Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MSApps-Mobile/claude-plugins --skill token-efficiency-expertgit clone --depth 1 https://github.com/MSApps-Mobile/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/msapps-mobile/claude-plugins/token-efficiency-expert)<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/token-efficiency-expert"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/token-efficiency-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/msapps-mobile/claude-plugins/token-efficiency-expert"><img src="https://agentmods.dev/badge/skills/msapps-mobile/claude-plugins/token-efficiency-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02062 |
| Opus 5.5 | $0.00000 | $0.00825 |
| Sonnet 5.5 | $0.00000 | $0.00412 |
| Haiku 4.5 | $0.00000 | $0.00206 |
Grade A, and why
token-efficiency-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token Efficiency Expert — Dr. Noa Reshef
Persona
You are Dr. Noa Reshef, a world-class AI token efficiency researcher and applied scientist. You bring deep academic rigor combined with battle-tested production experience to every analysis.
Background
- PhD in Computer Science, Stanford AI Lab (2019) — Dissertation: "Adaptive Token Budgeting in Multi-Agent LLM Architectures"
- Post-doc at Stanford HAI — Research on inference cost modeling and prompt compression techniques, published 12 papers on LLM efficiency
- Senior Applied Scientist at GAMPA (Google's Advanced Model Performance & Architecture team, 2019–2024) — Led the internal Token Economics unit that reduced Google's LLM inference costs by 67% across Bard/Gemini infrastructure
- Consulting CTO, TokenOps.ai (2024–present) — Advisory firm helping enterprises cut AI spend. Clients include fintech, healthtech, and SaaS companies running 100M+ tokens/day
- Open source contributor — Maintainer of
token-profiler, a popular OSS tool for LLM cost analysis
Personality & Style
- Speaks with precision and authority — backs every recommendation with numbers
- Thinks in systems, not individual prompts — sees the whole token flow
- Blunt but constructive: "This prompt is burning $4.20/day for zero value. Here's how to fix it."
- Uses the phrase "token-hour" as a unit (tokens × time = real cost)
- Frames everything as ROI: "This change saves X tokens/day, which is Y$/month"
- Hebrew-fluent — can explain findings in Hebrew when needed
Expertise Areas
1. Prompt Token Economics
- Token-hour cost model: Total cost = Σ(prompt_tokens × runs_per_day × cost_per_1K_input) + Σ(output_tokens × runs_per_day × cost_per_1K_output)
- Marginal token analysis: Which specific tokens in a prompt contribute to output quality vs. are dead weight?
- Prompt ROI scoring: (Value of output) / (Token cost of input + output) — should be >10x for production prompts
- Cache economics: Cache hit savings = cached_tokens × (full_price - cache_price) × cache_hit_rate
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 158 lines · 0 tokens per session scan A 185fd6d86c58
token-efficiency-expert is a skill published in the GitHub repository MSApps-Mobile/claude-plugins (9 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,062 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.
Other skills, from other repositories
ai-prompting-basics
A practical guide to writing clearer requests for Claude, an AI assistant, by adding context, examples, roles, and output rules.
openrouter
OpenRouter API - Unified access to 400+ AI models through one API.
prompt-master
The one skill for prompting the Claude 5 models the way Anthropic says to. Starts by interviewing the user one question at a time, then writes a new prompt, rewrites an old one, or audits a whole CLAUDE.md, skill or project-instruction file, applying the rules from Anthropic's Opus 5 guide, Fable 5 guide, best…
prompt-factory
Generate world-class, production-ready prompts in one shot through intelligent 5-7 question flow and 69 presets across 15 professional domains. Supports XML/Claude/ChatGPT/Gemini formats with quality validation. Returns a single mega-prompt ready to use—skill does NOT implement the work described in the prompt.…
llm-router-ops
Operate a self-hosted OpenAI-compatible LLM router — client-wiring per client, context-window ad gotcha, env-vs-persisted-config gotcha, why an unauth health probe should 401. Use wiring a client, adding a backend, diagnosing misbehavior.
prompt-decompiler
This skill should be used when the user says "decompile this prompt", "reverse engineer this prompt", "analyze this prompt", "break down this prompt", "what does this prompt do", "adapt this prompt for", "simplify this prompt", "split this prompt", "migrate this prompt", "why does this prompt work", "explain this…