Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Agent Protocol (C-Suite Coordination)

A communication protocol that defines how C-suite role agents invoke each other, prevents loops, and standardizes response formats.

AutomationIntermediate★ 24,151⑂ 3,405AI score 7/10Last updated: Aug 9, 2026

What it does

Defines the inter-agent protocol for a team of role-playing executive agents (CEO, CFO, CTO, CHRO, CISO, GC, and more) so cross-functional analysis doesn't devolve into infinite loops or fake consensus.

  • [INVOKE:role|question] syntax plus a strict [RESPONSE:role] template (key finding → supporting data → confidence → caveat)
  • Hard loop-prevention rules: no self-invocation, max chain depth of 2, no circular calls, explicit chain tracking
  • Isolation rules for board-meeting phases (independent analysis phase forbids invocations to avoid anchoring and groupthink)
  • A four-step quality loop: self-verify → peer-verify → critic pre-screen → post-decision course correction
  • A single founder-facing output standard (bottom line first, max 5 bullets, actions with owner and deadline)
  • Canonical two-layer decision memory layout under ~/.claude/decisions/

Who it's for

  • Founders and consultants running multi-role executive simulations with agents
  • Anyone whose sub-agents have gotten stuck calling each other in circles
  • Teams that want sources, assumptions, and confidence levels enforced on every agent output

Examples

  1. "What happens to runway if we hire 5 engineers in Q3?" → CRO invokes CFO for burn rate, stops at depth 2, and marks the rest with [ASSUMPTION: ...].
  2. Board meeting simulation: in Phase 2 every role analyzes independently with no invocations; in Phase 3 the critic may reference but not query other roles.
  3. CFO projects 14 months of runway while CRO implies 18+ → the protocol surfaces [CONFLICT: ...] and forces a resolution mode (conservative, confidence-weighted, or escalate to the human).

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .gemini/skills/agent-protocol folder from the GitHub repo alirezarezvani/claude-skills into my ~/.claude/skills/agent-protocol/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/alirezarezvani/claude-skills.git /tmp/claude-skills && mkdir -p ~/.claude/skills && cp -r /tmp/claude-skills/.gemini/skills/agent-protocol ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/alirezarezvani/claude-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy this skill: cp -r claude-skills/.gemini/skills/agent-protocol ~/.claude/skills/
  5. Verify that ~/.claude/skills/agent-protocol/SKILL.md exists.
  6. For full value, also copy the related C-suite skills from the same repo (board-meeting, decision-logger, chief-of-staff, and the role advisors).
  7. Restart Claude Code and try a prompt like "Have the CFO and CTO jointly assess our Q3 hiring plan" to see the protocol in action.
View source on GitHub ↗License: MIT