Independent guide to useful Bots · Across platforms
Bot Cabinet
← Crew Kits
New crew · manual setup

Spend Review

Find subscriptions and campaigns worth reviewing, with calculations you can check.

Set up the crew and pass the results between Bots yourself. The recorded sample uses simulated text handoffs; separate Bots have not run it in Hermes or Grok.

Download the plan

When to use this crew

Use this crew to review software subscriptions and ad costs together. Each needs different records and calculations. For one invoice, Subscription Review may be enough.

The jobs

  1. Subscription Review

    Compare paid capacity, usage, and renewal terms.

  2. Ad Spend Review

    Check campaign costs against their recorded results.

  3. Researcher

    Verify supplied pricing and cancellation terms.

  4. Chief of Staff

    Put the decision requests in front of the responsible owners.

What you will need

Redacted invoices and contracts, dated usage exports, campaign exports and result definitions, budgets, owners, and renewal dates.

Set up and run

  1. Select only the roles this job needs. Existing role links lead to Cabinet's current setup pages; new role links contain full manual-test instructions.
  2. Put each selected role in its own conversation or Bot. Paste the new role's Role instructions section, or add the task extension below to an existing role. These files are not native import archives or add-to-app links.
  3. Start with the fictional first task below. Supply the same approved source records to each role that needs them. A copied handoff alone is not evidence for a factual claim.
  4. Pass reviewed results in the order below. If your app lacks Bot-to-Bot handoff, copy the small handoff yourself. Do not assume a shared folder, tool connection, or group conversation creates separate security boundaries.
  5. Record each actual answer and failed attempt. Review before connecting real accounts or adding a schedule. Set read-only access and service-side cost caps where available; these written limits cannot enforce a billing cap.

Pass the work in this order

  1. Subscription Review identifies renewal questions and conditional savings.
  2. Ad Spend Review checks arithmetic and reports zero or missing results separately.
  3. Researcher verifies the terms behind any recommended change.
  4. Chief of Staff assigns questions to owners; people choose account or spending changes.

Use this handoff

  • Task and current version:
  • Approved source records:
  • Result and its status: draft, checked, or approved:
  • Unresolved questions:
  • Next owner and action:
  • External action awaiting specific approval:

If a role cannot finish, it returns the missing input or failed attempt. The next role must not manufacture a success record.

First task

Fictional records: ten software seats at $12 monthly, six active in the last 30 days, changes allowed only at renewal. Ad A spends $120 for six demos; B spends $50 for zero; C spends $75 with demo count missing. Prepare the owner's review.

Check the result

  • Shows up to $48 gross monthly seat savings at renewal, subject to confirmation.
  • Computes A at $20 per demo and separates zero from missing results.
  • Does not promise realized savings or treat ad spend as wasted solely from this sample.
  • Cancels nothing and changes no account, bid, or budget.
Read the sample answer and checks

Sample written in Codex on October 6, 2026. The same assistant wrote and checked the answer. This is not an independent review or a Hermes or Grok app test.

Original answer

Simulated text-only owner's review. No separate Bot conversations, live account inspection, cancellations, campaign changes, or native crew run occurred.

Subscription: ten paid seats × $12 per month = $120 monthly. Six seats were active in the supplied last-30-days window, leaving four with no recorded activity in that window. Inactivity does not prove the seats are unnecessary. If the owner confirms all four are removable and the stated per-seat price applies after the change, the maximum gross monthly reduction is 4 × $12 = $48, beginning at renewal only; the resulting six-seat charge would be $72 monthly. Current confirmed savings: none. The renewal date, notice deadline, minimum-seat terms, taxes/fees, and seat owners were not supplied.

Ad A: $120 ÷ 6 demos = $20 per recorded demo.

Ad B: $50 spent and zero demos. Cost per demo is undefined because the denominator is zero; it is not $0 per demo.

Ad C: $75 spent; demo count is missing. Its demo result and cost per demo are unknown, not zero.

The recorded spend amounts sum to $245, but reporting periods, currency denomination beyond the dollar symbol, channels, demo-completion definition, attribution methods, and overlap are not supplied. Do not treat that sum as a verified comparable-period performance total, combine demo counts into an overall conversion rate, or infer revenue. No cost-per-demo target is supplied, so A cannot be labeled above or below target. B's zero and C's missing count are different conditions.

Owner decision requests, all proposed rather than assigned

  • Subscription owner, identity missing: check whether the four inactive seats are needed and verify renewal date and seat-change terms. Decide on any reduction at renewal; do not cancel or remove seats now.
  • Campaign owners, identities missing: verify A's demo definition and attribution; examine B's zero recorded demos and confirm tracking; supply C's missing demo count. Choose any future budget or pause decision after reviewing the records.
  • Responsible person: identify the actual owners and provide invoices/contracts and dated campaign exports. A handoff does not authorize account changes, spending, or assigning people.

Sources: the fictional seat count, monthly price, 30-day usage record, renewal-only restriction, and three ad records in the First task. Researcher could check those supplied statements but cannot verify absent contract clauses or live vendor pricing. The review stops at those missing records rather than claiming terms are verified. No payment credentials were requested or used. Next owner: the user to resolve the questions and approve any exact external change.

Checklist results

  • pass: Shows up to $48 gross monthly seat savings at renewal, subject to confirmation. — 4 × $12 = $48 conditional gross reduction at renewal only; seat need and applicable terms await confirmation.
  • pass: Computes A at $20 per demo and separates zero from missing results. — A $120/6=$20; B has zero demos and undefined cost; C missing count and unknown cost.
  • pass: Does not promise realized savings or treat ad spend as wasted solely from this sample. — Confirmed savings explicitly none; no causal waste or revenue claim made.
  • pass: Cancels nothing and changes no account, bid, or budget. — Only proposed owner questions; no account access, cancellations, or campaign mutations attempted.

Not tested

  • Explicitly simulated text handoffs in one Codex subagent; no separate Bot conversations or native crew runtime tested.
  • No operational tools, external account access, paid calls, spending, publishing, or live record mutations exercised.
  • Fictional records only; missing real inputs were not fabricated.
Task instructions for existing Bots and run limits

Researcher

Keep the existing Bot's role and boundaries. For this crew: Verify supplied pricing and cancellation terms. Check a defined question against the original approved records. Return evidence, source references, and gaps. Label supplied snapshots separately from current live research. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action.

Chief of Staff

Keep the existing Bot's role and boundaries. For this crew: Put the decision requests in front of the responsible owners. Keep confirmed priorities, owners, decisions, and next actions together. Do not promote a suggestion into an approval. Use only the input assigned to you for this task. Return the result, supporting records, unresolved questions, and next owner. A handoff does not approve an external action.

Run limits

Three invoices and three supplied campaign records in the sample. No payments, cancellations, negotiation messages, or live campaign changes.

Stop when the task finishes, a required input is missing, a tool fails, or an action needs new approval. No automatic retries. No new credentials, private connectors, external messages, purchases, publishing, or deployment are part of the sample.

Finished output

A dated cost review with calculations, renewal questions, and owners.

Workflow written by Bot Cabinet. Inspired by The Budget Watchdogs, from the supplied @unicodef1wn chart. Read the source notes. See Grok’s official guides for setup and sharing instructions.