Skip to content
cccskills
FreePublished on GitHub

cost-export

Export recorded AI usage costs and budgets as Prometheus metrics or JSON. Feed external dashboards with totals, model tier breakdowns, session costs, and budget utilization, or send the same data to a webhook endpoint.

OriginalShow the original description

Export cost-tracking telemetry in Prometheus textfile or webhook JSON formats — for external observability (Grafana, Datadog, custom dashboards)

Works withDatadog
See how to install

Good for

  • Refreshing cost metrics for Grafana or Prometheus
  • Sending a one-time cost report to a webhook
  • Providing budget utilization data for monitoring
  • Exporting session costs and model tier totals as JSON

Files included (1)

  • SKILL.md2.7 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Cost Export

Pulls every session-* and budget-config-* record from cost-tracking and emits in formats consumable by external observability systems. Without this, cost data lives only inside the AgentDB namespace; with it, the same data lights up dashboards.

When to use

  • After any cost-track run, to refresh metrics for Grafana / Datadog / Prometheus.
  • Cron-friendly via /loop 5m to keep external dashboards near-real-time.
  • One-shot to a webhook for ad-hoc reporting (Slack, custom endpoint).

Steps

  1. Pick a format — textfile collector for Prometheus / Grafana, or webhook POST for everything else:

    # Prometheus node_exporter textfile collector
    node plugins/ruflo-cost-tracker/scripts/export.mjs --prometheus /var/lib/node_exporter/textfile_collector/cost_tracker.prom
    
    # Webhook (POSTs JSON; add auth via env)
    EXPORT_WEBHOOK_HEADER='Authorization: Bearer $TOKEN' \
      node plugins/ruflo-cost-tracker/scripts/export.mjs --webhook https://hooks.example.com/cost-tracker
    
    # Stdout JSON (default if no flag)
    node plugins/ruflo-cost-tracker/scripts/export.mjs
    
  2. Inspect what's emitted — Prometheus output includes:

    cost_tracker_total_usd                                    <gauge>
    cost_tracker_tier_total_usd{tier="opus|sonnet|haiku"}     <gauge>
    cost_tracker_session_total_usd{session="<8-char>"}        <gauge>
    cost_tracker_session_messages{session="<8-char>"}         <counter>
    cost_tracker_budget_usd                                   <gauge>  (if budget configured)
    cost_tracker_budget_utilization                           <gauge>  (spent / budget)
    
  3. Webhook payload shape — the JSON the webhook receives matches the stdout JSON: { exportedAt, sessions: [...], budget, totalUsd, byTier }. Headers may be added via EXPORT_WEBHOOK_HEADER='K1: V1, K2: V2' (comma-separated).

Env overrides

EnvDefaultPurpose
EXPORT_NAMESPACEcost-trackingOverride target namespace
EXPORT_WEBHOOK_HEADERunsetComma-separated K: V pairs for webhook auth
EXPORT_QUIET=1unsetSuppress non-error confirmation output

Cross-references

  • cost-track — produces the data this skill exports
  • cost-budget-check — the same cost_tracker_budget_* metrics are alertable in Prometheus
  • node_exporter textfile collector docs (Prometheus convention) — drop the .prom file in the collector directory and Prometheus picks it up

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.

  • Adding newly available router models to chat-ui
  • Writing concise descriptions of model capabilities
  • Updating production and development model entries together
ruvnet/ruflo76.6KUpdated Oct 18, 2026

adr-create

FreeSummary

Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.

  • Record the reasoning behind adopting a technology
  • Start an ADR for an API or data model change
  • Document an infrastructure decision
ruvnet/ruflo76.6KUpdated Oct 18, 2026

adr-index

FreeSummary

Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.

  • Index ADRs imported from another project
  • Refresh a graph that differs from files on disk
  • Set up ADR tracking in an existing codebase
ruvnet/ruflo76.6KUpdated Oct 18, 2026

adr-reindex

FreeSummary

Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.

  • Rebuild the index after deleting an ADR file
  • Remove stale relationships after editing an ADR
  • Reconcile the ADR index on a schedule
ruvnet/ruflo76.6KUpdated Oct 18, 2026

adr-review

FreeSummary

Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.

  • Check a pull request before merging
  • Review major code changes against agreed design decisions
  • Find references to superseded ADRs
ruvnet/ruflo76.6KUpdated Oct 18, 2026

adr-verify

FreeSummary

Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.

  • Checking ADR integrity after import
  • Blocking CI when ADR issues are found
  • Reviewing ADR data before a release
ruvnet/ruflo76.6KUpdated Oct 18, 2026

See all skills by ruvnet

Report a problem with this skill