agentmods.dev

trazum

A plugin for estimating prompt cost before an AI call and examining usage logs afterward. It works with token budgets, CI drift checks, deterministic prompt optimization, and configured spending limits.

In plain words
What is it for?
Use it to optimize prompts, set token budgets, check cost drift in continuous integration (CI), profile usage logs, and apply spending guards through its tools.
Why use it?
It helps reveal which prompts or usage patterns would increase an AI bill. Spending checks can also identify calls that exceed configured dollar ceilings before they are made.

Plugin for Claude Code

1 yesterday A scan tokens not measured original MIT
View the source file Davmunrey/Trazum
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.

Claude Code
/plugin marketplace add Davmunrey/Trazum
agentmods
npx agentmods add plugins/davmunrey/trazum/plugin
Clone the repo
git clone --depth 1 https://github.com/Davmunrey/Trazum

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

trazum 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 yesterday.

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.

plugin/.claude-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "trazum",
  "version": "2.2.1",
  "description": "Price a prompt before it costs money, and read the bill after. Deterministic prompt optimisation (no API key, no network), token budgets and drift gates for CI, usage-log profiling that names what would actually move the bill, and seven MCP tools including a spend guard that judges configured USD ceilings before a call is made.",
  "author": {
    "name": "David Mu\u00f1oz Rey"
  },
  "homepage": "https://github.com/Davmunrey/Trazum",
  "repository": "https://github.com/Davmunrey/Trazum",
  "license": "MIT",
  "keywords": [
    "prompt",
    "tokens",
    "cost",
    "llm",
    "budget",
    "optimiser",
    "usage",
    "mcp",
    "spend"
  ]
}
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. yesterday First seen · 23 lines scan A b2215f2eb80e

Subscribe to this mod's changes

trazum is a plugin published in the GitHub repository Davmunrey/Trazum (1 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Backend and APIsCost OptimizationData and AIDevOps and cloudai-agentsanthropicclaude-codeclideveloper-tools
Related

Other plugins, from other repositories

llm-router

Smart LLM routing with Claude subscription monitoring, complexity-first model selection, and 20+ AI providers.

ypollak2/llm-router · not measured

claude-cost-optimizer

Plugin marketplace listing 1 plugin: cost-mode.

Sagargupta16/claude-cost-optimizer · not measured

attune-ai

Plugin marketplace listing 2 plugins: attune-ai, attune-help.

Smart-AI-Memory/attune-ai · not measured

stuntman

Claude doesn't do its own stunts. Plan with Claude, execute with a near-free model (DeepSeek, Groq, Ollama, Grok, Kimi… via a local proxy or opencode), OpenAI's Codex CLI, Google's Antigravity CLI (agy), or Meta's Muse Code CLI, review with Claude — your subscription tokens go only where intelligence matters.

mhlaghari/stuntman · not measured

stuntman

Plugin marketplace listing 1 plugin: stuntman.

mhlaghari/stuntman · not measured

model-routing

Plugin marketplace listing 1 plugin: model-routing.

AqueGen/model-routing · not measured