agentmods.dev

stats

stats is a skill for Claude Code from Shweta-Mishra-ai/tokenmizer. It costs 51 tokens per session (365 once invoked), scanned A, original, MIT.

A local usage report for TokenMizer, a tool that reduces the amount of text sent to an AI model. It shows saved tokens, estimated cost savings, cache use, and savings by processing layer.

In plain words
What is it for?
Use it to check daily or weekly token savings, dollar savings, cache hit rate, and which of compression, caching, windowing, or file extraction saves the most.
Why use it?
It helps you see whether TokenMizer is reducing AI usage and where the savings come from. It also points out when savings are low.

Skill for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: positional $N argument.

Part of the tokenmizer plugin — 4 skills, 1 MCP server shipped together

not rated 35repo +1 changed 1mo ago A scan SkillSpector: pass 51 tokens original MIT

Good fit Use it to check daily or weekly token savings, dollar savings, cache hit rate, and which of compression, caching, windowing, or file extraction saves the most.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shweta-mishra-ai/tokenmizer/stats
View source ↗ Shweta-Mishra-ai/tokenmizer
Install

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.

Any agent
npx skills add Shweta-Mishra-ai/tokenmizer --skill stats
Clone the repo
git clone --depth 1 https://github.com/Shweta-Mishra-ai/tokenmizer

Made for: Claude Code.

Or install tokenmizer, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote 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.

agentmods badge for stats

README.md
[![agentmods](https://agentmods.dev/badge/skills/shweta-mishra-ai/tokenmizer/stats/github.svg)](https://agentmods.dev/skills/shweta-mishra-ai/tokenmizer/stats)
Your own site
<a href="https://agentmods.dev/skills/shweta-mishra-ai/tokenmizer/stats"><img src="https://agentmods.dev/badge/skills/shweta-mishra-ai/tokenmizer/stats/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.

agentmods 80×15 button for stats

Your own site · 80×15
<a href="https://agentmods.dev/skills/shweta-mishra-ai/tokenmizer/stats"><img src="https://agentmods.dev/badge/skills/shweta-mishra-ai/tokenmizer/stats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00365
Opus 5.5 $0.00020 $0.00146
Sonnet 5.5 $0.00010 $0.00073
Haiku 4.5 $0.00005 $0.00036

Measured 1mo ago against content hash da37371efae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stats scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:8000/api/stats
.claude-plugin/skills/stats/SKILL.md · 58 lines

What it actually says

Show TokenMizer token savings analytics.

What to do

curl -s http://localhost:8000/api/stats

Then also fetch cache stats:

curl -s http://localhost:8000/api/cache/stats

Format the output clearly

Show:

  • Tokens saved today and this week
  • Cost saved in USD
  • Cache hit rate
  • Which layer saved the most (compression / cache / windowing / file extraction)
  • Suggestions if savings are low

Example output

TokenMizer Stats
─────────────────────────
Today:    12,450 tokens saved (34%) — $0.0373
Week:     87,200 tokens saved (31%) — $0.2616

By layer:
  File extraction:  45,000 tokens
  Semantic cache:   28,000 tokens  
  Smart window:     9,200 tokens
  Compression:      3,800 tokens
  Output trim:      1,200 tokens

Cache: 847 entries | 68% hit rate | 8% full
─────────────────────────
Dashboard: http://localhost:8000

If nothing saved yet

Nothing has gone through the proxy yet. Show this, and nothing else:

from openai import OpenAI
client = OpenAI(
    api_key="your-key",
    base_url="http://localhost:8000/v1"
)
Changes

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.

  1. 1mo ago Changed da37371efae7
  2. 2mo ago First seen · 58 lines · 51 tokens per session scan A 42df69995b2a

Subscribe to this mod's changes

stats is a skill published in the GitHub repository Shweta-Mishra-ai/tokenmizer (35 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 365 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metricsClaude Codeclaude-aiclaude-code-pluginclaude-code-plugins-marketplacegraph-memoryllm-ai-memory-context-window
Related

stats compared with skills from other repositories

stats next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
statsShweta-Mishra-ai/tokenmizerSkill352d agoMITA51Claude Code
validate-albumbitwize-music-studio/claude-ai-music-skillsSkill6312d agoCC0-1.0A33Claude Code
promote-ideabitwize-music-studio/claude-ai-music-skillsSkill6312d agoCC0-1.0A50Claude Code
sheet-music-publisherbitwize-music-studio/claude-ai-music-skillsSkill6312d agoCC0-1.0A36Claude Code
import-artbitwize-music-studio/claude-ai-music-skillsSkill6312d agoCC0-1.0A32Claude Code
plagiarism-checkerbitwize-music-studio/claude-ai-music-skillsSkill6312d agoCC0-1.0A35Claude Code
opikcomet-ml/opik-claude-code-pluginSkill2515d agoApache-2.0A80Claude Code