agent-company: Skill for Claude Code

.claude/skills/company-setup/SKILL.md

company-setup is a skill for Claude Code from TOKTOKHAN-DEV/agent-company. It costs 78 tokens per session (2,614 once invoked), scanned A, original, MIT.

A project setup helper that checks and installs the exact dependencies a code project needs, then applies the chosen company template. It is meant for projects whose files are assembled from a shared core and a selected template.

In plain words
What is it for?
Use it after cloning a project, changing your environment, or when something no longer works. It helps choose a template, install dependencies, and optionally ask whether to follow the GitHub organisation or star its repository.
Why use it?
It removes guesswork when preparing a newly cloned project or fixing an environment that has changed. The checks run in a fixed order so setup results are consistent.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions Codex.

This is TOKTOKHAN-DEV/agent-company's own configuration. It tells Claude Code how to work on agent-company 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 agent-company configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/company-setup.sh --no-community-prompt --template <id>.

Reuse

Borrowing it

Nothing to install: this file belongs to TOKTOKHAN-DEV/agent-company. 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/TOKTOKHAN-DEV/agent-company/main/.claude/skills/company-setup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/TOKTOKHAN-DEV/agent-company

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 company-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/company-setup/github.svg)](https://agentmods.dev/skills/toktokhan-dev/agent-company/company-setup)
Your own site
<a href="https://agentmods.dev/skills/toktokhan-dev/agent-company/company-setup"><img src="https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/company-setup/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.

agentmods 80×15 button for company-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/toktokhan-dev/agent-company/company-setup"><img src="https://agentmods.dev/badge/skills/toktokhan-dev/agent-company/company-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,614 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00078 $0.02614
Opus 5 $0.00039 $0.01307
Sonnet 5 $0.00016 $0.00523
Haiku 4.5 $0.00008 $0.00261

Measured 10d ago against content hash 2cf846a4bf79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

company-setup 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 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.

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/company-setup/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/company-setup

프로젝트를 돌릴 수 있는 상태로 만든다.

핵심 원칙

당신이 직접 검사하지 마세요. 이 스킬의 존재 이유는 결정성입니다. 셸 스크립트가 항상 같은 순서로 같은 검사를 수행하고, 당신은 결과를 해석해 사용자에게 다음 행동을 안내합니다.

체크리스트를 모델이 매번 다르게 해석하면 "확인했습니다"가 실제로는 확인하지 않은 상태를 의미하게 됩니다.

순서

  1. 템플릿을 정합니다 — 스크립트를 돌리기 전에.
  2. 스크립트를 한 번 실행합니다.
  3. GitHub 응원을 묻습니다 — 선택.

1. 템플릿 먼저 정하기

이 저장소는 코어 + 템플릿 구조입니다. 템플릿이 apps/ · packages/ · agents/ 를 루트에 펼치므로, 무엇을 만들 회사인지 정해야 셋업이 의미 있게 끝납니다.

bash scripts/template.sh current    # 이미 적용된 것이 있는지
bash scripts/template.sh list       # 고를 수 있는 것
current 결과 당신이 할 일
none 이 아님 묻지 마세요. 이미 정해졌습니다. --template 없이 그대로 실행합니다
none + 사용자가 무엇을 만들지 이미 말함 그에 맞는 id 를 --template 로 넘깁니다
none + 모름 AskUserQuestion 으로 물어봅니다 (아래)

none 이고 무엇을 만들지 모를 때 물어볼 것: "어떤 회사를 차릴까요?"

옵션은 list 출력에서 planned 를 뺀 것들 + "나중에 고르기". 각 옵션의 설명에는 매니페스트의 summary 를 그대로 쓰세요.

planned 상태 템플릿을 제안하지 마세요. 내용물이 없어서 apply 가 거부합니다.

임의로 고르지 마세요. 템플릿은 파일을 루트에 펼치고, 갈아타면 이전 파일이 남습니다. 사용자가 "나중에"를 고르면 --template 없이 실행하고, 나중에 pnpm template apply <id> 로 할 수 있다고 알려주세요.

