renatoschust-dot/gamai-skills/agent-protocol
Claude Code and agent skill by renatoschust-dot/gamai-skills
- community
Checking that the SKILL.md file is still in the repository.
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.
Install
npx vskill@latest install renatoschust-dot/gamai-skills/agent-protocolSKILL.md
The same SKILL.md was published earlier as renatoschust-dot/gamai-skills/agent-protocol.
Inter-Agent Protocol
How C-suite agents talk to each other. Rules that prevent chaos, loops, and circular reasoning.
Keywords
agent protocol, inter-agent communication, agent invocation, agent orchestration, multi-agent, c-suite coordination, agent chain, loop prevention, agent isolation, board meeting protocol
Invocation Syntax
Any agent can query another using:
Examples:
Valid roles: ceo, cfo, cro, cmo, cpo, cto, chro, coo, ciso, gc, cdo, caio, cco, vpe
| Role token | Advisor skill | |
|---|---|---|
gc | general-counsel-advisor (legal, contracts, term sheets) | |
cdo | chief-data-officer-advisor (data strategy, training-data rights) | |
caio | chief-ai-officer-advisor (AI strategy, evals, AI risk) | |
cco | chief-customer-officer-advisor (retention, customer success) | |
vpe | vpe-advisor (engineering delivery, DORA, eng hiring) |
Response Format
Invoked agents respond using this structure:
Example:
Loop Prevention (Hard Rules)
These rules are enforced unconditionally. No exceptions.
Rule 1: No Self-Invocation
An agent cannot invoke itself.
Rule 2: Maximum Depth = 2
Chains can go A→B→C. The third hop is blocked.
Rule 3: No Circular Calls
If agent A called agent B, agent B cannot call agent A in the same chain.
Rule 4: Chain Tracking
Each invocation carries its call chain. Format:
Agents check this chain before responding with another invocation.
When blocked: Return this instead of invoking:
Isolation Rules
Board Meeting Phase 2 (Independent Analysis)
NO invocations allowed. Each role forms independent views before cross-pollination.
- Reason: prevent anchoring and groupthink
- Duration: entire Phase 2 analysis period
- If an agent needs data from another role: state explicit assumption, flag it with
[ASSUMPTION: ...]
Board Meeting Phase 3 (Critic Role)
Executive Mentor can reference other roles' outputs but cannot invoke them.
- Reason: critique must be independent of new data requests
- Allowed: "The CFO's projection assumes X, which contradicts the CRO's pipeline data"
- Not allowed:
[INVOKE:cfo|...]during critique phase
Outside Board Meetings
Invocations are allowed freely, subject to loop prevention rules above.
When to Invoke vs When to Assume
Invoke when:
- The question requires domain-specific data you don't have
- An error here would materially change the recommendation
- The question is cross-functional by nature (e.g., hiring impact on both budget and capacity)
Assume when:
- The data is directionally clear and precision isn't critical
- You're in Phase 2 isolation (always assume, never invoke)
- The chain is already at depth 2
- The question is minor compared to your main analysis
When assuming, always state it:
Conflict Resolution
When two invoked agents give conflicting answers:
- Flag the conflict explicitly:
`` [CONFLICT: CFO projects 14-month runway; CRO expects pipeline to close 80% → implies 18+ months] ``
- State the resolution approach:
- Conservative: use the worse case
- Probabilistic: weight by confidence scores
- Escalate: flag for human decision
- Never silently pick one — surface the conflict to the user.
Broadcast Pattern (Crisis / CEO)
CEO can broadcast to all roles simultaneously:
Responses come back independently (no agent sees another's response before forming its own). Aggregate after all respond.
Decision Memory (Canonical Layout)
All C-suite skills and /cs:* commands read and write decisions in one place — the two-layer model owned by /cs:decide and the decision-logger skill:
Rules:
- Layer 1 (raw) stores everything, including rejected arguments. Reference only — never feeds future sessions automatically.
