Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Inter-Agent Protocol (C-Suite Teams)

Defines invocation syntax, loop-prevention rules, and response formats so C-suite role agents can query each other without spiraling.

AutomationIntermediate★ 26,330⑂ 3,706AI score 7/10Last updated: Aug 30, 2026

What it does

  • Standardizes cross-agent calls with [INVOKE:role|question] and a structured [RESPONSE:role] block (key finding, supporting data, confidence, caveat).
  • Enforces hard loop-prevention rules: no self-invocation, max chain depth 2, no circular calls, explicit [CHAIN: ...] tracking with a [BLOCKED: ...] fallback.
  • Applies isolation rules for board-meeting phases — independent analysis phase forbids invocations, critique phase allows references only.
  • Requires conflicts between agents to be surfaced as [CONFLICT: ...] with a stated resolution strategy (conservative, probabilistic, or escalate).
  • Adds a 4-step internal quality loop (self-verify → peer-verify → critic pre-screen → post-decision review) plus one unified founder-facing output format.
  • Pins decision memory to a two-layer layout under ~/.claude/decisions/ (raw transcripts vs. approved records).

Who it's for

  • Founders and operators simulating executive decision-making with multiple C-level role agents.
  • Anyone building multi-agent setups that burned tokens on circular or redundant agent calls.
  • Users of this repo's companion C-suite advisor skills and /cs:* commands.

Examples

  1. "What if we hire 5 engineers in Q3?" — CRO invokes CFO for runway impact, stops at depth 2, and states remaining gaps as [ASSUMPTION: ...].
  2. During board-meeting Phase 2, each role forms an independent view with no invocations, avoiding anchoring and groupthink.
  3. CFO projects a 14-month runway while CRO implies 18+ — the protocol forces a [CONFLICT: ...] flag and a conservative default instead of a silent pick.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/alirezarezvani/claude-skills/HEAD/.gemini/skills/agent-protocol/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

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 && mkdir -p ~/.claude/skills && cp -r claude-skills/.gemini/skills/agent-protocol ~/.claude/skills/

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

  1. Open a terminal and clone the repo: git clone https://github.com/alirezarezvani/claude-skills.git
  2. Create the skills directory if needed: mkdir -p ~/.claude/skills
  3. Copy this skill: cp -r claude-skills/.gemini/skills/agent-protocol ~/.claude/skills/
  4. Also copy the companion C-suite skills (cfo, cto, board-meeting, decision-logger, etc.) — the protocol has limited value on its own.
  5. Restart Claude Code and test with a prompt like "Using the inter-agent protocol, synthesize CFO and CTO views on this hiring decision."
  6. Pre-create ~/.claude/decisions/raw and ~/.claude/decisions/approved so decision logging doesn't fail on missing paths.
View source on GitHub ↗License: MIT