consensus-agent-action-guard
INLINECODE0 is the final safety gate before autonomous action execution.
What this skill does
- - evaluates proposed agent actions (risk, irreversibility, side effects)
- applies hard-block and weighted consensus logic
- returns one of: INLINECODE1
- emits required follow-up actions (e.g., human confirmation)
- writes decision and persona updates to board artifacts
Why this matters
Most catastrophic automation failures happen at execution time. This skill inserts explicit governance before side effects.
Ecosystem role
Built on the same consensus stack as communication and merge guards, giving one policy language across agent operations.
Typical usage
- - gating destructive operations
- controlling external messaging/posting actions
- requiring human confirmation for irreversible high-risk tasks
Runtime, credentials, and network behavior
- - runtime binaries:
node, INLINECODE3 - network calls: none in the guard decision path itself
- filesystem writes: board/state artifacts under the configured consensus state path
Dependency trust model
- -
consensus-guard-core is the first-party consensus package used in guard execution - versions are semver-pinned in
package.json for reproducible installs - this skill does not request host-wide privileges and does not mutate other skills
Quick start
CODEBLOCK0
Tool-call integration
This skill is wired to the consensus-interact contract boundary (via shared consensus-guard-core wrappers where applicable):
- - readBoardPolicy
- getLatestPersonaSet / getPersonaSet
- writeArtifact / writeDecision
- idempotent decision lookup
This keeps board orchestration standardized across skills.
Invoke Contract
This skill exposes a canonical entrypoint:
INLINECODE7 starts the guard flow and executes deterministic policy evaluation with board operations via shared guard-core wrappers.
external_agent mode
Guards support two modes:
- -
mode="external_agent": caller supplies external_votes[] from agents/humans/models for deterministic aggregation. - INLINECODE10 : requires an existing
persona_set_id; guard will not generate persona sets internally.
consensus-agent-action-guard
consensus-agent-action-guard 是自主行动执行前的最终安全关卡。
该技能的功能
- - 评估拟议的智能体行动(风险、不可逆性、副作用)
- 应用硬阻断和加权共识逻辑
- 返回以下结果之一:ALLOW | BLOCK | REQUIRE_REWRITE
- 发出所需的后续行动(例如,人工确认)
- 将决策和角色更新写入板工件
为何重要
大多数灾难性的自动化故障发生在执行阶段。该技能在产生副作用之前插入明确的治理机制。
生态系统角色
基于与通信守卫和合并守卫相同的共识栈构建,为智能体操作提供统一的策略语言。
典型用途
- - 管控破坏性操作
- 控制外部消息/发布操作
- 要求对不可逆的高风险任务进行人工确认
运行时、凭证和网络行为
- - 运行时二进制文件:node、tsx
- 网络调用:守卫决策路径本身无网络调用
- 文件系统写入:在配置的共识状态路径下写入板/状态工件
依赖信任模型
- - consensus-guard-core 是守卫执行中使用的第一方共识包
- 版本在 package.json 中通过 semver 锁定以实现可重现安装
- 该技能不请求主机级权限,也不修改其他技能
快速开始
bash
node --import tsx run.js --input ./examples/input.json
工具调用集成
该技能通过共享的 consensus-guard-core 包装器(如适用)连接到共识交互合约边界:
- - readBoardPolicy
- getLatestPersonaSet / getPersonaSet
- writeArtifact / writeDecision
- 幂等决策查找
这使得板编排在不同技能之间保持标准化。
调用合约
该技能暴露一个规范入口点:
- - invoke(input, opts?) -> Promise
invoke() 启动守卫流程,并通过共享的 guard-core 包装器执行带有板操作的确定性策略评估。
external_agent 模式
守卫支持两种模式:
- - mode=externalagent:调用方提供来自智能体/人类/模型的 externalvotes[] 用于确定性聚合。
- mode=persona:需要现有的 personasetid;守卫不会在内部生成角色集。