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 0xatd/cheaptokens-skills --skill cheaptokensgit clone --depth 1 https://github.com/0xatd/cheaptokens-skillsWrote 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/0xatd/cheaptokens-skills/cheaptokens)<a href="https://agentmods.dev/skills/0xatd/cheaptokens-skills/cheaptokens"><img src="https://agentmods.dev/badge/skills/0xatd/cheaptokens-skills/cheaptokens/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/0xatd/cheaptokens-skills/cheaptokens"><img src="https://agentmods.dev/badge/skills/0xatd/cheaptokens-skills/cheaptokens.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 | $0.00097 | $0.08992 |
| Opus 5 | $0.00048 | $0.04496 |
| Sonnet 5 | $0.00019 | $0.01798 |
| Haiku 4.5 | $0.00010 | $0.00899 |
Grade A, and why
cheaptokens 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 11d 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.
that can read SKILL.md and make HTTPS calls (curl / fetch / OpenAI How it starts
The opening of the file, as written. The whole thing — 823 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CheapTokens — discounted Venice.ai credits for agents
CheapTokens.ai sells discounted Venice.ai API credits:
- Same-Day Credits: time-decay discounted credits for work today. They expire at 23:59:59 UTC on the purchase date. Capacity affects availability and maximum purchase size, not the time-based price.
- Prepaid API Key: one reusable Venice key with prepaid balance and a selected daily credit reserve. The reserve is debited from prepaid balance each UTC day.
Agents should usually pay with USDC on Base via the
x402 protocol. Human buyers can use card
checkout when available. Either way, the buyer receives a real
Venice.ai API key that works against the OpenAI-compatible endpoint
https://api.venice.ai/api/v1.
This skill is one file. There is nothing to install. Any agent
that can read SKILL.md and make HTTPS calls (curl / fetch / OpenAI
SDK / web_fetch / built-in HTTP tool) can use it.
Why this skill exists
CheapTokens is optimized for cheap burst inference and lightweight API key management. Same-Day keys are best when the task needs to run today at the largest available discount. Prepaid keys are better when a buyer wants one reusable key and a predictable daily reserve. This skill turns either key into immediate action: paste the key (or point the agent at a secret/env var), ask normally, and the agent discovers Venice capabilities, routes the task, spends the key, and attributes what actually ran.
Honest execution model — read this first
The hosting agent (OpenClaw, Claude Code, Cursor, Codex, Cline,
aider, etc.) is running on some default model. That host provider
is what generates the conversational tokens you see in chat. The
agent cannot transparently swap the provider behind its own
generation mid-session. If a user hands you a CheapTokens/Venice
key and you say "switched to Venice" without executing a real
HTTPS call against api.venice.ai, every token you produced still
came from the host provider. That is a silent lie.
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.
- 11d ago First seen · 823 lines · 97 tokens per session scan A 2fccbf79e799
cheaptokens is a skill published in the GitHub repository 0xatd/cheaptokens-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 8,992 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
bridgenode
BridgeNode MCP wrapper — stdio MCP server proxying to remote streamable-HTTP endpoint with automatic x402 payment on Solana USDC. No API keys. Use when an agent needs LLM inference through MCP (Claude Code, Cursor, etc.) and has no provider API key.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
image-prompting
Use when generating or editing images via blockrunimage — especially with GPT Image 2, Nano Banana, or Grok Imagine for posters, UI mockups, marketing assets, product shots, or anything with on-image text. Turns vague user requests ("make me a cool poster") into structured, text-accurate prompts that actually render…
gentech-blockrun
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.
surf
Surf (asksurf.ai) is RETIRED on BlockRun and the blockrunsurf tool was REMOVED in 0.49.0 — the gateway has answered every /v1/surf/ path with HTTP 410 endpointretired since 2026-09-06. Use this skill to route a former Surf question (on-chain SQL, wallet labels and net worth, CEX order books, social mindshare, news) to…
search
Use when the user wants real-time web or news results with AI-summarized answers and citations — Grok Live Search via BlockRun. Cheapest path for "what just happened" questions where freshness beats neural-semantic ranking.