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-companygit 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-company)<a href="https://agentmods.dev/skills/sw-in-beta/simon-skills/simon-company"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-company/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-company"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-company.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 | $0.00183 | $0.05173 |
| Opus 5 | $0.00092 | $0.02586 |
| Sonnet 5 | $0.00037 | $0.01035 |
| Haiku 4.5 | $0.00018 | $0.00517 |
Grade A, and why
simon-company 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 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.
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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
simon-company
풀 라이프사이클 소프트웨어 회사 스킬. 전문 팀들이 기획부터 배포·운영까지 협업하여 프로덕션 레벨의 서비스를 완성합니다.
핵심 철학:
- "모든 산출물은 3번 검증한다. 리드는 깐깐하다. 통과하지 못하면 재작업한다."
- "작게 만들고, 빠르게 검증하고, 피드백을 반영한다." (Agile Sprint Cycle)
- "Spec이 곧 기준이다. 모든 구현은 Spec에서 시작하고 Spec으로 검증한다." (Spec-Driven Development)
Progressive Disclosure: 이 파일은 오케스트레이션 계층(WHAT + WHEN)이다. 각 Phase의 HOW는
references/하위의 레퍼런스 파일에 정의되어 있다. 각 Phase 진입 시 해당 레퍼런스만 읽고, 모든 레퍼런스를 미리 로드하지 않는다.
Scope Guard
이 스킬은 다중 팀 협업이 필요한 대규모 프로젝트를 위한 것입니다.
| 기준 | simon-company | simon-pm으로 리다이렉트 |
|---|---|---|
| 필요 팀 수 | 3개 이상 (예: BE+FE+DevOps) | 1-2개 (BE만, 또는 BE+FE) |
| 인프라 필요 | CI/CD, 배포, 모니터링 필요 | 로컬 실행으로 충분 |
| 디자인 필요 | UI/UX 설계 필요 | API나 CLI 위주 |
| 예상 Feature 수 | 5개 이상 | 3-4개 |
리다이렉트 시: 왜 simon-company가 과한지 설명하고, simon-pm 또는 simon 사용을 제안한다. 사용자가 그래도 원하면 진행한다.
Instructions
이 스킬은 8단계 파이프라인으로 동작합니다. 모든 단계에 **Triple Review Protocol(TRP)**이 적용됩니다.
| Phase | 이름 | 핵심 팀 | 산출물 | TRP 적용 |
|---|---|---|---|---|
| 0 | Company Setup | CEO | roster.json, state.json | - |
| 1 | Discovery & Spec | PM, Design | spec.md, constitution.md, story-map.md | O |
| 2 | Architecture & Design Sprint | CTO, Design, DBA, DevOps | architecture.md, design/, db-schema.md | O |
| 3 | Sprint Planning & Backlog | CTO, All Leads | contracts/, backlog.json, sprint-plan.md | O |
| 4 | Sprint Execution (Iterative) | FE, BE, ML, DBA, DevOps | 구현 코드 (Sprint 단위 반복) | O (Sprint별) |
| 5 | QA & Integration | QA, Security | test-report.md, security-audit.md | O |
| 6 | Deployment & Operations | DevOps, QA | CI/CD, Dockerfile, monitoring | O |
| 7 | Delivery & Handoff | CEO, All Leads | final-report.md, PR | O |
Dependencies: simon-pm + simon-dev/simon-grind 스킬을 실행 에이전트로, Agent Team (TeamCreate/SendMessage)을 Sprint 조율에 사용합니다.
Cross-Cutting Protocols
What ships with it
13 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.
- evals/evals.json 5.5 KB
- references/contract-templates.md 6.3 KB
- references/contracts-execution.md 23 KB
- references/cross-cutting-protocols.md 9.0 KB
- references/discovery-interview.md 5.0 KB
- references/operational-protocols.md 13 KB
- references/phase-5-qa.md 5.9 KB
- references/phase-6-deployment.md 7.4 KB
- references/phase-7-delivery.md 2.2 KB
- references/planning-design.md 17 KB
- references/quality-gates.md 20 KB
- references/sprint-execution-templates.md 8.4 KB
- references/team-roster.md 9.5 KB
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 · 363 lines · 183 tokens per session scan A f0d0e38906fb
simon-company is a skill published in the GitHub repository SW-in-beta/simon-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 183 tokens to every session and 5,173 once invoked, about $0.0009 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…
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…