Terminal
Terminal/Skill
Reads Caveman Cloud data without changing anything and reports LLM cost, workflows, traces, latency, errors and savings, so you see where spend goes.
By Julius Brussee
Works with
npx skills add juliusbrussee/caveman --skill caveman-evidence-reviewAct as a read-only operator. Build conclusions from current Caveman data, not from repository guesses. Never start, approve, cancel, or roll back an experiment from this skill.
inferred daily headroom;verified ledger savings;Prefer MCP:
caveman_context {}
CLI fallback:
caveman cloud whoami
caveman cloud projects list
Stop if login or project selection is missing. Ask the user to run
caveman login or select a project; never guess.
Use caveman_report for:
overviewcostsscoreworkflowsverified_savingsThen use caveman_plan for ranked daily headroom. If question is narrow, skip
unrelated reports. Read shortest set that can answer it.
CLI fallback:
caveman cloud costs
caveman cloud score
caveman cloud plan --json
State report window and basis before interpreting direction.
Use caveman_trace_search. Choose a bounded window and closed filters:
workflow, agent, model, provider, error code, runtime mode, cache status,
optimization id, status class, token/cost/latency bounds, compression, or
monitor verdict.
Useful groupings:
workflow — find jobs driving cost or failures;model — compare model mix;session — isolate retry or loop behavior;Compare a suspect cohort with a control cohort or earlier bounded window. Do not infer causality from one expensive trace.
CLI fallback:
caveman cloud traces search \
--workflow <slug> \
--from <RFC3339> \
--to <RFC3339> \
--sort total_cost_usd \
--dir desc \
--limit 25
Call caveman_trace_get for a small number of high-signal trace ids. Inspect
request and span metadata, latency, status, token counts, cache state, applied
optimizers, and model route. Keep payload retrieval off.
CLI fallback:
caveman cloud traces show <trace-id> --spans
Use this shape:
## Caveman evidence review
Scope: <project> · <from> to <to>
Measured cost: <value and basis>
Verified savings: <ledger value, kept separate>
Inferred headroom: <per-day band, kept separate>
Findings:
1. <finding> — <aggregate evidence> — traces <ids>
2. <finding> — <aggregate evidence> — traces <ids>
Unproven:
- <plausible explanation lacking a control, trace, or eval>
Next read-only check:
- <one bounded query>
Possible action:
- <proposal only; use caveman-manage for read-only lifecycle review and safety gate>
If data is missing, name missing signal and stop at strongest supported statement. Never turn a catalog subtotal into an invoice or an experiment result into verified savings.