Cost Benchmark
Runs a structured benchmark suite against the cost-booster routing logic and optionally compares it to Gemini, Sonnet, and Opus baselines. You'd fire this before cutting a release to confirm your win rate didn't regress, or when you add new test cases to the corpus and want to verify routing decisions. The benchmark takes about 85ms for the booster-only run and writes timestamped JSON results to a docs folder that other skills can read. The smoke gate expects at least 80% win rate on tier-1 cases. It's designed to turn "claimed upstream" tags into "verified" ones by giving you repeatable numbers you can point to in documentation.
- skills.sh installs
- 679
- GitHub stars
- 81.4K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add ruvnet/ruflo --skill cost-benchmark --agent claude-codeInstalls into .claude/skills of the current project.
Files
Cost Benchmark
Runs scripts/bench.mjs against the structural+adversarial corpus and writes per-case + summary results to docs/benchmarks/runs/. This is the verification gate that backs every measurable claim in cost-booster-edit / cost-booster-route.
When to use
- Before publishing a release — verify booster win rate didn't regress.
- After expanding
bench/booster-corpus.json— confirm new cases route correctly. - When auditing a "claimed upstream" tag — flip it to "verified" once the bench supports it.
- On a cost question ("is Sonnet 4.6 cheaper than Opus 4.7 for these tasks?") — re-run with
BENCH_ANTHROPIC=1.
Steps
-
Run the bench from
v3/(whereagent-boosterresolves):( cd v3 && node ../plugins/ruflo-cost-tracker/scripts/bench.mjs ) # booster only — free, ~85 ms ( cd v3 && BENCH_LLM_BASELINE=1 node ../plugins/ruflo-cost-tracker/scripts/bench.mjs ) # + Gemini 2.0 Flash (cheap) ( cd v3 && BENCH_LLM_BASELINE=1 BENCH_ANTHROPIC=1 \ node ../plugins/ruflo-cost-tracker/scripts/bench.mjs ) # + Sonnet 4.6 + Opus 4.7
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/ruvnet/ruflo
- First seen
- Jun 3, 2026
More from ruvnet/ruflo
All 236- Cost Booster Edit679
- Browser674
- Witness656
- AgentDB Advanced Features
- AgentDB Learning Plugins
- AgentDB Memory Patterns
- AgentDB Performance Optimization
- AgentDB Vector Search
- Hooks Automation
- Pair Programming
- ReasoningBank Intelligence
- ReasoningBank With AgentDB
- Skill Builder
- V3 CLI Modernization
- V3 Core Implementation
- V3 DDD Architecture
- V3 Deep Integration
- V3 MCP Optimization
- V3 Memory Unification
- V3 Performance Optimization
- V3 Security Overhaul
- V3 Swarm Coordination
- Agent Arch System Design1.4K
- Agent Workflow1.4K
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs