stats SKILL.md skillA

stats from shweta-mishra-ai/tokenmizer is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add shweta-mishra-ai/tokenmizer/stats@git:20260911.15f5b03

Pins git:20260911.15f5b03 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
shweta-mishra-ai/tokenmizer
Path
.claude-plugin/skills/stats/SKILL.md
Versions recorded
2
Latest version
git:20260911.15f5b03, committed Sep 11, 2026
First version recorded
Jun 11, 2026
Size
1,440 bytes
Repository stars
34
License
MIT

Show TokenMizer token savings stats — how many tokens saved today, this week, cache hit rate, and which layers are saving the most. Use when user asks about token usage, costs, savings, or "how much have we saved".

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

Show TokenMizer token savings analytics.

## What to do

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

Then also fetch cache stats:
```bash
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:
```python
from openai import OpenAI
client = OpenAI(
    api_key="your-key",
    base_url="http://localhost:8000/v1"
)
```

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add shweta-mishra-ai/tokenmizer/stats@sha256:da37371efae7d2fe

The line at the top of this page pins the label git:20260911.15f5b03, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_cegllt632jqktspl.svg)](https://markdownregistry.com/a/art_cegllt632jqktspl)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jun 11, 2026 and Sep 11, 2026, about one every 93 days.

versioncommittedcommitsizeaudit
git:20260911.15f5b03 latest2026-09-11 15f5b03 1,440 BA view · diff
git:20260611.1d9847e2026-06-11 1d9847e 1,423 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1440 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

shweta-mishra-ai/tokenmizer · 34 stars · license MIT · pushed 2026-10-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cegllt632jqktspl
GET https://markdownregistry.com/api/v1/resolve?ref=shweta-mishra-ai/tokenmizer/stats
GET https://markdownregistry.com/api/v1/blob/da37371efae7d2fe524416de6a1e1e7d790f5098aa55e06ba6279424945a8d16

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from shweta-mishra-ai/tokenmizer

analyze SKILL.md skill
shweta-mishra-ai/tokenmizer · .claude-plugin/skills/analyze/SKILL.md · Analyze a large file (CSV, Excel, PDF, JSON, code) and return a token-efficient summary. Instead of reading thousands…
git:20260611.1d9847e · audit A · 34 stars
checkpoint SKILL.md skill
shweta-mishra-ai/tokenmizer · .claude-plugin/skills/checkpoint/SKILL.md · Save the current session to TokenMizer graph memory. Creates a persistent checkpoint with all tasks, decisions, files…
git:20260911.15f5b03 · audit A · 34 stars
resume SKILL.md skill
shweta-mishra-ai/tokenmizer · .claude-plugin/skills/resume/SKILL.md · Load a previous session from TokenMizer graph memory. Returns a compact context block (100-600 tokens) covering goals…
git:20260911.15f5b03 · audit A · 34 stars

Every file in shweta-mishra-ai/tokenmizer

Other files named stats

stats SKILL.md skill
apache/magpie · plugins/magpie-pr-management/skills/stats/SKILL.md · Read-only maintainer dashboard for the open-PR backlog of <upstream>. Surfaces a health rating, prioritised action…
git:20261016.b4fca1e · audit A · 133 stars
stats SKILL.md skill
anantys-oss/koan · koan/skills/core/stats/SKILL.md · Show session outcome statistics per project
v1.0.0 · audit A · 48 stars
stats SKILL.md skill
mikeprasad/aria-knowledge · plugin-openai-codex/skills/stats/SKILL.md · Show ARIA knowledge-base health metrics: counts, backlog depth, audit status, codemap freshness, tag coverage, and…
git:20261022.3855e1f · audit A · 17 stars
stats SKILL.md skill
mikeprasad/aria-knowledge · plugin-claude-cowork/skills/stats/SKILL.md · Show knowledge base health metrics — file counts, backlog depth, audit status, tag stats, and coverage gaps. Use when…
git:20261014.e0f7288 · audit A · 17 stars
stats SKILL.md skill
mikeprasad/aria-knowledge · plugin-antigravity/skills/stats/SKILL.md · Show knowledge base health metrics — file counts, backlog depth, audit status, codemap dates, tag stats, and coverage…
git:20261022.3855e1f · audit B · 17 stars
stats SKILL.md skill
mikeprasad/aria-knowledge · plugin-claude-code/skills/stats/SKILL.md · Show knowledge base health metrics — file counts, backlog depth, audit status, codemap dates, tag stats, and coverage…
git:20261022.3855e1f · audit B · 17 stars
stats SKILL.md skill
harnessprotocol/harness-kit · plugins/stats/skills/stats/SKILL.md · Use when user invokes /stats or asks about Claude Code usage, token consumption, session history, model distribution…
git:20260316.376a192 · audit A · 10 stars
stats SKILL.md skill
kalinbogatzevski/captain-memo · plugin/skills/stats/SKILL.md · Show Captain Memo's corpus statistics (chunks per channel, observation counts, indexing progress, embedder info). Use…
git:20261015.b3cb7c0 · audit A · 5 stars

Browse by kind, by grade A, or by owner.