token-accountant SKILL.md skillA

token-accountant from alebgl77/claude-inc is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add alebgl77/claude-inc/token-accountant@git:20260713.f3dd6ed

Pins git:20260713.f3dd6ed in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
alebgl77/claude-inc
Path
skills/token-accountant/SKILL.md
Versions recorded
1
Latest version
git:20260713.f3dd6ed, committed Jul 13, 2026
Size
3,177 bytes
Repository stars
22
License
MIT

The company audits its own payroll — tracks AI token spend per department and mission, estimates costs from session data or telemetry, sets budget alerts and writes the monthly cost memo. Use when the user says "how much is this costing me", "token spend", "AI budget", "cost per mission", or wants FinOps visibility on their AI usage.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Token Accountant — The Bean Counter

> "The first company whose payroll is measured in tokens."

*Staff position — reports to the CFO. Audits everyone, including the CEO.*

## When to use

- "How much did this mission cost?"
- "Track my token spend by department"
- "Set a monthly AI budget and warn me"
- "Write the monthly cost memo"
- Works with whatever is available: `/cost` output pasted by the user, Claude Code telemetry (OTel), API invoices, or honest estimation from transcript volume — always labels which

## Workflow

1. **Establish the data source** and label the confidence: EXACT (telemetry/invoice/`/cost` pasted), ESTIMATED (transcript length × model rates), or MIXED. Never present estimates as measurements.
2. **Maintain the books** at `token-ledger.md`: date, mission, department(s), input/output tokens (or estimate), model, cost, cumulative month-to-date.
3. **Attribute by department**: tag each mission's cost to the departments the CEO engaged (a /company mission fans out — attribute per subagent when known, else split with a stated rule).
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add alebgl77/claude-inc/token-accountant@sha256:24565557633527b1

The line at the top of this page pins the label git:20260713.f3dd6ed, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_nffnxzyny2fishte.svg)](https://markdownregistry.com/a/art_nffnxzyny2fishte)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 13, 2026.

versioncommittedcommitsizeaudit
git:20260713.f3dd6ed latest2026-07-13 f3dd6ed 3,177 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3177 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

alebgl77/claude-inc · 22 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_nffnxzyny2fishte
GET https://markdownregistry.com/api/v1/resolve?ref=alebgl77/claude-inc/token-accountant
GET https://markdownregistry.com/api/v1/blob/24565557633527b1b1f8842544f8b7fe197f77ef442aba1daa651bf1f260ea9b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from alebgl77/claude-inc

account-intelligence SKILL.md skill
alebgl77/claude-inc · skills/account-intelligence/SKILL.md · Senior account intelligence analyst for B2B ICP research, explainable account qualification and signal validation…
git:20260926.09b173a · audit A · 22 stars
account-research SKILL.md skill
alebgl77/claude-inc · skills/account-research/SKILL.md · Researches a company or person and returns actionable sales intel — what they do, recent signals, likely pains, entry…
git:20260713.f3dd6ed · audit A · 22 stars
ad-creative SKILL.md skill
alebgl77/claude-inc · skills/ad-creative/SKILL.md · Generates batches of ad concepts — headlines, primary text, and visual briefs — organised by angle and awareness level…
git:20260711.2713ff9 · audit A · 22 stars
agent-evaluation SKILL.md skill
alebgl77/claude-inc · skills/agent-evaluation/SKILL.md · Measures a skill's practical value with fixed business tasks, paired with-skill and without-skill trials, explicit…
git:20260908.272d42d · audit A · 22 stars
agent-reliability SKILL.md skill
alebgl77/claude-inc · skills/agent-reliability/SKILL.md · Diagnoses AI workflow failures from reproducible evidence, defines operational measures, and prepares a bounded…
git:20260926.09b173a · audit A · 22 stars
ai-adoption-lead SKILL.md skill
alebgl77/claude-inc · skills/ai-adoption-lead/SKILL.md · Turns a reviewed AI workflow into a bounded team pilot with practical instructions, acceptance evidence, feedback, and…
git:20260926.09b173a · audit A · 22 stars
ai-data-steward SKILL.md skill
alebgl77/claude-inc · skills/ai-data-steward/SKILL.md · Creates a minimal, sourced, versioned context contract for AI-assisted work across teams, including freshness, quality…
git:20260926.09b173a · audit A · 22 stars
ai-seo SKILL.md skill
alebgl77/claude-inc · skills/ai-seo/SKILL.md · Optimizes content to get cited by AI assistants (ChatGPT, Perplexity, Google AI Overviews) and rank in classic SERPs —…
git:20260711.13c718d · audit B · 22 stars
ai-workflow-architect SKILL.md skill
alebgl77/claude-inc · skills/ai-workflow-architect/SKILL.md · Designs a bounded AI-assisted process across departments with explicit inputs, ownership, handoff contracts, acceptance…
git:20260926.09b173a · audit A · 22 stars
appsec-review SKILL.md skill
alebgl77/claude-inc · skills/appsec-review/SKILL.md · Produces a bounded defensive application security review: threat model, security-sensitive diff, dependencies, and…
git:20260908.272d42d · audit A · 22 stars
audit-support SKILL.md skill
alebgl77/claude-inc · skills/audit-support/SKILL.md · Gets the books audit-ready: builds the PBC (prepared-by-client) list by area, drafts walkthrough narratives for key…
git:20260711.2713ff9 · audit A · 22 stars
brand-guidelines SKILL.md skill
alebgl77/claude-inc · skills/brand-guidelines/SKILL.md · Generates a brand kit from a company one-liner — positioning adjectives, a palette with hex codes, usage ratios and…
git:20260711.13c718d · audit A · 22 stars

Every file in alebgl77/claude-inc

Browse by kind, by grade A, or by owner.