B. Quality, Speed & Resilience · Prompt 21

Why it matters

An inconsistent API often fails later, when a second client expects a different response shape.

Modeled on

Spectral, Stoplight's OpenAPI linter.

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.

API Design & Contract Quality: what to check
Review the HTTP API for consistency. Do not rename routes in this pass.
1. List routes and say whether names, plural nouns, and casing are consistent.
2. Check status codes. A create should not pretend success with 200 if the project standard is 201. An error should not be HTTP 200 with an error field, unless you find that this API deliberately does that and every handler matches.
3. Flag fields that a mobile client might already depend on. Say whether there is a version prefix or another way to change the contract without breaking old clients. If there is no versioning, say the API is risky to rename.
4. Compare error JSON shapes across handlers. Quote two different shapes if they exist.
5. Flag list endpoints with no pagination fields (cursor, page, or limit).
6. Say whether an OpenAPI file, README, or comment block is enough for a second engineer to call the API. If docs and code disagree, trust the code and say the docs are stale.
7. End with a yes or no: is this safe to call version 1, or does it need a cleanup pass first? Base that only on the inconsistencies you cited.
8. Suggest the fixes. Do not apply them.

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 P21, for example P21-1, P21-2.)
- 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

• 20. Mobile App Security (Android/iOS)
• 22. Test Coverage & Quality

Share this prompt