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 Wishmakingfairy/vibecheck --skill secure-deploygit clone --depth 1 https://github.com/Wishmakingfairy/vibecheckWrote 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/wishmakingfairy/vibecheck/secure-deploy)<a href="https://agentmods.dev/skills/wishmakingfairy/vibecheck/secure-deploy"><img src="https://agentmods.dev/badge/skills/wishmakingfairy/vibecheck/secure-deploy.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 5.1 | $0.00047 | $0.00401 |
| Opus 5 | $0.00023 | $0.00200 |
| Sonnet 5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
secure-deploy 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.
What it actually says
Secure Deploy: Pre-Launch Checklist
CRITICAL (Must fix before deploy)
- No API keys/secrets in source code (run
vibecheck scan) - .env files in .gitignore
- DEBUG=False / NODE_ENV=production
- Supabase RLS enabled on ALL tables
- CORS restricted to your domains (not *)
- Rate limiting on auth endpoints
- HTTPS enforced (redirect HTTP to HTTPS)
- Source maps disabled in production build
- No default credentials (admin:admin)
WARNING (Should fix before deploy)
- Security headers configured (CSP, HSTS, X-Frame-Options)
- JWT tokens have expiry
- Session cookies have Secure + HttpOnly + SameSite
- File uploads validated (type + size)
- SQL queries use parameterized statements
- Dependencies audited (npm audit / pip audit)
- Error responses do not expose stack traces
- Admin routes require authentication
INFO (Best practice)
- Structured logging configured (no PII)
- Monitoring and alerting set up
- Backup strategy in place
- Incident response plan documented
- MFA available for admin accounts
Quick Verification
Run: /security-scan to check all 156 items automatically.
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 First seen · 49 lines · 47 tokens per session scan A 73b4a4afed2a
secure-deploy is a skill published in the GitHub repository Wishmakingfairy/vibecheck (4 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 401 once invoked, about $0.0002 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
cloud-security-posture
../../../cloud-infra/cloud-security-posture/SKILL.md.
iac-security
../../../cloud-infra/iac-security/SKILL.md.
cloud-workload-protection
../../../cloud-infra/cloud-workload-protection/SKILL.md.
identity-access-risk
../../../identity-access/identity-access-risk/SKILL.md.
security-sweep
Scan codebase for security vulnerabilities, hardcoded secrets, injection flaws, misconfigurations, and attack surfaces. Use when user wants a security audit, vulnerability scan, or to find security issues.
cloud-security
Cloud and infrastructure configuration security auditor for Vercel, Netlify, AWS, Azure, Google Cloud, and Supabase/Firebase project settings. Use when reviewing deployment configuration, environment variable management, IAM permissions, storage bucket access, or general cloud misconfiguration — rather than the…