Diagnose CCB runtime, mounted daemon graph, tmux namespace and panes, provider context, queue/inbox/trace, replies/artifacts, config drift, and storage boundaries.
SkillScore74Maintained
Automatic
◆DevOps & SRE pack
Last verified 8/8/2026
What it changes
Passed 13 of 18 test cases with the skill, and 6 of 18 without it.
Without skill35%
With skill74%
Checks it passed that the model alone missed
Classify stale socket files under Residue.
Recommend handing off execution to ccb-self-chain.
Use ccb ping ccbd to verify daemon responsiveness.
and 16 more in the full report
12 fixed5 passed either way3 still failing3 broke
Pass-rate lift
+39 pp
Tokens
+2%
Agent turns
0%
Response time
-53%
Model gemini-3.6-flashMeasured 8/8/2026v117 of 23 cases passed with skill · 18 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
We need to verify if the primary CCB daemon ccbd is running, responsive, and holding a valid lease before running further agent checks. What read-only command pair validates daemon health?
What was checked, without and with the skill
Checked
Without skill
With skill
Use ccb ping ccbd to verify daemon responsiveness.
Missed
Passed
Use ccb doctor to inspect control plane system health.
Missed
Passed
case-17 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md95 linessingle file
CCB Self Diagnose
Use this skill for read-only triage. Prefer CCB control-plane diagnostics and
read-only tmux evidence. Do not mutate runtime state from this skill.
Evidence Model
Keep these categories separate in every diagnosis:
Authority: current mounted daemon service graph, lifecycle, lease, current
configured-agent runtime records, and loaded config.
Residue: disk-only .ccb/agents/* directories for unknown agents, stale
panes, stale sockets, old session artifacts, dead helpers, and orphaned
provider state.
Configured-agent and restart target authority comes from the mounted daemon
graph, not disk config, tmux panes, or .ccb/agents/* residue.
Core Workflow
Confirm the project anchor and current mounted daemon generation.
Gather the control-plane snapshot:
ccb ping ccbd
ccb doctor
ccb ps
ccb queue --detail all
ccb fault list
ccb pend --inbox --detail <agent> when one agent is suspected
ccb trace <job_id|message_id|attempt_id|reply_id> for lineage issues
ccb doctor logs <agent> when provider/API evidence is needed
Gather read-only tmux evidence when pane or provider state matters:
current CCB tmux namespace/session/socket
pane ids, active/dead flags, titles, current commands, and captured text
activity sampling when supported
provider session and pid-file paths plus modification times when useful,
without reading secret or private provider-state contents