agent-launcher-orchest…
Use when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an…
Use when choosing or setting up how the company runs: EOS, Scaling Up or OKRs, accountability chart, scorecard, meeting rhythm, quarterly rocks.
Claude Code
$ npx -y skills add alirezarezvani/claude-skills --skill company-os --agent claude-code
Codex
$ npx skills add alirezarezvani/claude-skills --skill company-os -a codex -y
Cursor
$ npx skills add alirezarezvani/claude-skills --skill company-os -a cursor -y
Gemini CLI
$ npx skills add alirezarezvani/claude-skills --skill company-os -a gemini-cli -y
GitHub Copilot
$ npx skills add alirezarezvani/claude-skills --skill company-os -a github-copilot -y
OpenCode
$ npx skills add alirezarezvani/claude-skills --skill company-os -a opencode -y
Windsurf
$ npx skills add alirezarezvani/claude-skills --skill company-os -a windsurf -y
name: "company-os" description: "Use when choosing or setting up how the company runs: EOS, Scaling Up or OKRs, accountability chart, scorecard, meeting rhythm, quarterly rocks." license: MIT metadata: version: 1.0.0 author: Alireza Rezvani category: c-level domain: company-operations updated: 2026-03-05 frameworks: os-comparison, implementation-guide
The operating system is the collection of tools, rhythms, and agreements that determine how the company functions. Every company has one — most just don't know what it is. Making it explicit makes it improvable.
operating system, EOS, Entrepreneurial Operating System, Scaling Up, Rockefeller Habits, OKR, Holacracy, L10 meeting, rocks, scorecard, accountability chart, issues list, IDS, meeting pulse, quarterly planning, weekly scorecard, management framework, company rhythm, traction, Gino Wickman, Verne Harnish
Most operational dysfunction isn't a people problem — it's a system problem. When:
Fix the system. The people will operate better inside it.
Every effective operating system has these six, regardless of which framework you choose:
Not an org chart. An accountability chart answers: "Who owns this outcome?"
**Key distinction:** One person owns each function. Multiple people may work in it. Ownership means the buck stops with one person.
**Structure:**
CEO
├── Sales (CRO/VP Sales)
│ ├── Inbound pipeline
│ └── Outbound pipeline
├── Product & Engineering (CTO/CPO)
│ ├── Product roadmap
│ └── Engineering delivery
├── Operations (COO)
│ ├── Customer success
│ └── Finance & Legal
└── People (CHRO/VP People)
├── Recruiting
└── People operations**Rules:**
**Build it in a workshop:** 1. List all functions the company performs 2. Assign one owner per function — no exceptions 3. Identify gaps (functions nobody owns) and overlaps (functions two people think they own) 4. Publish it. Update it when something changes.
Weekly metrics that tell you if the company is on track. Not monthly. Not quarterly. Weekly.
**Rules:**
**Example scorecard structure:**
| Metric | Owner | Target | This Week | Status | |--------|-------|--------|-----------|--------| | New MRR | CRO | €50K | €43K | 🔴 | | Churn | CS Lead | < 1% | 0.8% | 🟢 | | Active users | CPO | 2,000 | 2,150 | 🟢 | | Deployments | CTO | 3/week | 3 | 🟢 | | Open critical bugs | CTO | 0 | 2 | 🔴 | | Runway | CFO | > 18mo | 16mo | 🟡 |
**Anti-pattern:** Measuring everything. If you track 40 KPIs, you're watching, not managing.
The meeting rhythm that drives the company. Not optional — the pulse is what keeps the company alive.
**The full rhythm:**
| Meeting | Frequency | Duration | Who | Purpose | |---------|-----------|----------|-----|---------| | Daily standup | Daily | 15 min | Each team | Blockers only | | L10 / Leadership sync | Weekly | 90 min | Leadership team | Scorecard + issues | | Department review | Monthly | 60 min | Dept + leadership | OKR progress | | Quarterly planning | Quarterly | 1–2 days | Leadership | Set rocks, review strategy | | Annual planning | Annual | 2–3 days | Leadership | 1-year + 3-year vision |
**The L10 meeting (Weekly Leadership Sync):** Named for the goal of each meeting being a 10/10. Fixed agenda: 1. Good news (5 min) — personal + business 2. Scorecard review (5 min) — flag red items only 3. Rock review (5 min) — on/off track for each rock 4. Customer/employee headlines (5 min) 5. Issues list (60 min) — IDS (see below) 6. To-dos review (5 min) — last week's commitments 7. Conclude (5 min) — rate the meeting 1–10, what would make it a 10 next time
The core problem-solving loop. Maximum 15 minutes per issue.
**IDS: Identify, Discuss, Solve**
**Anti-patterns:**
**The Issues List:** A running, prioritized list of all unresolved issues. Owned by the leadership team. Reviewed and pruned weekly. If an issue has been on the list for 3+ meetings and hasn't been discussed, it's either not a real issue or it's too scary to address — both deserve attention.
Rocks are the 3–7 most important things each person must accomplish in the next 90 days. They're not the job description — they're the things that move the company forward.
**Why 90 days?** Long enough for meaningful progress. Short enough to stay real.
**Rock rules:**
411 production-ready skills for Claude Code and 12 other coding agents, covering engineering, product, marketing, compliance, finance and the C-suite. We test whether each skill loads when you ask in plain words, and publish the results.
Use when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an…
Use when a launched managed agent needs grading against a rubric and improving ('grade my agent', 'is it good enough'). Builds…
Use when someone has an agent idea to scope before launch ('help me scope an agent'). Interviews them about the one job and…
Use when a graded managed agent should run on a schedule, on an event trigger or on demand ('run it every morning'). Validates…
Use when a managed-agent build sheet is ready to launch ('launch it', 'deploy the agent'). Generates and validates API payloads…
Use when closing out a launched managed agent ('wrap up', 'what do I own now'). Inventories primitives with…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI…