B. Quality, Speed & Resilience · Prompt 23

Why it matters

The bill that ends a side project is often one loop calling a paid API, not the base hosting fee.

Modeled on

FinOps checks of the kind tools such as Infracost popularized for infrastructure cost.

How to run this prompt

1. Switch to a mode that does not edit files. In Cursor that is Ask or Plan. In Claude Code that is Plan mode.
2. Paste the audit prompt. Wait for the report. It must stop and ask which IDs to fix.
3. Read the report. Keep the IDs you agree with.
4. Switch to a mode that can edit. Paste the fix prompt and the IDs you chose.
5. Switch back to the read-only mode and paste the same audit prompt again. Confirm those IDs are gone.

• Cursor: audit in Ask mode or Plan mode. Fix in Agent mode.
• Claude Code: audit in Plan mode (Shift+Tab cycles to it). Fix in Normal mode, which can edit.
• Any other tool: audit in Chat, Discuss, or Plan mode, whichever answers without editing files. If the tool has no such mode, the prompt itself forbids edits. Fix in the mode that is allowed to edit files.

MODE: AUDIT ONLY. Do not create, edit, or delete any file. Do not run commands
that change anything: no installs, migrations, git commits, deploys, or "--fix" flags.
If your tool has an Ask, Plan, Chat, or Discuss mode, use it for this prompt.

Before you start:
- Tell me the stack you detect (framework, language, database, auth, hosting,
  payment provider) and which folders you will review.
- If a check below does not apply to this stack, write "Not applicable" and why.
- If you can run read-only commands, run the ones listed. If you cannot, list them
  so I can run them and paste the output.

Cost & Resource Efficiency: what to check
Look for code that can make a cloud or API bill jump. Do not change quotas. Do not guess a dollar amount you cannot compute from the repo.
1. Find loops or retries that call a paid API (AI, SMS, email, maps) with no maximum attempts and no per-user cap.
2. Find an expensive call that repeats for the same input with no cache and no memoization.
3. Find uploads with no size limit. Say which route.
4. Find cron jobs or queues that can run more often than intended, or a worker with no stop condition.
5. Find a path where one user can trigger unlimited paid work on your account.
6. Note infrastructure config that is always on for work that looks occasional. If the host config is not in the repo, mark Needs manual check. Do not invent the monthly cost.
7. Order the list by what could spike first. For each, name the guardrail (max attempts, max bytes, max calls per user per day) as a suggestion.
8. Do not apply the guardrails in this pass.

Evidence rules:
- Every finding cites a file path and line number, or the exact command output used.
- Mark each finding Confirmed (seen in the code) or Needs manual check (depends on
  something outside the repo, such as a dashboard setting or production data).
- Never print a full secret. Show the first 4 characters and the location only.
- If you are not sure, say so. Do not invent files, settings, or results.

Severity: Critical = exploitable now, or leaks real data or money. High = serious
with little effort. Medium = weakens defenses or needs a second bug. Low = hygiene.

Report:
- Summary: count of findings by severity.
- Table: ID | Severity | Confirmed? | Finding | Evidence | Why it matters | Suggested fix | Effort
  (IDs for this prompt use the prefix P23, for example P23-1, P23-2.)
- Checked and fine: what you verified is already OK.
- Could not check: what I need to look at myself, and where.

Then stop. Do not fix anything. Ask me which IDs I want fixed.

Related prompts

• 22. Test Coverage & Quality
• 24. Error Handling & Observability

Share this prompt