2. 실행

bash scripts/company-setup.sh --no-community-prompt --template <id>

정리(prune)는 셋업에 포함되어 자동으로 실행됩니다. 회사를 고른 것 자체가 의사 표시이므로 따로 묻지 않습니다. 남은 카탈로그가 필요한 특수한 경우에만 --no-prune 을 붙이세요.

--no-community-prompt항상 붙이세요. 스크립트의 텍스트 메뉴는 /dev/tty 에서 입력을 읽는데, Claude Code 의 Bash 도구에는 tty 가 없어 그 자리에서 막히거나 조용히 기본값(건너뛰기)으로 떨어집니다. 7단계는 아래 GitHub 응원 절차대로 당신이 AskUserQuestion 으로 직접 묻습니다.

같은 이유로 3단계(회사 선택)도 tty 가 없으면 건너뜁니다. 그래서 템플릿은 위에서 미리 정해 --template 로 넘기는 것입니다.

그 외 옵션은 필요할 때만 붙입니다:

옵션 언제
--yes 비대화형 환경(CI). 모든 확인을 자동 승인
--skip-install 방금 pnpm install 을 돌렸고 다시 돌릴 필요가 없을 때

스크립트가 하는 일

  1. 필수 도구 — node ≥20.11, pnpm ≥10, git. 없으면 설치 명령을 출력하고 중단.
  2. 도구 상태 — codex(선택), gh(선택), claude 상태를 알림.
  3. 회사 선택--template 이 있으면 적용. 없고 tty 도 없으면 건너뜀.
  4. 환경.env 생성, 템플릿이 요구하는 디렉터리 생성, 실행 권한 부여.
  5. 의존성pnpm install.
  6. 검증 — 구조 검사 + 타입 검사.
  7. GitHub 응원 (선택)--no-community-prompt 로 넘겼으므로 아무것도 하지 않습니다.

Read the full file on GitHub · 204 lines

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. 10d ago First seen · 204 lines · 78 tokens per session scan A 2cf846a4bf79

Subscribe to this mod's changes

company-setup is a skill published in the GitHub repository TOKTOKHAN-DEV/agent-company (77 stars, last pushed 14d ago), licensed MIT. It adds 78 tokens to every session and 2,614 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

capture-lessons

Ship and capture lessons workflow. Creates the PR, updates lessons learned, updates documentation, generates the sprint retrospective, and updates the backlog. Use at the end of a sprint cycle, or when the user says "ship", "capture", "lessons", "retro", "retrospective", "wrap up", or "done with this sprint". Also use…

rbah31/claude-code-workflow · 100 tokens

red-team

Security red team that produces executable attack scripts and a static code audit. Use this skill for any security sprint, pre-release hardening, or when code touches authentication, billing, data storage, API endpoints, or secrets. Also use when the user says "red team", "pentest", "attack surface", "security audit"…

rbah31/claude-code-workflow · 131 tokens

full-sprint

Orchestrates a complete sprint cycle autonomously. Each phase runs as a separate claude -p session for context isolation. Use when the sprint-directive.md is ready and the sprint should execute end-to-end. Also use when the user says "run a full sprint", "execute the sprint", "build everything", "autonomous sprint"…

rbah31/claude-code-workflow · 79 tokens

data-analysis

Fetch, query, and analyze project data. Use this skill when the user wants to investigate metrics, understand user behavior, debug a data issue, or answer a question that requires looking at real data. Triggers on "what happened", "why did X drop", "show me the numbers", "query", "metrics", "funnel", "cohort", "data"…

rbah31/claude-code-workflow · 119 tokens

fix

Fix phase workflow. Fixes issues identified during code review, based on the triaged review output. Use after a review phase is complete and the human has triaged the findings, or when the user says "fix", "fix the issues", "address review feedback", or "apply fixes". Also use when the user says "fix these" after…

rbah31/claude-code-workflow · 83 tokens

review

Code review workflow. Reviews the build output for quality, conventions, performance, security, and test coverage. Use after a build phase is complete, or when the user says "review", "check the code", "PR review", "quality check", or "is this good". Also use when the user wants a second opinion on code that was just…

rbah31/claude-code-workflow · 82 tokens