What is project-costs?

A project cost report for cloud services, including Amazon Web Services (AWS) and Databricks. It runs the project’s cost command and adds written analysis to the generated report.

Review cloud spend by week, service, Databricks billing category, job, or data pipeline. It writes the analysis into a dated Markdown report and reports the findings in chat.

It turns raw spending tables into an explanation of cost trends, unusual spikes, and differences between AWS and Databricks.

project-costs — Skill for Claude Code by andre-salvati

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.

Any agent

npx skills add andre-salvati/databricks-template --skill project-costs

Clone the repo

git clone --depth 1 https://github.com/andre-salvati/databricks-template

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andre-salvati/databricks-template/project-costs/github.svg)](https://agentmods.dev/skills/andre-salvati/databricks-template/project-costs)

Your own site

<a href="https://agentmods.dev/skills/andre-salvati/databricks-template/project-costs"><img src="https://agentmods.dev/badge/skills/andre-salvati/databricks-template/project-costs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andre-salvati/databricks-template/project-costs"><img src="https://agentmods.dev/badge/skills/andre-salvati/databricks-template/project-costs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,549 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00093	$0.01549
Opus 5.5	$0.00037	$0.00620
Sonnet 5.5	$0.00019	$0.00310
Haiku 4.5	$0.00009	$0.00155

Measured 2mo ago against content hash 623fbcb41dd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-costs 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 2mo 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/skills/project-costs/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project cost analysis

Run the project cost script, analyze the output for anomalies, spikes and trends, and write the analysis into the generated markdown report.

Steps

Run make project-costs via Bash and capture the full output. It prints to stdout and writes reports/cost/YYYY-MM-DD.md (gitignored) containing every table in markdown, ending with an empty ## Analysis section. The script writes only numbers, never prose.
Analyze the output (see below).
Edit reports/cost/YYYY-MM-DD.md and replace the ## Analysis placeholder with your written analysis. Do not retype the tables — they are already in the file, and re-transcribing numbers risks introducing errors. Reference them instead.
Report the same analysis back in chat, and link the report path.

If make project-costs fails to reach Databricks with an auth error, the dev profile's OAuth refresh token has expired. Tell the user to run ! databricks auth login --profile dev in the session, then re-run. Do not attempt the browser login yourself.

What the script emits

Four tables, and only four:

AWS by Week × Service (USD, Total column)
Databricks by Week × SKU (USD at list price, Total column)
Combined Totals by Service across both clouds — native Quantity/Unit plus a totalled USD column. This is the only place native DBU/DSU/GB quantities appear.
Databricks by Job / Pipeline — one row per job or SDP pipeline that incurred spend, with Kind, native Quantity/Unit, USD and Days (distinct days with usage). In the generated report it sits directly after Combined Totals; on stdout it prints last.

Databricks usage is monetized by joining system.billing.list_prices inside the script, so DBU/DSU /GB and AWS dollars are directly comparable.

Per-day data is not printed to stdout — it lives only in the collapsed <details> blocks of the generated report. You will need it: the weekly pivots average single-day spikes away, and those blocks are the only place a spike can be attributed to a date. Read the report file, don't ask the script for a daily table.

Read the full file on GitHub · 108 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

examples/2026-07-22.md 23 KB

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.

2mo ago First seen · 108 lines · 93 tokens per session scan A 623fbcb41dd1

Subscribe to this mod's changes

project-costs is a skill published in the GitHub repository andre-salvati/databricks-template (87 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,549 once invoked, about $0.0004 per session on Opus 5.5. 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.

Analytics and metrics Finance and fintech data-engineering databricks github-actions medallion-architecture pyspark unity-catalog

project-costs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
project-costsandre-salvati/databricks-template	Skill	87	1mo ago	Apache-2.0	A	93	Claude Code
databricks-expertpersonamanagmentlayer/pcl	Skill	44	12d ago	Apache-2.0	A	74	Claude Code
databricks-dashboardmexmarv/ai-genie-factory	Skill	5	2mo ago	MIT	A	146	Claude Code, Codex
ui-ux-patternsmexmarv/ai-genie-factory	Skill	5	2mo ago	MIT	A	149	Claude Code, Codex
dlt-pipelinemexmarv/ai-genie-factory	Skill	5	2mo ago	MIT	A	122	Claude Code, Codex
data-accessmexmarv/ai-genie-factory	Skill	5	2mo ago	MIT	A	85	Claude Code, Codex
databricks-appmexmarv/ai-genie-factory	Skill	5	2mo ago	MIT	A	63	Claude Code, Codex