C level agents

Skill timdevai/proteus/skills/community/from-alireza/c-level-advisor/c-level-agents/skills/c-level-agents

Always-on multi-agent AI workstation for Claude Code. 142 specialist agents (ML, security, K8s, backend, frontend) · 366 curated skills · 200+ prompt templates · auto prompt-matcher · auto skill-matcher · MCP support · token router cuts Anthropic bill 6x via Kimi/Haiku/Ollama. LiteLLM · BYOK · MIT + Apache. One-line install.

Install

npx -y skills add timdevai/proteus --skill c-level-agents

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Founder-mode executive team. 8 cs-* C-suite agents (CFO, CMO, CRO, CPO, COO, CHRO, CISO, Chief of Staff) and 17 /cs:* slash commands for forcing-question office hours, multi-role boardroom deliberation, strategic sprint pipeline, and meta routing. Use when the founder needs a virtual executive team, when invoking /cs:* commands, or when orchestrating multi-role decisions.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.6 KB, as published. Nobody here has run it

c-level-agents — Founder-Mode Executive Team

A virtual C-suite delivered through slash commands and persona agents.

Keywords

founder mode, virtual c-suite, executive team, boardroom, office hours, cfo review, cmo review, strategic sprint, decision logging, cross-model consensus, persona agents, chief of staff, forcing questions

What This Plugin Provides

8 cs-* Agents (in `agents/`)

Each agent wraps an existing c-level skill and adds:

A distinct cognitive voice (numerate skeptic, narrative-first, etc.)
Forcing questions specific to the role
Workflow orchestration tied to skill Python tools
Output template: Bottom Line → What → Why → How to Act → Your Decision

See ../references/persona-voices.md for voice specs.

17 /cs:* Slash Commands (in `skills/`)

Forcing-question office hours (8):

/cs:office-hours — YC-style 6-question intake
/cs:cfo-review — unit economics, runway, dilution
/cs:cmo-review — ICP, CAC payback, positioning
/cs:cpo-review — RICE, JTBD, North Star, PMF
/cs:cro-review — pipeline coverage, win rate, NRR
/cs:cto-review — architecture risk, scaling cliff
/cs:ciso-review — threat model, blast radius, compliance
/cs:gc-review — contracts, IP, regulatory, term sheets

Strategic sprint pipeline (5):

/cs:brief → /cs:boardroom → /cs:decide → /cs:execute → /cs:post-mortem

Meta + safety (4):

/cs:founder-mode — auto-routes to the right C-role
/cs:onboard — founder interview → company-context.md
/cs:cross-eval — multi-model consensus
/cs:freeze — cooldown lock on a decision

Quick Start

/cs:onboard                          # populate company context first
/cs:office-hours "should we hire a VP Sales?"
/cs:founder-mode "runway pressure"   # auto-routes to CFO
/cs:boardroom briefs/pricing-v3.md   # full panel

Architecture

User question
   │
   ├─ Single-role? → cs-{role}-advisor agent
   │                     ↓
   │                  /cs:{role}-review command (forcing Qs)
   │                     ↓
   │                  Skill tools + references
   │                     ↓
   │                  Bottom Line + Memo
   │
   └─ Multi-role?  → /cs:boardroom
                        ↓
                     6-phase deliberation (Phase 2 isolation)
                        ↓
                     /cs:decide → decision-logger (two-layer memory)
                        ↓
                     /cs:execute → 90-day plan

Integration Points

Existing 28 c-level skills — wrapped, not replaced
decision-logger — every /cs:decide writes here
chief-of-staff — routing layer the agent orchestrates
board-meeting — protocol the /cs:boardroom command runs
llm-wiki — optional persistent memory bridge (see ../references/llm-wiki-bridge.md)
executive-mentor — adversarial /em:* commands stack cleanly on top

Design Principles

Voice is bookended, analysis is neutral.
Artifacts over chat. Every command produces a Markdown artifact the next command consumes.
Phase 2 isolation in boardroom. Independent thinking before cross-examination.
Graceful degradation. /cs:cross-eval falls back to Claude-only.
No paid dependencies. All Python tools are stdlib-only.

References

Version: 1.0.0 Last Updated: 2026-05-12 Status: Production Ready