Plugin Claude Code
Plugin marketplace listing 1 plugin: llm-router.
15 tagged Cost Optimization, measured the same way as everything else here.
Browse within: LLM 5
Plugin Claude Code
Plugin marketplace listing 1 plugin: llm-router.
Plugin Claude Code
Bundles 4 skills, 1 agent · 349 tokens together
Eco mode for Claude Code: minimize token consumption with critical findings intact. Ships /eco and /eco-max (frugality rules, with a low reasoning-effort override), an Eco output style, /eco audit and /eco report, opt-in enforcement hooks, and a benchmark harness. Measured -35% to -57% output tokens on the same task…
Sagargupta16/claude-cost-optimizer
Plugin Claude Code
Plugin marketplace listing 1 plugin: cost-mode.
Plugin Claude Code
Bundles 4 commands, 1 hook · 54 tokens together
Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits. A passthrough proxy that stabilizes the exact request bytes CC emits — deterministic tool order, canonical JSON, volatile-content relocation — plus the env hardening that stops a custom endpoint from busting the cache.
Plugin Claude Code
Bundles 1 skill, 8 commands · 204 tokens together
Live session-first savings status line, /distil commands (stats, dashboard, shadow equivalence, doctor, onboard, trajectory certificate, savings badge) for distil — certified context compression.
Plugin Claude Code
Bundles 1 skill, 2 commands, 2 hooks · 96 tokens together
Prices what your coding agent is about to do before it runs: asks before costly launches and destroys, tracks AI spend, and answers cost questions across AWS, Azure, GCP, Kubernetes and AI providers. Local, read-only. The guard is on once the plugin is installed; nable guard off pauses it. Credentials stay on your…
Plugin Claude Code
Bundles 9 skills, 9 hooks · 811 tokens together
Plan and review in Claude Code or Codex, delegate to five worker backends, keep project memory, and watch agents on the live floor.
Plugin Claude Code
Bundles 1 command, 6 agents, 1 hook · 402 tokens together
Persistent memory and receipt-verified workflows for Claude Code — /spec plans, reviews, and executes with quality gates; plus security audits, code reviews, test generation, and release prep from /attune.
Plugin Claude Code
Bundles 8 skills, 14 commands, 5 agents, 6 hooks, 1 MCP server · 946 tokens together
Precision-tuned context engineering for Claude Code. Optimize context flow with modular plans (95% fewer tokens), parallel workflows (81% cost reduction), and zero-transformation architecture. Quick research (/ctx:research: 3 parallel agents, 1-2 min). Contextune your workflows for peak performance!
Plugin Claude Code
Bundles 3 skills, 1 hook · 150 tokens together
EOQ-optimal context restart advisor for Claude Code — statusline, dashboard, and MCP tools with zero context pollution.
Plugin Claude Code
Bundles 1 skill, 1 command, 8 agents, 2 hooks · 466 tokens together
Tiered model routing for token economy: the strongest model thinks, cheaper models grind. Ready-made subagents (sonnet scout, implementer, task-reviewer and E2E runner, haiku surveyor, test-runner and verifier, opus reviewer) plus a routing skill and dispatch stats.
Plugin Claude Code
Bundles 1 skill · 83 tokens together
Native-first FinOps agent for AWS, GCP, and Azure. Finds cloud savings using each provider's own CLIs and recommendation engines (Cost Explorer/Compute Optimizer, GCP Recommender, Azure Advisor).
Plugin Claude Code
Bundles 1 skill, 4 commands, 1 MCP server · 153 tokens together
Find and quantify cloud and CI spend waste from your coding agent. Costguard runs read-only billing checks (GitHub Actions, Supabase, Railway, Netlify, Neon), static CI/cron waste rules, dry-run-first auto-fixes for workflow files, and a monthly cost digest — all driven from your session via /costguard-audit…
Plugin Claude Code
Bundles 18 skills, 3 commands, 5 hooks · 1,657 tokens together
The godspeed methodology — a routing-and-orchestration pipeline for Claude Code. Fires on the word 'godspeed': scores the prompt on S0-S5 complexity, routes to the cheapest model that handles it well, dispatches parallel Sonnet workers for S3+ tasks, critic-gates the synthesis, and persists PASSing answers to a vector.