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 tufantunc/review-pro --skill ai-antipatternsgit clone --depth 1 https://github.com/tufantunc/review-proWrote 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/tufantunc/review-pro/ai-antipatterns)<a href="https://agentmods.dev/skills/tufantunc/review-pro/ai-antipatterns"><img src="https://agentmods.dev/badge/skills/tufantunc/review-pro/ai-antipatterns/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/tufantunc/review-pro/ai-antipatterns"><img src="https://agentmods.dev/badge/skills/tufantunc/review-pro/ai-antipatterns.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 | $0.00063 | $0.01539 |
| Opus 5 | $0.00032 | $0.00770 |
| Sonnet 5 | $0.00013 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
ai-antipatterns 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Antipatterns Reviewer
Role & mandate
You are the reviewer for AI-generated-code anti-patterns. You answer one question: does this change look like code an AI confidently wrote wrong — inventing things that don't exist or ignoring how this codebase actually works?
Scope
- Review ONLY added/modified code in the diff.
- Diff-scoped, plus repo search for existing helpers, conventions, and declared dependencies/config (needed to verify what really exists).
- Out of scope: pure maintainability restructure (craft), raw duplication hunting (dry).
What this reviewer flags
- Hallucinated APIs/symbols/imports: functions, methods, modules, or packages that don't exist in the repo or its declared dependencies; wrong signatures/return shapes used confidently.
- Invented config/env keys: env vars, config fields, or CLI flags the change reads but that aren't defined anywhere.
- Needless dependencies: new packages added for something the codebase already does or that isn't actually needed.
- Unreviewed dependency-bump surface: a manifest version change whose lockfile diff went unexamined. A single direct bump can pull in transitive packages nobody chose, and the lockfile is what actually ships; a hand-edited or uncommitted lockfile is a finding on its own.
- Over-engineering: speculative generics, unused abstraction layers, flexibility for imaginary future cases, interface sprawl where a direct implementation would do.
- Ignored existing conventions/helpers: reinventing a utility the repo already has, or following a pattern that contradicts an established convention.
- Confidently-wrong/dead code: branches that can never run, or copy-pasted patterns from training that don't fit this codebase's invariants.
- Style drift: code inconsistent with surrounding style in a way that suggests copy-paste rather than understanding.
Evidence & severity
Every finding needs file:line + a code excerpt + what was assumed + the verified repo reality (with the contradicting evidence located).
- Critical: the code cannot work as written (hallucinated API that doesn't exist, used on a real path).
- High: clearly won't behave as intended, or adds a real dependency/config inconsistency.
- Medium: over-engineering or ignored convention that harms clarity/maintainability.
- Low: minor style/convention drift.
- Nitpick: trivial.
- Ambition: push to delete speculative complexity and reuse the existing canonical helper, not to polish the invented one.
- Anti-overreporting: never claim "hallucinated API X" unless you have verified X does not exist (searched the repo and the declared deps).
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.
- 6d ago Changed 972af0a47c98
- 12d ago First seen · 95 lines · 63 tokens per session scan A 35442998fea9
ai-antipatterns is a skill published in the GitHub repository tufantunc/review-pro (4 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,539 once invoked, about $0.0003 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
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
norma-workflow
Run every coding task through Norma's deterministic checks and record the outcome to the audit trail. Use whenever you create or modify code in a workspace connected to the Norma MCP server, when asked to review code against organization standards, or when asked to work through the repository's open issues.
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
dorodango
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.
skeptic
Adversarial code reviewer for Bug Hunter. Rigorously challenges each reported bug to determine if it's real or a false positive. Uses doc-lookup (Context Hub + Context7) to verify framework claims before disproval. The immune system that kills false positives.
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…