Agent Skills
› SeemSeam/claude_codex_bridge
› ccb-diagnose
ccb-diagnose
GitHub用于诊断 CCB 托管代理的运行状态，通过执行 ping、ps 等命令获取运行时与作业血缘证据，并基于日志分析进行受限修复，严禁未授权操作。
Trigger Scenarios
需要诊断 CCB 托管代理故障时
检查代理运行状态和作业队列详情时
Install
npx skills add SeemSeam/claude_codex_bridge --skill ccb-diagnose -g -y
SKILL.md
Frontmatter
{
"name": "ccb-diagnose",
"metadata": {
"short-description": "Diagnose CCB agent"
},
"description": "Diagnose a named CCB managed agent using runtime, job-lineage, and provider evidence."
}
CCB Diagnose
Diagnose exactly one current mounted agent. Start with CCB authority:
command ccb ping "$AGENT"
command ccb ps
command ccb queue --detail "$AGENT"
command ccb pend --inbox --detail "$AGENT"
Use ccb trace for a current lineage id and ccb doctor logs for provider/API
evidence. For DSH, the pane is only the managed host process/log surface: pane
text is not prompt, reply, or completion authority. Native authority is the
exact DSH session/RPC event history and turn/end reason recorded by CCB.
Do not read credentials, mutate tmux directly, restart all agents, or submit a GitHub issue without showing a redacted proposal and receiving explicit authorization. Apply only a bounded supported repair, then re-check the same runtime and lineage evidence.
Version History
- 070e86f Current 2026-08-20 03:05
