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.
git clone --depth 1 https://github.com/VersoXBT/claude-initial-setupWrote 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.
[](https://agentmods.dev/commands/versoxbt/claude-initial-setup/api-review)<a href="https://agentmods.dev/commands/versoxbt/claude-initial-setup/api-review"><img src="https://agentmods.dev/badge/commands/versoxbt/claude-initial-setup/api-review/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.
<a href="https://agentmods.dev/commands/versoxbt/claude-initial-setup/api-review"><img src="https://agentmods.dev/badge/commands/versoxbt/claude-initial-setup/api-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00009 | $0.00504 |
| Opus 5.5 | $0.00004 | $0.00202 |
| Sonnet 5.5 | $0.00002 | $0.00101 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
api-review 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Review
Review API endpoints for adherence to REST conventions, proper error handling, and documentation.
Steps
-
Inventory all API endpoints:
- List every route with its HTTP method, path, and handler.
- Group endpoints by resource (users, orders, products, etc.).
- Identify any endpoints that do not follow RESTful naming conventions.
-
Check REST conventions:
- Verify correct HTTP methods: GET (read), POST (create), PUT/PATCH (update), DELETE (remove).
- Verify resource-based URLs (nouns, not verbs):
/users/:idnot/getUser. - Verify plural resource names:
/usersnot/user. - Check that nested resources are properly scoped:
/users/:id/orders. - Verify consistent URL casing (kebab-case preferred).
-
Validate request handling:
- All request bodies are validated with a schema before processing.
- Query parameters are validated and sanitized.
- Path parameters are validated (type, format, existence).
- Content-Type headers are checked and enforced.
-
Review error responses:
- Verify consistent error response format across all endpoints.
- Check that appropriate HTTP status codes are used (400, 401, 403, 404, 409, 422, 500).
- Confirm error messages are helpful but do not leak internal details.
- Verify that validation errors return specific field-level messages.
-
Check pagination, filtering, and sorting:
- List endpoints return paginated results (not unbounded queries).
- Pagination uses consistent parameters (page/limit or cursor-based).
- Filtering and sorting are supported where appropriate.
- Response includes total count and pagination metadata.
-
Review authentication and authorization:
- All protected endpoints require authentication.
- Authorization checks enforce proper access levels per endpoint.
- Public endpoints are intentionally and explicitly public.
-
Check API documentation:
- All endpoints are documented with request/response schemas.
- Examples are provided for common use cases.
- Error responses are documented.
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.
- 1mo ago First seen · 60 lines · 9 tokens per session scan A cbab7943caf3
api-review is a command published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 504 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
unity-review
Full Unity-aware code review — checks serialization safety, performance, architecture, and Unity-specific pitfalls.
story-continue
Resume an interrupted story from where you left off.
contract
Contract-First — defines the interface, writes contract tests, then implements. Use when building a new component or port and the abstraction must come before the code.
refactor
A guided code-refactoring command that changes a chosen module, file, or subsystem while aiming to keep its behavior unchanged.
dev-api
Create or document REST, GraphQL, or tRPC endpoints, with a versioning strategy.
review-pr-staging
Staging review mode — comprehensive review of staging branch before deploy to main.