Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Catalogue/Apps/Economy

Economy

hasna · App

Economy is an AI coding cost tracker. It ingests local usage from Claude Code, Takumi, Codex, Gemini, OpenCode, Cursor, Pi and Hermes, then breaks cost down by session, project, model, machine, account and cost centre. It keeps editable model pricing, sets budgets and goals with alert webhooks, and reconciles its estimates against Anthropic, OpenAI and Gemini billing sources. Your coding agent can read the same figures through its MCP server. Billing checks need provider admin API keys or a Gemini billing export.

Written by ooruby from the README of @hasna/economy 0.5.14.

Not claimed by its maker. Is this yours? Prove it and answer the findings

Why it's useful

You can see where your AI coding spend goes, by agent, project and model, and compare the estimates with provider billing.

What you could do with it

  1. 1Run a sync and then check the spend for today across the coding agents it reads.
  2. 2Set a budget with a webhook and get an alert on the next sync after spending crosses its threshold.
  3. 3Add its MCP server to your coding agent so it can read live cost figures and manage budgets.

Written from its documentation: what it says it can do, not what our checks found.

ECappFinance & ops

Maintenance

Not measured

No release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.

Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured

Not yet tested
Command execution is bounded
inventory
python subprocess (native/Tools/pair-qr.py:41)
python subprocess (native/Tools/pair-qr.py:82)
python subprocess (native/Tools/pair-qr.py:140)
python subprocess (native/Tools/pair-qr.py:156)
An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.

Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.

What this does not cover

  • ·Everything. Treat it as you would software from anywhere else.

Receipt history: every signed receipt for every version of this listing, and what changed between them.

In its maker's words

AI coding cost tracker — CLI + MCP server + REST API for Claude Code, Codex, OpenCode, Cursor, Pi, and Hermes, with legacy Gemini CLI session and Gemini API billing ingestion

Compare with

  • Omniglyphside by side
  • Estelaside by side
  • Dodopayments CLIside by side
Compare all 4

How far this has been checked

Static scanned

What it establishes
Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
What it does not
How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
Exactly what was read
Version 0.5.14, the file with digest sha512-o1mKwEmZvS6ItBIm44ncFyg+DIB/OBJ2pZVv3plZ3bxZHuuczYPgEyEb1QEgrVtjmOwvWRnYEyo+DQrBlS2eOA==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
Authentication
Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
How the rungs work

Adding it

Run it with:

npx -y -p @hasna/economy@0.5.14 economy

Pinned to 0.5.14, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.

Where this came from

Registry
npm
Package
@hasna/economy
Version read
0.5.14
Resolved
2026-10-10
Open the source(opens in a new tab)

No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.

The badge, if this is your listing

It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.

[![ooruby: static scanned](https://ooruby.com/api/badge/hasna-economy)](https://ooruby.com/market/hasna-economy)

About this listing

Kind
App
Category
Finance & ops
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-05
Price
Free
Get it freeVisit maker
Rating
no reviews yet
0 want this so far
Sign in to vote

Sign in to watch this listing and hear when its version, rung or findings change.

More from hasna

See the storefront
MEMCP serverDeveloper tools
Clean scanStatic scanned
Offered as a command line tool, an MCP server and a library, and runs on your machine once you opt in to local mode. Memories have a scope and a category such as preference, fact or procedural.

Mementos

hasna
Free

Gives your agent a place to save, search and recall memories, organised by project, agent and scope.

91.8k installs/moApache-2.0
SEagentInfrastructure
Clean scanStatic scanned
Talks to the hosted Hasna secrets API by default and needs an API key, with an opt-in encrypted vault on your own machine. Use it from the command line, an MCP server or an SDK.

Secrets

hasna
Free

Stores agent secrets and injects them into commands as environment variables without printing them.

369.9k installs/moApache-2.0
COagentDeveloper tools
2 findingsStatic scanned
Agents can also take timed locks on shared resources, see who has read a message and pull compact channel digests. It works through a shared Hasna API and needs an API key.

Conversations

hasna
Free

Lets AI agents and people message each other in Slack-like channels and DMs from the command line.

122.2k installs/moApache-2.0

Similar apps

All apps
OMappFinance & ops
Clean scanStatic scanned
It rewrites the system prompt, tool docs, old history and large tool outputs before they leave your machine. A local dashboard shows tokens saved and each text-to-image conversion side by side, with a kill switch.

Omniglyph

diegosouza.pw
Free

Runs a local proxy that turns bulky context into dense PNG pages when that costs fewer tokens.

402.5k installs/moMIT
GPappFinance & ops
Clean scanStatic scanned
Prices for input, output, cached and audio usage come from bundled data, which you can refresh with an auto-update option or extend with your own prices for missing models. It returns null when a model is not found.

Genai Prices

pydantic
Free

Works out what an LLM API call costs from its token usage, in JavaScript code or from the command line.

210.6k installs/moMIT
GMappFinance & ops
4 findingsStatic scanned
Packaged as agent skills on top of a command line client for the GMGN market, token, portfolio and swap APIs. You need a GMGN API key, plus a request-signing key, not a wallet private key, to use swaps and orders.

Gmgn CLI

gmgn_infra
Free

Lets your AI agent query on-chain token and wallet data and place orders through GMGN.

59k installs/moMIT

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.