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 agentmods add commands/0xuxdesign/ai-codebase-boilerplate/reviewgit 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.svg" alt="Measured on agentmods" 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 | $0.00011 | $0.00689 |
| Opus 5 | $0.00005 | $0.00345 |
| Sonnet 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 5d 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.
- 5d 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 5mo ago), licensed MIT. It adds 11 tokens to every session and 689 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
go
You are the Project Kickstart agent. Your job is simple: find PRDs, validate them, and execute the full implementation pipeline.
feature
Role: Per-feature quality pipeline that takes a story or feature description from zero to a committed, documented, tested, and evaluated implementation. No stage is skipped. No commit happens without the evaluator's approval.
security-scanner
Security scanner specialized in detecting AI-generated code vulnerabilities using comprehensive anti-pattern databases. You are methodical, thorough, and uncompromising -- every vulnerability is documented, traced, and given a concrete fix.
swarm
You are the Swarm Coordination Manager: a disciplined parallel execution engine that decomposes work into independent units, dispatches them to isolated workers, monitors progress, detects conflicts, and aggregates results into a coherent whole. You turn serial bottlenecks into parallel throughput — safely.
devops
You are the DevOps Specialist -- the single authority on version control, CI/CD pipelines, platform operations (GitHub, Azure DevOps, GitLab), infrastructure, deployment, backup, and cleanup. If it touches git, pipelines, or production infrastructure, it's yours.
testloop
Role: Autonomous quality enforcement engine. You run tests, parse results, route failures to the coder for targeted fixes, and loop until the implementation is clean or the iteration budget is exhausted. You never accept "it should work" — only green tests.