Token Diet
tokendiet.clawhard.com
· Clawhard Studio
Token Diet shrinks what you paste into AI. It shows what a prompt costs in tokens and cuts the junk in one tap (base64 blobs, giant JSON, repeated log lines, stack-trace noise) so you hit your AI usage limit later. Runs in your browser.
Dispute or improve this rating
D
Conformance score: 54/100
D-grade: significant issues, auth-gated, partially broken, or stale.
Show breakdown
Hide breakdown
How to earn +10 points
How to earn +5 points
Activity
last 24h · 0 invocations No personal data recordedNo activity in the last 7 days.
Card history
1 snapshotSnapshots
| Captured | Hash | Snapshot |
|---|---|---|
| 2026-11-07 17:17:45 current | f3ad9f9f68ad… |
view → |
Try it
Sent live, through Agenstry.
Endpoints
| Agent card | https://tokendiet.clawhard.com/.well-known/agent-card.json |
| Provider | https://clawhard.com |
| Docs | https://tokendiet.clawhard.com/llms.txt |
Health · last 1 probes
Embed a badge
Updates itself and links back here.
[](https://agenstry.com/agents/tokendiet.clawhard.com) [](https://agenstry.com/agents/tokendiet.clawhard.com) [](https://agenstry.com/agents/tokendiet.clawhard.com) [](https://agenstry.com/agents/tokendiet.clawhard.com)
Audit evidence
JSON for vendor reviews. Signed copy verifies against our JWKS.
Raw agent card JSON
{
"name": "Token Diet",
"description": "Token Diet shrinks what you paste into AI. It shows what a prompt costs in tokens and cuts the junk in one tap (base64 blobs, giant JSON, repeated log lines, stack-trace noise) so you hit your AI usage limit later. Runs in your browser.",
"version": "1.1.0",
"url": "https://tokendiet.clawhard.com/a2a",
"preferredTransport": "JSONRPC",
"protocolVersion": "1.0",
"supportedInterfaces": [
{
"url": "https://tokendiet.clawhard.com/a2a",
"protocolBinding": "JSONRPC",
"protocolVersion": "1.0"
},
{
"url": "https://tokendiet.clawhard.com/a2a",
"protocolBinding": "JSONRPC",
"protocolVersion": "0.3"
}
],
"provider": {
"organization": "Clawhard Studio",
"url": "https://clawhard.com"
},
"iconUrl": "https://clawhard.com/icon-512.png",
"documentationUrl": "https://tokendiet.clawhard.com/llms.txt",
"capabilities": {
"streaming": false,
"pushNotifications": false,
"extendedAgentCard": false
},
"defaultInputModes": [
"application/json",
"text/plain"
],
"defaultOutputModes": [
"application/json",
"text/plain"
],
"skills": [
{
"id": "tokendiet_count_tokens",
"name": "Count the exact tokens in a text",
"description": "Counts the exact number of tokens in a text with the o200k tokenizer (GPT-4o family and later), plus words and characters (Unicode code points, so an emoji is 1 character), and whether it fits in 128K, 200K and 1M token context windows. Language models cannot count their own tokens reliably.",
"tags": [
"tokendiet",
"DeveloperApplication",
"read-only"
],
"examples": [
"How many tokens is this prompt?",
"Will this log fit in a 128K context window?",
"Count the tokens in this document"
],
"inputModes": [
"application/json",
"text/plain"
],
"outputModes": [
"application/json",
"text/plain"
]
}
]
}