saas-spend-audit SKILL.md skillA

saas-spend-audit from trevhud/rote is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add trevhud/rote/saas-spend-audit@git:20261020.d5cace8

Pins git:20261020.d5cace8 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
trevhud/rote
Path
examples/holdout/saas-spend-audit/skill/SKILL.md
Versions recorded
1
Latest version
git:20261020.d5cace8, committed Oct 20, 2026
Size
4,646 bytes
Repository stars
8
License
Apache-2.0

Monthly SaaS spend audit for finance ops. Pulls the month's software card spend from Ramp, the vendor register from Google Sheets and per-app seat usage from Okta, works out which vendor every charge belongs to, runs the audit rules, gets the finance lead's keep / cancel / renegotiate call on every flagged vendor, and logs the actions in the Procurement Requests sheet. Use for "run the SaaS audit", "software spend review for <month>", or "who are we paying for tools we don't use".

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

# Monthly SaaS spend audit

Run on the 3rd business day of the month, for the month that just closed.
Inputs: the first and last day of that month (`YYYY-MM-DD`).

## Data

Pull these three at the same time. None of them needs the others.

| Source | Tool | Details |
| --- | --- | --- |
| Card spend | `list_transactions` (Ramp MCP) | `from_date` / `to_date` = the month, `category` = `software` |
| Vendor register | `read_sheet_values` (Google Sheets MCP) | spreadsheet `1VendorRegisterExampleSheetId000000000000`, range `Register!A:J` |
| Seat usage | `get_app_usage` (Okta MCP) | once per Okta app id listed in the register, `days` = 30 |

The register has one row per approved vendor: vendor, card descriptor,
category, budget owner, contracted monthly price (USD), paid seats, Okta
app id (blank if the tool isn't behind Okta), renewal date, auto-renew
(Y/N), notes. Skip the header row and any row with a blank vendor.

Seat usage needs the register's Okta app ids, so read the register first,
then fan out over the ids.

## Match charges to vendors

Card merchant strings are messy (`SQ *FIGMA`, `ATLASSIAN* JIRA SOFTWARE`,
`PADDLE.NET* LINEAR`). Group the month's transactions by merchant
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add trevhud/rote/saas-spend-audit@sha256:1c70c8d9c45d7703

The line at the top of this page pins the label git:20261020.d5cace8, 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_6sni3f5n7uw4m4g5.svg)](https://markdownregistry.com/a/art_6sni3f5n7uw4m4g5)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 20, 2026.

versioncommittedcommitsizeaudit
git:20261020.d5cace8 latest2026-10-20 d5cace8 4,646 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 (4646 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

trevhud/rote · 8 stars · license Apache-2.0 · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_6sni3f5n7uw4m4g5
GET https://markdownregistry.com/api/v1/resolve?ref=trevhud/rote/saas-spend-audit
GET https://markdownregistry.com/api/v1/blob/1c70c8d9c45d7703261bb2d01ce99fbab7f4ff99f7a8579dc639553f0a9743e7

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 trevhud/rote

AGENTS.md AGENTS.md file
trevhud/rote · AGENTS.md
git:20261021.272666a · audit A · 8 stars
CLAUDE.md CLAUDE.md file
trevhud/rote · CLAUDE.md
git:20261022.c685456 · audit A · 8 stars
bdr-outreach SKILL.md skill
trevhud/rote · examples/bdr-outreach/skill/SKILL.md · End-to-end BDR outreach campaign workflow. Use when running pharma/biotech outreach campaigns: finding leads via…
git:20260407.fe83e92 · audit A · 8 stars
deal-monitor SKILL.md skill
trevhud/rote · examples/deal-monitor/skill/SKILL.md · Scheduled morning dashboard for a fulfillment brokerage's deal pipeline. Pulls the #deal-intake Slack channel and Gmail…
git:20260710.d1736d9 · audit A · 8 stars
expense-audit SKILL.md skill
trevhud/rote · examples/expense-audit/skill/SKILL.md · Month-end audit of employee expense reports. Takes the month's export from the expense tool, converts every line to USD…
git:20261018.2fbef89 · audit A · 8 stars
customer-onboarding SKILL.md skill
trevhud/rote · examples/holdout/customer-onboarding/skill/SKILL.md · Onboard a new customer once their deal is closed-won in HubSpot. Pulls the deal, screens the company, checks the terms…
git:20261020.d5cace8 · audit A · 8 stars
incident-triage SKILL.md skill
trevhud/rote · examples/holdout/incident-triage/skill/SKILL.md · First-responder triage for a PagerDuty page. Acknowledges the incident, figures out which service is hurting and who…
git:20261020.d5cace8 · audit A · 8 stars
sequence-load SKILL.md skill
trevhud/rote · examples/holdout2/apollo-sequence-load/skill/SKILL.md · Find leads matching criteria and bulk-add them to an Apollo outreach sequence. Handles enrichment, contact creation…
git:20261022.f72c049 · audit A · 8 stars
call-prep SKILL.md skill
trevhud/rote · examples/holdout2/call-prep/skill/SKILL.md · Pre-call brief for an upcoming meeting - attendees, account history, prior call context from transcripts, open…
git:20261022.f72c049 · audit A · 8 stars
crm-hygiene-check SKILL.md skill
trevhud/rote · examples/holdout2/crm-hygiene-check/skill/SKILL.md · Read-only audit of your CRM opportunities for missing fields, stale dates, and stage mismatches - outputs a fix…
git:20261022.f72c049 · audit A · 8 stars
huggingface-best SKILL.md skill
trevhud/rote · examples/holdout2/hf-best-model/skill/SKILL.md · Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to…
git:20261022.f72c049 · audit A · 8 stars
hiring-screener SKILL.md skill
trevhud/rote · examples/holdout2/hiring-screener/skill/SKILL.md · Takes a pile of applications and turns it into a ranked shortlist, scored only against the job's stated rubric, with…
git:20261022.f72c049 · audit A · 8 stars

Every file in trevhud/rote

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