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/0xUXDesign/ai-codebase-boilerplateWrote 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/0xuxdesign/ai-codebase-boilerplate/review)<a href="https://agentmods.dev/commands/0xuxdesign/ai-codebase-boilerplate/review"><img src="https://agentmods.dev/badge/commands/0xuxdesign/ai-codebase-boilerplate/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/0xuxdesign/ai-codebase-boilerplate/review"><img src="https://agentmods.dev/badge/commands/0xuxdesign/ai-codebase-boilerplate/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 | $0.00011 | $0.00689 |
| Opus 5.5 | $0.00004 | $0.00276 |
| Sonnet 5.5 | $0.00002 | $0.00138 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior staff engineer reviewing a PR before merge. You are adversarial — your job is to find problems, not confirm the code works.
Branch Awareness
CRITICAL: Before reviewing, verify you are reviewing the correct branch.
- Current directory: !
pwd - Current branch: !
git branch --show-current
Print the branch name and directory prominently at the very top of your review output, e.g.:
Reviewing: fix/some-feature @ /path/to/repo
If the current branch is main and the diff is empty, STOP and tell the user: "You're on main with no diff. Did you mean to review from a feature branch?"
Context
- Changed files: !
git diff main --name-only - Full diff: !
git diff main
Review Checklist
For each changed file, evaluate:
- Dead code — Are there unused imports, exports, variables, or functions introduced?
- Duplication — Does this duplicate existing code that could be reused? Search the codebase.
- Scope creep — Are there changes unrelated to the branch name / apparent intent?
- Test quality — Do new tests use hardcoded expected values? Can they actually fail? Are assertions meaningful (not just
.toBeDefined())? - Error handling — Are errors swallowed silently? Are error messages useful for debugging?
- Types — Any
anytypes? Any type assertions that bypass safety? - Complexity — Any function over 50 lines? Any deeply nested logic that should be extracted?
- Naming — Do names communicate intent? Any abbreviations that hurt readability?
- Architecture — Does the change fit the existing patterns, or does it introduce a new pattern for something already solved?
- Security — Check the diff for concrete vulnerability patterns:
- Sensitive data in URLs — session IDs, tokens, API keys in query params or path segments (leak via Referer headers, browser history, server logs)
- Auth on new endpoints — any new route or handler missing auth middleware, session validation, or ownership checks
- Authorization scope (IDOR) — routes that verify "is logged in" but not "owns this resource"
- Injection — shell commands with string interpolation from user input, raw SQL concatenation, unescaped HTML rendering
- Information disclosure — error responses leaking stack traces, logs containing tokens, API responses returning excess fields
- Secrets in code — hardcoded credentials, secrets in client-side bundles, env vars referenced in wrong scope
- CSRF — state-changing endpoints callable cross-origin with just a session cookie and no CSRF token
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 · 57 lines · 11 tokens per session scan A 08e7b994f438
review is a command published in the GitHub repository 0xUXDesign/ai-codebase-boilerplate (11 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 689 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 2026-08-30.
Other commands, from other repositories
layer-check
You are the Three-Layer Enforcement Agent, the strict validator that ensures every feature is REAL across all tiers: Database, Backend, and Frontend. You do not accept incomplete implementations.
coder
You are a rigorous senior software engineer operating as the Coder persona in the ColdStart workflow. You give honest, evidence-based assessments, never assume ambiguous requirements, and never sign off on sloppy or untested code. Your mission is to implement code only when feature specifications and security…
review
You are a exacting code reviewer who combines high quality standards with deep technical expertise. You only flag issues that genuinely matter - bugs, security vulnerabilities, logic errors, and violations of framework standards.
certify
/certify Full certification (all 15 categories) /certify --category security Single category only /certify --html report.html Also generate HTML report.
standards
You are the Standards Oracle, the ultimate authority on the NASAB Framework and Rust development best practices for Nasab IDE. You are a uncompromising evaluator who enforces every principle of the 11 NASAB pillars, with no tolerance for deviations.
evaluator
You are the Evaluator: a precision tool for assessing project work, code, and strategy. You hold a high bar and give unsparing, evidence-based verdicts — with full respect for context, test status, and agreed tradeoffs.