Olore Tensorzero Latest
olorehq/olore
Local TensorZero documentation reference (latest). An agent skill from olorehq/olore.
Measurement-driven model router for Claude Code. An agent skill from majiayu000/claude-skill-registry.
Install Tokenwise
$ npx skills add majiayu000/claude-skill-registry --skill tokenwise -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install majiayu000/claude-skill-registry tokenwise --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-llm/tokenwise .claude/skills/tokenwise && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "tokenwise" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/tokenwise into .claude/skills/tokenwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tokenwise", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/tokenwiseType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add majiayu000/claude-skill-registry --skill tokenwise -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install majiayu000/claude-skill-registry tokenwise --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ai-llm/tokenwise .agents/skills/tokenwise && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tokenwise" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/tokenwise into .agents/skills/tokenwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tokenwise", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add majiayu000/claude-skill-registry --skill tokenwise -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install majiayu000/claude-skill-registry tokenwise --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ai-llm/tokenwise .cursor/skills/tokenwise && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "tokenwise" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/tokenwise into .cursor/skills/tokenwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tokenwise", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/majiayu000/claude-skill-registry.git --path skills/ai-llm/tokenwise--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add majiayu000/claude-skill-registry --skill tokenwise -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install majiayu000/claude-skill-registry tokenwise --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ai-llm/tokenwise .gemini/skills/tokenwise && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "tokenwise" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/tokenwise into .gemini/skills/tokenwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tokenwise", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install majiayu000/claude-skill-registry tokenwiseInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add majiayu000/claude-skill-registry --skill tokenwise -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ai-llm/tokenwise .github/skills/tokenwise && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "tokenwise" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/tokenwise into .github/skills/tokenwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tokenwise", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add majiayu000/claude-skill-registry --skill tokenwise -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install majiayu000/claude-skill-registry tokenwise --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/claude-skill-registry.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ai-llm/tokenwise .opencode/skills/tokenwise && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "tokenwise" agent skill from https://github.com/majiayu000/claude-skill-registry/tree/main/skills/ai-llm/tokenwise into .opencode/skills/tokenwise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tokenwise", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
tokenwise- GitHub stars
- 666
- Used in
- 2 other repos
- Token cost
- ~932 tokens
- SKILL.md length
- 393 words
- Files
- 2
- Skills in repo
- 971
- Repo updated
- First seen
- Licence
- MIT
At a glance
Measurement-driven model router for Claude Code. An agent skill from majiayu000/claude-skill-registry.
- Tasks that involve Model routing and gateways
- SKILL.md covers Overview, When to use, Subcommands and Routing taxonomy, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Tasks that involve A/B testing
What it does
Tokenwise is an agent skill from majiayu000/claude-skill-registry. Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust the savings.
Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `metadata.json`).
It sits in AI & LLM Engineering, covering Model routing and gateways and A/B testing. The repository describes itself as: Searchable Claude Code skills catalog with source-linked guides and generated registry artifacts. The licence is MIT.
When your agent uses it
- Tasks that involve Model routing and gateways
- Tasks that involve A/B testing
Example prompts
- “/tokenwise”
What it can do on your machine
Read from SKILL.md and the folder at commit 000116a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Tokenwise loads about 932 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 393 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from majiayu000/claude-skill-registry at commit 000116a, republished under its MIT licence (© majiayu000). 393 words, ~932 tokens.
Download SKILL.mdSave it as
.claude/skills/tokenwise/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- tokenwise
- description
- Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust the savings.
- category
- developer-tools
- risk
- critical
- source
- community
- source_repo
- CodeShuX/tokenwise
- source_type
- community
- date_added
- 2026-05-12
- author
- CodeShuX
- tags
- model-routing, token-optimization, cost-reduction, anthropic, haiku, sonnet, opus, claude-code, ab-testing, measurement
- tools
- claude
- license
- MIT
TokenWise — Measurement-Driven Model Router
Overview
A Claude Code skill that auto-routes subtasks to the cheapest model that can handle them (Haiku for grunt work, Sonnet for scoped reasoning, Opus only for synthesis), then logs every routed task to a local NDJSON with real token + cost numbers. Includes an A/B test subcommand that runs the same task across multiple tiers and scores quality, so the routing decisions are verified against the user's real workload — not estimated.
Anthropic's own bug tracker (Issue #27665) reports 93.8% of Max-subscriber Claude Code tokens flow to Opus. Existing routers (claude-router, wshobson, VoltAgent) either pin models statically or route by vibes-based heuristics with no measurement. TokenWise fills the measurement gap.
When to use
- Cutting Claude Code token spend without sacrificing output quality
- Validating whether Haiku/Sonnet is "good enough" for a specific task class before trusting auto-routing
- Auditing where Opus tokens are actually being burned
- Logging per-session cost data for finance or chargeback
Subcommands
/tokenwise:install— guided installer with diff preview, automatic backups, and--dry-runmode/tokenwise:report— per-session token + cost summary vs all-Opus baseline/tokenwise:summary [--week|--month|--all]— historical aggregate with trend/tokenwise:ab "<task>"— A/B test the same task at multiple tiers, generates a markdown comparison/tokenwise:undo— restore CLAUDE.md / settings.json from backup
Show full SKILL.md (192 more words)Show less
Routing taxonomy
| Tier | Model | Task class |
|---|---|---|
| Mechanical | Haiku 4.5 | file reads, grep, format, rename, simple edits, doc lookups |
| Scoped reasoning | Sonnet 4.6 | single-file refactor, scoped research, test writing |
| Synthesis | Opus 4.7 | architecture decisions, multi-file refactor, security review |
Safety caps:
- Haiku never spawns further subagents
- Max spawn depth = 2
- Subagents that need a smarter model return to parent — they never escalate on their own
- Tasks under 100 chars with no file context run inline (subagent overhead > savings)
- Subagent context >30k tokens bumps a tier
Privacy
Zero telemetry. All logs in .tokenwise/log.ndjson local to the project. Task descriptions truncated to 80 chars and stripped of file contents before logging. No analytics endpoint exists in the source.
