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 EliasOulkadi/shokunin --skill auth-architectgit clone --depth 1 https://github.com/EliasOulkadi/shokuninWrote 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/eliasoulkadi/shokunin/auth-architect)<a href="https://agentmods.dev/skills/eliasoulkadi/shokunin/auth-architect"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/auth-architect/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/eliasoulkadi/shokunin/auth-architect"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/auth-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 99 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high YARA Match · line 276 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00101 | $0.03715 |
| Opus 5 | $0.00051 | $0.01858 |
| Sonnet 5 | $0.00020 | $0.00743 |
| Haiku 4.5 | $0.00010 | $0.00371 |
Grade A, and why
auth-architect 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 11d 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auth Architect
Production authentication following OWASP Top 10, NIST SP 800-63B, and patterns from Auth0, AWS Cognito, and the OWASP Cheat Sheet Series.
Sub-Commands
| Command | Description |
|---|---|
implement |
Implement full authentication system (login, signup, sessions, MFA, password reset) |
audit |
Audit existing auth against OWASP Top 10 checklist |
enforce |
Add missing security measures (rate limiting, CSRF, session rotation) |
teach |
Set up auth context file (AUTH.md) with project-specific configuration |
Workflow
Step 1: Choose auth method
| Method | Use Case | Security | Complexity |
|---|---|---|---|
| Session-based (httpOnly cookies) | Server-rendered web apps | High | Low |
| JWT access + refresh tokens | SPAs, mobile, APIs | High (with proper storage) | Medium |
| OAuth 2.0 + OIDC | Third-party login, SSO | High | High |
| API keys with HMAC | M2M, CLIs, integrations | Medium | Low |
| WebAuthn / Passkeys | Passwordless, high-security | Very High | Medium |
| Magic links / OTP | Low-friction, email-based | Medium | Low |
Step 2: Implement authentication
Password-based auth
1. Validate email format + length (< 254 chars)
2. Check against breached passwords (HaveIBeenPwned API k-anonymity)
3. Hash with Argon2id: memory=19456, iterations=2, parallelism=1
OR BCrypt: cost=12 minimum
4. Generate session UUIDv4 via crypto.randomUUID()
5. Store session server-side (Redis, TTL=24h)
6. Set cookie: httpOnly, Secure, SameSite=Strict
7. Return user object (never return password hash)
Password requirements (NIST SP 800-63B):
- Minimum 12 characters (no max below 64)
- NO composition rules (uppercase, number, symbol required - these weaken security, NIST §5.1.1.2)
- Allow all printable ASCII + Unicode
- Check against HaveIBeenPwned API (k-anonymity, SHA-1 prefix)
- Rate limit: 5 attempts per 15 min per IP + username
JWT implementation
{
"iss": "https://api.example.com",
"sub": "user_abc123",
"aud": ["web", "mobile"],
"exp": 900,
"iat": 1700000000,
"jti": "a1b2c3d4e5f6",
"sid": "sess_xyz789"
}
What ships with it
2 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.
- 11d ago First seen · 338 lines · 101 tokens per session scan A 0719d390c185
auth-architect is a skill published in the GitHub repository EliasOulkadi/shokunin (113 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 3,715 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
knowject-api-to-types
A Knowject skill that generates TypeScript types from an OpenAPI document, which describes an API's available requests and data shapes, and connects them to a typed client.
knowject-read-api
A project skill for finding backend API endpoints and generating typed HTTP clients when the project contains a knowject/context.yaml file.
python-sdk
Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.
potpie-infra-architecture
Use for project infra and architecture context: environments, adapters, runtime configuration, deployments, service dependencies, datastores, API contracts, ownership, incidents, and dependency blast radius.
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.
memstack-automation-webhook-designer
Use this skill when the user says 'webhook', 'webhook handler', 'webhook endpoint', 'receive events', 'HMAC verification', 'idempotency', or needs secure webhook handlers with signature verification, retry handling, and dead letter queues. Do NOT use for full n8n workflows or scheduled tasks.