# Agentic Board Protocol

> Use this skill for any handoff between agentic-board agents and accountable human principals, any decision request about an agentic system's architecture, security posture or automation investment, any stop condition (depth, deadline, budget, blocking missing evidence, mutation intent, instruction bait, routing loop, challenge rounds), any R0-R5 risk-tier crosswalk or candidate framework mapping, and any value case for an automation investment. It defines the versioned handoff envelope, computed stop conditions, the adversarial decision process with designated challengers and HARD gates, and the value-case contract, each checked offline by a deterministic gate. It is a data and process contract that authorizes nothing: it does not authenticate senders, enforce access or store records, and a valid envelope is not proof that an approval happened.

- Skill: `vincentchuwaichow/agentic-board-protocol` (Agent Skill, multi-file: 7 files)
- Install (CLI): `npx get-skill add vincentchuwaichow/agentic-board-protocol`
- Raw SKILL.md: https://api.skillmd.com/api/skills/vincentchuwaichow/agentic-board-protocol/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: VincentChuWaiChow (https://skillmd.com/u/vincentchuwaichow)
- Updated: 2026-11-12
- Page: https://skillmd.com/skills/vincentchuwaichow/agentic-board-protocol

---


# Agentic Board Protocol

## Purpose

Give the agentic board one shared, checkable contract for how work moves between its agents and the humans who own the decision: a versioned handoff envelope, computed stop conditions, an adversarial decision process, a risk-tier crosswalk and a value case. The envelope is defined in `schemas/agentic-handoff.schema.json` (shape only); every cross-field rule is checked offline by `tests/agentic-board-suite/agentic_board_rules.py`.

This repository ships role contracts, skills, a JSON Schema and offline gates. It is not an orchestration runtime: nothing here authenticates senders, enforces authorization at runtime or stores audit records. This skill's `allowed-tools` line pre-approves Read, Grep and Glob; it does not restrict other tools. Tool limits come from the board agents' harness adapters: copilot, codex, cursor and claude-code carry read-only grants, while gemini, kiro-ide and kiro-cli carry none here, so their limits are prompt-level only.

## When to use

Use this skill when:

- an agent delegates, returns, challenges or escalates, or a principal records a decision,
- someone asks for a decision on an agentic system's architecture, security posture or automation investment,
- a task meets a stop condition, or an objective reads as a mutation request or claims a prior approval,
- you must express risk as R0 to R5, translate another risk scale, or draft a candidate NIST AI RMF mapping,
- an automation investment needs a value case, counterfactuals or a promotion decision.

## When not to use

- Single-vendor platform work: use that vendor's agent or maestro (for example aws-agentcore-agent).
- Runtime authorization, identity enforcement or audit storage: use the deploying runtime, or the python-live governance control-plane pattern (python-live-governance-maestro-agent).
- Live mutation: use the owning provider's gated live-guard path in `docs/execution-tiers.md`. The board has no execute verb.
- Certification or compliance conclusions: mappings here are candidate review aids that an accountable owner confirms.

## Core rules

- The envelope is the only inter-agent channel. No free-form side channel, no credentials, no secrets.
- Agents never decide. Every decision-request is addressed to a principal.
- Only a principal-sourced decision-record carries approved or rejected, bound to the request by the sha256 of its canonical JSON. Agent messages carry not-required or pending-human-review.
- There is no execute verb. Authorized actions are read, analyze, recommend, challenge and escalate. R3+ live work escalates to a principal with a route hint.
- Monotonic attenuation down a chain: tier, classification, materiality flags and prohibitions never shrink; deadline and max_hops never extend; actions and budget limits only narrow.
- Stop conditions are computed from envelope fields, never the wall clock: depth, deadline, budget, blocking missing evidence, mutation intent, instruction bait, routing loop, challenge rounds.
- Challengers are designated by decision class. The proposer never challenges its own proposal; independence is procedural, not epistemic.
- HARD gate: a security challenge with hard_gate true that is open (sustained or unresolved, or stopped whatever outcome it records) forbids recommending approve or conditional-approve. Only a principal decision-record with a risk acceptance reference may approve over it.
- subject_risk_tier is the canonical R0 to R5 tier of the decision under review. The board's own work is static review. Materiality flags force full-depth review and never remap the tier.
- Value-case promotion rule: beyond pilot needs measured confidence and a net annual value low above every counterfactual's low. Synthetic records never exceed pilot.
- Frameworks are candidate mappings, never certification or a claim of compliance.
- Validate record sets offline with `python3 tests/agentic-board-suite/agentic_board_rules.py <record-set.json>`. A pass proves form and consistency, not truth or that anyone approved anything.

## One owner per concept

| Concept | Owning asset |
|---|---|
| Cascading-failure containment; pattern selection (deterministic workflow, single agent, multi-agent); durable execution, state and memory lifecycle | `agentic-system-architecture-review-agent` |
| Agent identity, delegated authorization, MCP audience binding and token passthrough, A2A security schemes and card signatures; tool, skill and MCP-server provenance; memory and context poisoning | `agentic-security-review-agent` |
| MCP tool-schema fidelity and protocol version | `typescript-mcp-tool-contract-agent` (existing) |
| Evaluation design | `llm-ai-pipeline-test-review-agent` (existing) |
| Model and token unit prices | `finops-ai-economist-agent` (existing) |
| Value-case challenge | `finance-capital-allocation-advisor-agent` (existing) |
| Regulatory classification, including the EU AI Act | `legal-regulatory-compliance-agent` (existing) |
| Business automation ladder rungs (eliminate, redesign, conventional automation), value case, stop conditions | This protocol |

## References

Load these only when needed:

- [Handoff envelope](references/handoff-envelope.md) — message types, field-by-field purpose, principal subjects, what a valid envelope does not prove, a synthetic example and the envelope rules.
- [Stop conditions](references/stop-conditions.md) — each computed stop, what to declare and do next, why, and the fixture-oracle limits.
- [Decision record](references/decision-record.md) — the ten-step adversarial process, depth by risk, designated challengers, HARD gate, dissent and the principal's record.
- [Risk-tier crosswalk](references/risk-tier-crosswalk.md) — canonical R0 to R5, the owner's scale, execution tiers, candidate NIST AI RMF mapping and EU AI Act routing.
- [Value case](references/value-case.md) — automation ladder, net annual value, unit economics, counterfactuals, promotion and the finance attack checklist.

## Response minimum

Return, at minimum:

- the message type and, for a decision, the decision class, the subject_risk_tier and any materiality flags,
- the designated challenger and each challenge outcome, or why none was required,
- open dissent and any HARD gate, carried unchanged to the principal,
- stop conditions declared, with the route hint for each,
- for investments, the net annual value range, counterfactuals, confidence and promotion state,
- evidence labels and missing evidence, and an explicit statement that nothing here approves or executes anything.

