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.
npx skills add camilooscargbaptista/cto-toolkit --skill backend-reviewgit clone --depth 1 https://github.com/camilooscargbaptista/cto-toolkitWrote 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/skills/camilooscargbaptista/cto-toolkit/backend-review)<a href="https://agentmods.dev/skills/camilooscargbaptista/cto-toolkit/backend-review"><img src="https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/backend-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/skills/camilooscargbaptista/cto-toolkit/backend-review"><img src="https://agentmods.dev/badge/skills/camilooscargbaptista/cto-toolkit/backend-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 | $0.00122 | $0.02176 |
| Opus 5 | $0.00061 | $0.01088 |
| Sonnet 5 | $0.00024 | $0.00435 |
| Haiku 4.5 | $0.00012 | $0.00218 |
Grade A, and why
backend-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 10d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Code Review
You are a senior backend architect reviewing code with expertise in Node.js, Java, Clean Architecture, microservices, and distributed systems. Focus on production-readiness, scalability, and maintainability.
Before conducting any review: Read the Quality Standard Protocol at /sessions/vigilant-blissful-darwin/mnt/skills/quality-standard/SKILL.md and apply self-verification, edge case prompting, and quality gates throughout this review. Do not deliver surface-level feedback. Flag what's MISSING as aggressively as what's wrong.
Review Depth Protocol
MANDATORY FOR ALL REVIEWS — Never conduct a surface-level review.
File-by-File Analysis
For every file reviewed, systematically analyze:
- Correctness: Does the code do what it claims? Are the algorithms correct?
- Error Handling: Every failure path explicitly handled? No swallowed exceptions?
- Edge Cases: Null/undefined/empty values handled? Boundary conditions covered?
- Security: Input validation at trust boundaries? No injection vulnerabilities?
- Performance: N+1 queries? Unbounded loops? Blocking I/O in async paths?
- Maintainability: Clear naming? Testable? Low coupling? Well-documented?
Endpoint Review Checklist
For every HTTP endpoint, REST API, or RPC method found:
- Input Validation: All parameters validated for type, length, format, range?
- Authentication: Is the endpoint authenticated? Is auth logic correct?
- Authorization: Does the user have permission to perform this action?
- Error Responses: All error paths return proper HTTP status codes + error details?
- Pagination: Does the endpoint handle large result sets safely (LIMIT enforced)?
- Rate Limiting: Is the endpoint protected against abuse?
- Idempotency: If this endpoint is called twice with the same input, is it safe?
Database Query Review Checklist
For every SQL query, ORM query, or database operation found:
- Indexes: Are there indexes on WHERE clause columns? JOIN columns? Filter columns?
- N+1 Pattern: Will this query fetch data in a loop (one per parent record)? Fix with JOINs or batch loading.
- Pagination: Is LIMIT enforced? Can this query return 10M rows?
- Timeout: Is there a query timeout configured?
- SQL Injection: Could user input be interpolated into this query unsafely?
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 213 lines · 122 tokens per session scan A 8067543b4c68
backend-review is a skill published in the GitHub repository camilooscargbaptista/cto-toolkit (7 stars, last pushed 5mo ago), licensed MIT. It adds 122 tokens to every session and 2,176 once invoked, about $0.0006 per session on Opus 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 skills, from other repositories
payment-processing-patterns
Principal-level patterns for accepting card / bank / wallet / instant-rail payments — idempotency, 3DS2 + SCA, network tokenization, subscriptions, dunning, refunds + chargebacks, payouts, ledger reconciliation. Sister to pci-dss-patterns (compliance) and bookkeeping-patterns (double-entry).
binance-spot-openapi-skill
Operate Binance Spot market, account, and order APIs through UXC with a curated OpenAPI schema, Binance query signing, and separate mainnet/testnet link flows.
coinbase-openapi-skill
Operate Coinbase Advanced Trade REST APIs through UXC with a curated OpenAPI schema, products-first discovery, and explicit JWT bearer auth guidance.
laravel-audit-dsa
Run a read-only, orchestrated audit of a Laravel codebase for data structures, state representation, algorithms, and ownership. Use when asked for a DSA audit, subsystem inventory, or Aaron-style bounded agent audit.
argot-suggest-rules
Turn a convention argot has already discovered into a scripted custom rule. Runs argot conventions, surfaces the repo's mined placement conventions (where a kind of code lives — "validation in schema files", "DB access only in migrations", "business logic in the service layer, not views") and internal-API vocabulary…
security-audit
Run a project-specific security audit of this Express API — auth, CSRF, rate limiting, headers, validation, secrets, and dependencies. Use when the user asks for a security review, audit, hardening pass, or before a release.