agentmods.dev

tokencost-dev CLAUDE.md

Project instructions for tokencost, an MCP server that looks up current language-model prices and estimates usage costs.

In plain words
What is it for?
Use it when developing or running tokencost, looking up model pricing, estimating token costs, comparing models, or refreshing its price data.
Why use it?
It gives an agent the project structure, available operations, data source, build commands, and caching details needed to work on the server.

Instructions file

1 7d ago A scan 288 tokens original MIT
View the source file atriumn/tokencost-dev
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.

agentmods
npx agentmods add instructions/atriumn/tokencost-dev/claude-md
Clone the repo
git clone --depth 1 https://github.com/atriumn/tokencost-dev
Per session 288 This file is loaded in full into every session.
When invoked 288 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00288 $0.00288
Opus 5 $0.00144 $0.00144
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured 2d ago against content hash a955f42a8965, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tokencost-dev CLAUDE.md 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 2d 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.

CLAUDE.md · 34 lines

What it actually says

tokencost — LLM Pricing Oracle MCP Server

Overview

Lightweight MCP server that pulls real LLM pricing data from LiteLLM's community-maintained registry and exposes it as tools any MCP-compatible client can query.

Architecture

  • TypeScript, ESM ("type": "module")
  • @modelcontextprotocol/sdk with stdio transport
  • Data source: LiteLLM model_prices_and_context_window.json
  • Fuzzy model name matching via fuse.js

File Structure

  • src/index.ts — Server setup, stdio transport, handler wiring
  • src/tools.ts — Tool definitions (inputSchema) + executeTool dispatch
  • src/pricing.ts — Fetch, cache, normalize LiteLLM data
  • src/search.ts — Fuzzy model name matching

Tools Exposed

  1. get_model_details — Look up pricing/capabilities for a model
  2. calculate_estimate — Estimate cost for a given token count
  3. compare_models — Filter and compare models by provider/context/mode
  4. refresh_prices — Force re-fetch pricing data

Build & Run

npm run build
npm start

Cache

  • In-memory with 24h TTL
  • Disk fallback at .cache/prices.json
  • Background refresh on startup
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. 2d ago First seen · 34 lines · 288 tokens per session scan A a955f42a8965

Subscribe to this mod's changes

tokencost-dev CLAUDE.md is an instructions file published in the GitHub repository atriumn/tokencost-dev (1 stars, last pushed 7d ago), licensed MIT. It adds 288 tokens to every session, about $0.0014 per session on Opus 5. 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 2026-08-31.

Data and AILLMPlanningclaudelitellmmcpmodel-context-protocolopenai
Related

Other instructions, from other repositories

Assistant CLAUDE.md

Instructions for bearlike/Assistant, covering agents guide — mewbo, mandatory: hydrate before touching files, what mewbo is, monorepo layering — read before adding a module and engineering principles.

bearlike/Assistant · 6,737 tokens

Assistant AGENTS.md

Instructions for bearlike/Assistant: This is a shim file for external agents.

bearlike/Assistant · 60 tokens

ai AGENTS.md

AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.

vercel/ai · 2,900 tokens

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…

Azure/GPT-RAG · 207 tokens

llm-context.py CLAUDE.md

Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.

cyberchitta/llm-context.py · 582 tokens

seekstone CLAUDE.md

Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.

shaqmughal/seekstone · 1,116 tokens