assess

assess is a command for coding agents from CPUtester5465/countbean-plugin. It costs 27 tokens per session (721 once invoked), scanned A, original, MIT.

A command that reviews a personal spending ledger and reports what the recorded numbers show, including spending rates, categories, changes, unusual entries, and missing data.

In plain words
What is it for?
Use it to assess recorded spending, compare complete months, identify unusual account activity, and explain what additional records are needed before drawing conclusions.
Why use it?
It prevents guesses caused by incomplete months, unclear date ranges, or incorrectly calculated figures by relying on the ledger's assessment tool and its rules.

Command

Part of the countbean plugin — 1 skill, 7 commands, 1 MCP server shipped together

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 commands/cputester5465/countbean-plugin/assess
Clone the repo
git clone --depth 1 https://github.com/CPUtester5465/countbean-plugin

Or install countbean, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 1 MCP server.

Wrote 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.

agentmods badge for assess

README.md
[![agentmods](https://agentmods.dev/badge/commands/cputester5465/countbean-plugin/assess.svg)](https://agentmods.dev/commands/cputester5465/countbean-plugin/assess)
Your own site
<a href="https://agentmods.dev/commands/cputester5465/countbean-plugin/assess"><img src="https://agentmods.dev/badge/commands/cputester5465/countbean-plugin/assess.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 721 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00027 $0.00721
Opus 5 $0.00014 $0.00360
Sonnet 5 $0.00005 $0.00144
Haiku 4.5 $0.00003 $0.00072

Measured 4d ago against content hash dad587dcbffc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

assess 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 4d 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.

plugin/commands/assess.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review the user's book and report findings. Focus, if given: $ARGUMENTS

Call assess_book and report what it returns. Do not do your own arithmetic on the ledger. The tool computes every figure, and it computes them carefully — which months are complete, whether there is enough data for a run rate, what counts as unusual for a given account. Those decisions are the difference between a report and a guess.

The rules, in order of how much damage breaking them does

  1. sufficient: false means you do not have the number. It is not a number with a caveat. Say what is missing and what would fix it — usually "another month or two of recording". Never estimate around it, never say "roughly" or "on track for".

  2. Only complete months are averaged. The tool marks each month complete. The current month is almost never complete, and including it makes spending look like it fell in every category. Report the current month as its own line, clearly labelled as still in progress.

  3. State the window. Every finding is about coverage.first_date to coverage.last_date. A reader who does not know the window cannot judge anything you say.

  4. An outlier is not an error. outliers are postings large relative to their own account. The annual insurance premium lands here every year and is correct. Present them as "worth a look", never as mistakes, and never imply fraud.

  5. posting_count is postings, not transactions. One transaction has at least two. Do not call it a transaction count.

  6. Do not advise on tax, or tell the user what to do with their money. Describe what the book shows. If they ask what to do about it, answer as a bookkeeper would — what the numbers mean — and suggest their accountant for anything that turns on jurisdiction or intent.

Shape of the report

Lead with the window and one honest sentence about what the data can support. Then:

  • Where the money went — top categories from categories, with shares. Group the long tail.
  • What changedmovers between the two named complete months. pct_change: null with note: "new this month" means a new category, not infinite growth.
  • Run rate — from run_rate if sufficient, always with months_used. If it carries a runway_months, quote runway_note alongside it: it assumes the next months look like the last ones, which is an assumption and should be said out loud.
  • Worth a lookoutliers, with the account's own median for context.
  • Gapsdata_quality. These are the findings the user can act on immediately, and uncategorised spending makes every category figure above it less trustworthy, so say so.

Read the full file on GitHub · 53 lines

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. 4d ago First seen · 53 lines · 27 tokens per session scan A dad587dcbffc

Subscribe to this mod's changes

assess is a command published in the GitHub repository CPUtester5465/countbean-plugin (46 stars, last pushed 9d ago), licensed MIT. It adds 27 tokens to every session and 721 once invoked, about $0.0001 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 2026-08-30.