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 silvioventre/lovable-skills --skill lovable-codebase-audit-cleanupgit clone --depth 1 https://github.com/silvioventre/lovable-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/silvioventre/lovable-skills/lovable-codebase-audit-cleanup)<a href="https://agentmods.dev/skills/silvioventre/lovable-skills/lovable-codebase-audit-cleanup"><img src="https://agentmods.dev/badge/skills/silvioventre/lovable-skills/lovable-codebase-audit-cleanup/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/silvioventre/lovable-skills/lovable-codebase-audit-cleanup"><img src="https://agentmods.dev/badge/skills/silvioventre/lovable-skills/lovable-codebase-audit-cleanup.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 | $0.00165 | $0.03056 |
| Opus 5 | $0.00082 | $0.01528 |
| Sonnet 5 | $0.00033 | $0.00611 |
| Haiku 4.5 | $0.00016 | $0.00306 |
Grade A, and why
lovable-codebase-audit-cleanup 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lovable Codebase Audit & Cleanup
This skill governs two distinct, sequential phases of codebase rationalization. They must never be merged into a single pass. Determine which phase applies before doing anything else.
Phase routing
- No prior audit exists, or the user asks to inspect/find/review issues → run Phase 1: Audit.
- An audit report already exists and the user references an approved batch or finding IDs to implement → run Phase 2: Cleanup.
- The user asks to "clean up" without a prior audit → do not skip to editing. Run Phase 1 first, present the findings and the batch roadmap, and wait for explicit batch approval before touching any code.
Never combine phases in one response. Never modify code while still in Phase 1.
Phase 1: Audit (read-only)
Use Plan mode (or the project's equivalent read-only/chat mode). Perform a comprehensive, read-only audit of the entire existing codebase to identify dead code, unused code, obsolete dependencies, duplicated implementations, and maintainability risks.
Do not modify, delete, rename, move, or refactor any file during this phase.
Objective
Rationalize the codebase to make it as professional, maintainable, predictable, and technically robust as possible. Identify code that:
- Is no longer referenced or executed, or is unreachable.
- Is obsolete or superseded by a newer implementation.
- Duplicates existing functionality.
- Adds unnecessary complexity or creates maintenance risk.
- Could produce technical issues in future releases.
- Increases bundle size, build time, runtime overhead, or cognitive load without providing value.
- Is inconsistent with the architecture and conventions currently used by the project.
Audit scope
Inspect the complete repository, including:
- Application routes and route registrations.
- Pages, layouts, components, hooks, utilities, services, providers, contexts, stores, reducers, actions, schemas, types, interfaces, constants, configuration files, tests, scripts, styles, assets, and public files.
- Frontend and backend code, if both are present.
- Supabase or Lovable Cloud integrations: migrations, Edge Functions, database clients, queries, RPC calls, storage usage, authentication logic, generated types.
- Package dependencies and dev dependencies.
- Build configuration, TypeScript configuration, linting configuration, environment-variable usage, import aliases, deployment configuration.
- Feature flags, role-based flows, experimental features, legacy implementations, commented-out code, temporary workarounds, stale TODOs.
- CSS classes, design tokens, stylesheets, images, icons, fonts, and other assets that may no longer be used.
- Tests, mocks, fixtures, and test utilities that no longer correspond to active functionality.
What ships with it
1 file 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 · 211 lines · 165 tokens per session scan A 34a9e17ce7ed
lovable-codebase-audit-cleanup is a skill published in the GitHub repository silvioventre/lovable-skills (2 stars, last pushed 15d ago), licensed MIT. It adds 165 tokens to every session and 3,056 once invoked, about $0.0008 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
assignment-review
A review skill for checking submitted Python, Go, code explanations, debugging notes, or practice exercises.
agent-code-review-swarm
Agent skill for code-review-swarm - invoke with $agent-code-review-swarm.
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
critique-theater
Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…