Agent Skills
› NeverSight/learn-skills.dev
› backend-agents-operons
backend-agents-operons
GitHub负责 consent-protocol 运行时中后端智能体、operons、ADK 表面及编排契约的变更。适用于智能体所有权调整、ADK 集成边界修改及关联测试更新，需确保文档与实现一致，并正确路由至安全或治理技能。
Trigger Scenarios
智能体和 operon 所有权或编排变更
ADK 集成边界和后端工具表面调整
智能体运行时文档和测试更新
Install
npx skills add NeverSight/learn-skills.dev --skill backend-agents-operons -g -y
SKILL.md
Frontmatter
{
"name": "backend-agents-operons",
"description": "Use when changing backend agents, operons, ADK surfaces, or orchestration contracts inside the consent-protocol runtime."
}
Hushh Backend Agents Operons Skill
Purpose and Trigger
- Primary scope:
backend-agents-operons - Trigger on agents, operons, ADK surfaces, orchestration boundaries, or tool/agent runtime changes.
- Avoid overlap with
backend-runtime-governanceandsecurity-audit.
Coverage and Ownership
- Role:
spoke - Owner family:
backend
Owned repo surfaces:
consent-protocol/hushh_mcp/agentsconsent-protocol/hushh_mcp/operonsconsent-protocol/hushh_mcp/toolsconsent-protocol/hushh_mcp/hushh_adkconsent-protocol/hushh_mcp/adk_bridge
Non-owned surfaces:
backendsecurity-auditrepo-operations
Do Use
- Agent and operon ownership or orchestration changes.
- ADK integration boundaries and backend tool surfaces.
- Agent-runtime docs and tests tied to orchestration behavior.
Do Not Use
- Broad backend intake where the correct spoke is still unclear.
- Generic service-layer placement or API wire contract changes.
- Trust-policy work where authorization or vault boundary is the primary concern.
Read First
consent-protocol/docs/reference/agent-development.mdconsent-protocol/docs/reference/kai-agents.mddocs/reference/ai/README.md
Workflow
- Confirm whether the change is about orchestration, tool surface, or agent packaging before editing code.
- Keep orchestration docs and relevant tests aligned with the implementation.
- Route trust, consent, or scope-enforcement questions into
security-audit.
Handoff Rules
- If the request is still broad or ambiguous, route it back to
backend. - If the task becomes service/runtime boundary work, use
backend-runtime-governance. - If the task becomes trust or consent enforcement work, use
security-audit.
Required Checks
cd consent-protocol && python3 -m pytest tests/agents -q
cd consent-protocol && python3 -m pytest tests/test_hushh_adk_foundation.py -q
Version History
- e0220ca Current 2026-07-05 21:32