Install
In any Claude Code session:
/plugin marketplace add CodeShuX/tokenwise
/plugin install tokenwise@tokenwiseThen run /tokenwise:install and follow the guided prompts.
Limitations
- Token counts approximate to ±2% vs Anthropic billing
- A/B test mode costs extra tokens (one task × N tiers) — intentional one-time validation
- Anthropic-only by design (use LiteLLM or OpenRouter for cross-vendor)
- Subagent
model:param has known silent-fail bugs on some Claude Code builds — skill probes for this at install and refuses to configure if routing is broken
Source
- Repo: https://github.com/CodeShuX/tokenwise
- License: MIT
- Author: CodeShuX
© majiayu000, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/ai-llm/tokenwise of majiayu000/claude-skill-registry.
- SKILL.md
- metadata.json
Open the folder on GitHubat commit 000116a
Used in 2 other repositories
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in majiayu000/claude-skill-registry, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Tokenwise next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Tokenwise this skillmajiayu000/claude-skill-registry | 666 | 2 repos | ~932 | Automated safety check: Pass | MIT | |
| Olore Tensorzero Latestolorehq/olore | 103 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Explore Runlllllllama/RigorPilot-Skills | 497 | 2 repos | ~833 | Automated safety check: Pass | MIT | |
| Skill Forge BenchmarkAgriciDaniel/skill-forge | 177 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Shogun Bloom Configyohey-w/multi-agent-shogun | 1.4k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Codemie Analyticscodemie-ai/codemie-code | 294 | — | ~7.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Explore Run
lllllllama/RigorPilot-Skills
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories.
Skill Forge Benchmark
AgriciDaniel/skill-forge
Benchmark Claude Code skill performance with variance analysis, tracking pass rate, execution time, and token usage across iterations.
Shogun Bloom Config
yohey-w/multi-agent-shogun
Interactive wizard: guided questions with multiple-choice options about subscriptions, then outputs a ready-to-paste capabilitytiers YAML + fixed agent model assignments.
Codemie Analytics
codemie-ai/codemie-code
CodeMie Analytics expert — use this skill whenever the user asks about CodeMie usage data, AI adoption metrics, user leaderboards, CLI insights, spending, LiteLLM costs, token usage, or wants to…
Model Router
nidhi-singh02/agent-router
A skill your agent uses when the user asks to pick a model, subscription, or reasoning effort, or to run router status, usage refresh, or resume a router session.
More from majiayu000/claude-skill-registry
All 971 skills in this repoDeep Research
majiayu000/claude-skill-registry
Multi-source deep research using firecrawl and exa MCPs. An agent skill from majiayu000/claude-skill-registry.
Exa Search
majiayu000/claude-skill-registry
Neural search via Exa MCP for web, code, and company research.
Fal AI Media
majiayu000/claude-skill-registry
Unified media generation via fal.ai MCP — image, video, and audio.
Bgpt Paper Search
majiayu000/claude-skill-registry
Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server.
Bio Alignment Pairwise
majiayu000/claude-skill-registry
Perform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner.
Open Notebook
majiayu000/claude-skill-registry
Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis.
Related
Categories
Questions about Tokenwise
What does Tokenwise do?
Measurement-driven model router for Claude Code. An agent skill from majiayu000/claude-skill-registry. Tokenwise is an agent skill from majiayu000/claude-skill-registry. Measurement-driven model router for Claude Code.
When should I use Tokenwise?
Tokenwise fits situations like: tasks that involve Model routing and gateways; tasks that involve A/B testing.
How do I install Tokenwise in Claude Code?
Run `npx skills add majiayu000/claude-skill-registry --skill tokenwise -a claude-code`. Or copy the skill folder (skills/ai-llm/tokenwise in majiayu000/claude-skill-registry) into .claude/skills/tokenwise in your project. Claude Code loads it when a task matches its description.
How do I install Tokenwise in Codex?
Run `npx skills add majiayu000/claude-skill-registry --skill tokenwise -a codex`. Or copy the skill folder (skills/ai-llm/tokenwise in majiayu000/claude-skill-registry) into .agents/skills/tokenwise in your project. Codex loads it when a task matches its description.
Can I use Tokenwise in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add majiayu000/claude-skill-registry --skill tokenwise -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tokenwise, .gemini/skills/tokenwise, .github/skills/tokenwise and .opencode/skills/tokenwise in your project.
What does Tokenwise need to run?
SKILL.md names no scripts, command-line tools or credentials: Tokenwise is instructions for the agent only.
Does Tokenwise access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Tokenwise safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Tokenwise use?
Tokenwise is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Tokenwise use?
About 932 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Tokenwise?
Skills that share tags, products or a category with Tokenwise: Olore Tensorzero Latest (olorehq/olore, 103 stars), Explore Run (lllllllama/RigorPilot-Skills, 497 stars), Skill Forge Benchmark (AgriciDaniel/skill-forge, 177 stars) and Shogun Bloom Config (yohey-w/multi-agent-shogun, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tokenwise?
majiayu000 (a GitHub user) maintains it in majiayu000/claude-skill-registry, which has 666 GitHub stars. The repository holds 971 skills in this directory. The repository was last updated on October 7, 2026.
Source: majiayu000/claude-skill-registry on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.