Quality-first per-stage model routing for Claude Code dynamic workflows (ultracode): a SessionStart hook that injects the routing policy, a PreToolUse cost gate, a routing skill, and slash commands for the whole workflow — /ultracost:check (guard agent() stages), estimate, explain, simulate, diff, audit, usage, reconcile, calibrate, ledger, status.
Audit pin coverage across your real workflow scripts, identify the worst offenders, and offer to check or fix a specific one.
Tune the estimator from your real token usage (outlier-filtered prior) so future estimates match your reality, and report what changed.
Guard a dynamic-workflow script and fix it: flag agent() stages that would inherit the session model or mismatch the task, propose the right per-stage pins, and offer to apply them.
Diff the estimated cost of two workflow versions and judge whether the change is worth it; add --ci for a PR-comment table.
Estimate a workflow before launch and help cut its cost: agent count, model mix, tiered vs all-opus, then surface the costly stages and offer concrete downgrades.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.
When ultracode is on, the session is pinned to Opus @ xhigh and a single dynamic
workflow fans out to dozens of subagents that inherit that session model unless every
stage is pinned. ultracost makes per-stage routing explicit, policy-driven, and
verifiable — quality-first, so coding and reasoning stay on Opus while pre-planned
mechanical work drops to Sonnet. No telemetry. No network on the hot path. MIT.
Built for
ultracode(Opus @xhighdynamic workflows) — the only place this fan-out happens. ultracost routes by tier (opus/sonnet), not a pinned version, so it tracks whatever Opus your session runs.
Security & trust. ultracost has zero runtime and dev dependencies, so there is no
supply chain to compromise — Snyk Open Source and npm audit report 0 vulnerabilities.
Releases publish to npm with OIDC Trusted Publishing and signed provenance, every
GitHub Action is pinned to a commit SHA, and CodeQL + OpenSSF Scorecard run in CI.
The installer touches only its own files and is fully reversible. See SECURITY.md.
Claude Code plugin (recommended):
/plugin marketplace add danielkremen818/ultracost
/plugin install ultracost@ultracost
npm CLI (CI / scripting):
npx ultracost init
Via ClaudePluginHub (one command — adds the marketplace and installs the plugin):
npx claudepluginhub danielkremen818/ultracost --plugin ultracost
First command, in Claude Code: /ultracost:check ./path/to/workflow.js — flag any
agent() stage that would silently inherit Opus. Every verb is also a slash command, so
plugin users need nothing on PATH.
When ultracode is on, Claude Code runs the session on Opus @ xhigh (the only model that supports xhigh) and auto-orchestrates dynamic workflows that fan out to dozens — up to 1,000 — subagents. Two defaults compound:
The documented result: one prompt spawning 46 Opus subagents and ~3M tokens with no warning. A grep sweep and a per-file verifier do not need Opus. (Why ultracode makes this worse →)
This is the default behavior, not user error. In a scan of ~22 real ultracode workflow scripts, almost none pinned model: on any stage — even Anthropic's own bundled deep-research workflow pins zero. Reproduce it on your own history in one command:
npx ultracost audit ~/.claude/projects
npx claudepluginhub danielkremen818/ultracost --plugin ultracostA Claude Code slash command that rewrites your request into an optimized, reasoning-maximizing prompt — clarifying first only when the ask is ambiguous or risky — then carries it out. Ships /p: structured context, specificity, meta-instructions for extended thinking, robust skip-comments for literals, intent typing, and a --dry optimize-only mode.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.