- Layer 2 (approved) stores only founder-approved decisions. This is what board meetings,
/cs:office-hours, and/cs:founder-modeload. Prevents hallucinated consensus. - Writers:
/cs:decideand the Chief of Staff (post board-meeting Phase 5). Individual role agents never write decisions directly. - decision-logger, chief-of-staff, and board-meeting all use this layout. Their SKILL.md files link here rather than defining their own paths.
Migration: earlier versions used memory/board-meetings/ (decision-logger, board-meeting) and ~/.claude/decision-log.md (chief-of-staff); read those for history if present, but write all new entries to ~/.claude/decisions/.
Quick Reference
| Rule | Behavior | |
|---|---|---|
| Self-invoke | ❌ Always blocked | |
| Depth > 2 | ❌ Blocked, state assumption | |
| Circular | ❌ Blocked, state assumption | |
| Phase 2 isolation | ❌ No invocations | |
| Phase 3 critique | ❌ Reference only, no invoke | |
| Conflict | ✅ Surface it, don't hide it | |
| Assumption | ✅ Always explicit with [ASSUMPTION: ...] |
Internal Quality Loop (before anything reaches the founder)
No role presents to the founder without passing through this verification loop. The founder sees polished, verified output — not first drafts.
Step 1: Self-Verification (every role, every time)
Before presenting, every role runs this internal checklist:
Step 2: Peer Verification (cross-functional validation)
When a recommendation impacts another role's domain, that role validates BEFORE presenting.
| If your recommendation involves... | Validate with... | They check... | |
|---|---|---|---|
| Financial numbers or budget | CFO | Math, runway impact, budget reality | |
| Revenue projections | CRO | Pipeline backing, historical accuracy | |
| Headcount or hiring | CHRO | Market reality, comp feasibility, timeline | |
| Technical feasibility or timeline | CTO | Engineering capacity, technical debt load | |
| Operational process changes | COO | Capacity, dependencies, scaling impact | |
| Customer-facing changes | CRO + CPO | Churn risk, product roadmap conflict | |
| Security or compliance claims | CISO | Actual posture, regulation requirements | |
| Market or positioning claims | CMO | Data backing, competitive reality | |
| Legal exposure, contracts, term sheets | GC | Clause risk, IP ownership, regulatory triggers | |
| Data rights, training-data provenance | CDO | Consent basis, GDPR Art. 6, data-asset impact | |
| AI model claims, eval results, AI risk | CAIO | Eval coverage, hallucination SLO, EU AI Act tier | |
| Retention, churn, customer-health claims | CCO | GRR/NRR decomposition, churn root cause | |
| Delivery timelines, eng throughput | VPE | DORA metrics, cycle-time reality, team capacity |
Peer validation format:
Skip peer verification when:
- Single-domain question with no cross-functional impact
- Time-sensitive proactive alert (send alert, verify after)
- Founder explicitly asked for a quick take
Step 3: Critic Pre-Screen (high-stakes decisions only)
For decisions that are irreversible, high-cost, or bet-the-company, the Executive Mentor pre-screens before the founder sees it.
Triggers for pre-screen:
- Involves spending > 20% of remaining runway
- Affects >30% of the team (layoffs, reorg)
- Changes company strategy or direction
- Involves external commitments (fundraising terms, partnerships, M&A)
- Any recommendation where all roles agree (suspicious consensus)
Pre-screen output:
Step 4: Course Correction (after founder feedback)
The loop doesn't end at delivery. After the founder responds:
Verification Level by Stakes
| Stakes | Self-Verify | Peer-Verify | Critic Pre-Screen | |
|---|---|---|---|---|
| Low (informational) | ✅ Required | ❌ Skip | ❌ Skip | |
| Medium (operational) | ✅ Required | ✅ Required | ❌ Skip | |
| High (strategic) | ✅ Required | ✅ Required | ✅ Required | |
| Critical (irreversible) | ✅ Required | ✅ Required | ✅ Required + board meeting |
What Changes in the Output Format
The verified output adds confidence and source information:
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/agent-protocol/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/renatoschust-dot/gamai-skills/agent-protocol)