observability
Extract and normalize usage and cost metrics from native assistant logs.
Install
mkdir -p .claude/skills/observability-ancplua && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12105" && unzip -o skill.zip -d .claude/skills/observability-ancplua && rm skill.zipInstalls to .claude/skills/observability-ancplua
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Parse native Claude and Codex logs into normalized usage metrics. Use when analyzing token burn, cost per task, model mix, or budget tracking. Do not use for runtime behavior changes.Key capabilities
- →Parse native Claude logs into normalized usage metrics
- →Parse native Codex logs into normalized usage metrics
- →Extract UsageEvents from log sources
- →Aggregate usage data for cost reporting
- →Track token burn
- →Analyze model mix
How it works
The skill identifies log sources, runs a Python script to extract UsageEvents, and then pipes the output to another script for aggregation into normalized usage metrics.
Inputs & outputs
When to use observability
- →Analyze token burn
- →Track session costs
- →Review model usage patterns
About this skill
Observability
Parse vendor-native log files. Normalize only the metrics layer.
Normalized fields
provider, session, task, role, model,
input_tokens, output_tokens, cache_write, cache_read,
total_tokens, estimated_cost, prompt_hash, outcome
Workflow
- Identify log source:
~/.claude/projects/(JSONL). - Run
scripts/ingest_claude_logs.pyto extract UsageEvents. - Pipe output to
scripts/cost_report.pyfor aggregation.
References
Key constraint
ccusage is a host-local collector, not global truth (issue #222). Use it for operational visibility and local burn rate.
When not to use it
- →For runtime behavior changes
- →When not analyzing token burn, cost per task, model mix, or budget tracking
- →When not working with native Claude or Codex logs
Limitations
- →Does not use for runtime behavior changes
- →ccusage is a host-local collector, not global truth
- →Focuses on normalizing only the metrics layer
How it compares
This skill specifically normalizes metrics from vendor-native Claude and Codex logs for usage analysis, unlike general log parsing that might not focus on token burn or cost per task.
Compared to similar skills
observability side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| observability (this skill) | 0 | 4mo | No flags | Intermediate |
| model-usage | 5 | 2mo | Review | Beginner |
| analytics-tracking | 7 | 6mo | No flags | Intermediate |
| splunk-analysis | 5 | 5mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
model-usage
openclaw
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
analytics-tracking
davila7
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.
splunk-analysis
incidentfox
Splunk log analysis using SPL (Search Processing Language). Use when investigating issues via Splunk logs, saved searches, or alerts.
tracking-crypto-derivatives
jeremylongshore
Track cryptocurrency futures, options, and perpetual swaps with funding rates, open interest, liquidations, and comprehensive derivatives market analysis. Use when monitoring derivatives markets, analyzing funding rates, tracking open interest, finding liquidation levels, or researching options flow. Trigger with phrases like "funding rate", "open interest", "perpetual swap", "futures basis", "liquidation levels", "options flow", "put call ratio", "derivatives analysis", or "BTC perps".
weights-and-biases
davila7
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
perf-analyzer
ComposioHQ
Use when synthesizing perf findings into evidence-backed recommendations and decisions.