Cost Trend

Reads every benchmark run JSON in your docs folder and shows you how win rate, latency, escalation rate, and cost have drifted over time. The smoke gate is binary pass or fail, but this surfaces the slow creep from 100% to 85% win rate that still passes smoke yet signals real degradation. Run it before releases to catch performance regressions the gate missed, or after corpus changes to verify consistency. Flags when win rate drops or latency climbs 1.5x between first and last run. Basically turns your accumulated benchmark history into a regression detector instead of letting those JSON files sit unused.

skills.sh installs: 683
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill cost-trend --agent claude-code

Installs into .claude/skills of the current project.

Files

Cost Trend

The smoke gate is binary (winRate ≥ 0.80 → pass/fail). The corpus benchmarks captured over time form a curve — and curves catch regressions the gate misses (win rate slowly creeping from 100% to 85% is "still passing" by smoke but a real degradation).

This skill reads every persisted run in docs/benchmarks/runs/*.json and reports first→last deltas plus a per-run series, flagging regressions in win rate or latency.

When to use

Before a release — check that the speedup hasn't drifted.
After expanding the corpus — verify older runs still hit the same win rate on the new corpus they reflected.
After upgrading agent-booster — surface latency / strategy changes.

Steps

Run the trend script from the project root:
```
node plugins/ruflo-cost-tracker/scripts/trend.mjs
```
Optional env:
- TREND_FORMAT=json — emit JSON instead of markdown
- TREND_LIMIT=10 — consider only the most recent N runs
Inspect the drift summary — first vs last on win rate, avg latency, p99, escalation rate, speedup vs Gemini.