 에러 처리/안전성
- 전부 다
사용자가 "전부" 또는 별다른 언급이 없으면 전방위 분석.
Step 1: Content Extraction
1-A: 링크 내용 가져오기
WebFetch로 링크 내용을 가져온다.
- 웹페이지: WebFetch로 본문 추출
- GitHub 레포: 주요 파일들 (README, SKILL.md, workflow 관련 파일) 탐색
- PDF/논문: 가능한 범위 내에서 내용 추출
1-B: 핵심 내용 정리
가져온 내용에서 simon 스킬 개선과 관련될 수 있는 핵심 내용을 정리:
## Source Summary
- **제목**: ...
- **유형**: 블로그 / GitHub / 논문 / 기타
- **핵심 주제**: ...
- **주요 아이디어** (bullet points):
- ...
- **관련 기법/패턴/도구**: ...
Save: .claude/boost/source-summary-{slug}.md
Step 2: Target Skill Loading (선택적)
분석 전에 대상 스킬들의 현재 상태를 파악하되, 컨텍스트 효율을 위해 선택적으로 로딩한다.
2-A: 관련 스킬 식별
Step 1의 자료 요약에서 가장 관련성이 높은 스킬 1-3개를 식별한다:
- 워크플로 구조 관련 → simon (코어)
- 재시도/복구 관련 → simon-grind
- 프로젝트 관리 관련 → simon-pm
- 분석/보고서 관련 → simon-report
- 세션 관리 관련 → simon-sessions
2-B: 단계적 로딩
- 식별된 스킬의 SKILL.md만 먼저 읽기 (references는 아직 읽지 않음)
- SKILL.md에서 개선 대상 영역을 좁힌 후, 해당 references 파일만 추가 로딩
- 나머지 스킬은 Step 3 전문가 패널에서 필요 시 개별 전문가가 직접 읽기
예시:
- 자료가 "에러 복구 전략"에 관한 것이면:
- simon-dev SKILL.md + references/error-resilience.md
- simon-grind SKILL.md + references/grind-error-resilience.md
- 나머지 스킬은 SKILL.md description만 참조
이 방식으로 컨텍스트 소비를 1/3 이하로 줄이면서도 정확한 분석이 가능하다.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 303 lines · 168 tokens per session scan B 78b07f374b2a
simon-boost is a skill published in the GitHub repository SW-in-beta/simon-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 168 tokens to every session and 3,853 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…
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…