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 Smirnov-Labs/claude-skills --skill detect-overengineeringgit clone --depth 1 https://github.com/Smirnov-Labs/claude-skillsWrote 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/smirnov-labs/claude-skills/detect-overengineering)<a href="https://agentmods.dev/skills/smirnov-labs/claude-skills/detect-overengineering"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/detect-overengineering/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/smirnov-labs/claude-skills/detect-overengineering"><img src="https://agentmods.dev/badge/skills/smirnov-labs/claude-skills/detect-overengineering.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 | $0.00089 | $0.01621 |
| Opus 5 | $0.00044 | $0.00811 |
| Sonnet 5 | $0.00018 | $0.00324 |
| Haiku 4.5 | $0.00009 | $0.00162 |
Grade A, and why
detect-overengineering 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 12d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
detect-overengineering
Audit an implementation plan document for LLM-style overengineering. Two passes (rubric-driven Claude pass + Codex adversarial pass) merge into a single report of specific edits to slim the plan before code is written.
Sits between writing-plans and executing-plans in the superpowers workflow. Cheaper to fix bloat in a plan than in merged code.
Prerequisites
Verify codex is on PATH:
codex --version
If missing, instruct user to install Codex CLI (npm install -g @openai/codex) and stop.
Process
1. Discover the plan
Look for plan files in this priority order; pick the most recently modified:
docs/superpowers/plans/*.mddocs/superpowers/specs/*.mddocs/plans/*.md
If zero matches, ask the user for the path. If multiple matches in the top-priority directory have mtimes within 24h of each other, present a numbered list and ask which to review.
2. Pass A — Rubric pass (Claude in-session)
Read ./rubric.md and ./examples.md.
For each H2 section in the plan, walk every rubric pattern:
- Look for the pattern's plan-level signal in the section text
- If matched, check
examples.mdfor "don't flag" look-alikes — suppress if the matched text fits a don't-flag case better than a flag case - Otherwise emit a finding
Each finding is a structured record:
{
source: "rubric",
pattern_id: 3,
plan_section: "## 4. Service layer",
evidence: "Define IUserRepository...",
rationale: "One consumer, one implementation. The interface is a name without substance.",
suggested_edit: "Strike the interface (lines 47-58). Replace IUserRepository references with UserRepository directly.",
confidence: "high"
}
3. Pass B — Codex adversarial pass
Run Codex with this exact command (matches codex-plan-review for consistency — non-spark model, high effort, read-only):
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.
- 12d ago First seen · 186 lines · 89 tokens per session scan A d63e799798ca
detect-overengineering is a skill published in the GitHub repository Smirnov-Labs/claude-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,621 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…