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 securegit 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/secure)<a href="https://agentmods.dev/skills/silvioventre/lovable-skills/secure"><img src="https://agentmods.dev/badge/skills/silvioventre/lovable-skills/secure/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/secure"><img src="https://agentmods.dev/badge/skills/silvioventre/lovable-skills/secure.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 | $0.00174 | $0.01103 |
| Opus 5.5 | $0.00070 | $0.00441 |
| Sonnet 5.5 | $0.00035 | $0.00221 |
| Haiku 4.5 | $0.00017 | $0.00110 |
Grade A, and why
secure 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure
Lovable apps have three layers, and each has exactly one security job. Nearly every real vulnerability comes from putting a decision in the wrong layer.
| Layer | Runs | Trust | Job |
|---|---|---|---|
| Frontend | In the user's browser | None. Public, inspectable, modifiable | Presentation only. Never decides access |
| Edge functions | Server-side, isolated | Trusted | Validation, authorisation, business logic, external calls |
| Database (RLS) | In the database | Trusted | Enforces row access even when the layers above fail |
The frontend is not a weak line of defence — it is not a line of defence at all. Anything shipped to the browser is readable and changeable by anyone who wants to.
Route the concern
| The question or task | Playbook |
|---|---|
| Where do I put an API key, token, or secret? | reference/frontend.md |
| Is there anything sensitive exposed in my client code? | reference/frontend.md |
| Is form or input validation enough as written? | reference/frontend.md |
| What belongs server-side rather than in a component? | reference/edge-functions.md |
| Calling an external or paid API safely | reference/edge-functions.md |
| Payments, uploads, registration, anything multi-step | reference/edge-functions.md |
| Can users see or change each other's data? | reference/rls.md |
| Setting up or reviewing row-level security | reference/rls.md |
| Team, organisation, or shared-record access rules | reference/rls.md |
| Login, sessions, roles, protecting a route | reference/auth.md |
| Admin areas and privileged actions | reference/auth.md |
| Full security review, or "am I safe to publish?" | reference/review.md |
If the request spans layers — most real ones do — start at reference/review.md and let it dispatch.
What ships with it
6 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.
- 1mo ago First seen · 63 lines · 174 tokens per session scan A e63a6ed823a8
secure is a skill published in the GitHub repository silvioventre/lovable-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 174 tokens to every session and 1,103 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
bmad-correct-course
Assess the impact of a significant change during sprint execution across the PRD, epics, architecture, and UX documents, and produce a sprint change proposal. Use when the user says "correct course" or "propose sprint change".
bmad-spec
Condense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: one kernel file plus supporting files that downstream skills build from. Also updates and validates existing specs. Use when the user says "create a spec", "distill this into a spec", "validate this spec", or "update the spec".
bmad-product-brief
Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.
bmad-ticket
Create and manage tickets — initiatives, epics, stories, bugs. Use when the user says "create a new initiative", "slice this initiative", "split this epic up", "break this into stories", "incept this epic", "make a ticket", "refine this ticket", "what's ready", "status of a story", "publish ticket changes", "validate…
bmad-deep-recon
Research a topic to support a decision, three ways: draft a research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), turn a finished research report into a short summary with cited sources that other skills can use directly, or run the research here with parallel web searches.…
bmad-eval
Runs the evals of a BMad skill through the agent harness the user works in and reports what they show: baseline against the bare model, variant against a stripped or prior version, quality against a rubric, and trigger accuracy of the description with an optional optimization loop. Use when the user asks to evaluate…