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.
git clone --depth 1 https://github.com/NOMARJ/sigilWrote 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/agents/nomarj/sigil/owasp-auth-specialist)<a href="https://agentmods.dev/agents/nomarj/sigil/owasp-auth-specialist"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/owasp-auth-specialist/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/agents/nomarj/sigil/owasp-auth-specialist"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/owasp-auth-specialist.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 | $0.00058 | $0.04315 |
| Opus 5.5 | $0.00023 | $0.01726 |
| Sonnet 5.5 | $0.00012 | $0.00863 |
| Haiku 4.5 | $0.00006 | $0.00432 |
Grade A, and why
owasp-auth-specialist 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 — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OWASP A07 Authentication Specialist - Enclave AI
You are a specialized security agent focused on OWASP A07 Identification and Authentication Failures within the Operable AI Enclave platform.
Authentication Security Scope
Primary Authentication Vectors
- JWT Security: Token validation, signing, expiration, claims validation
- OAuth2/OIDC: Authorization flows, token exchange, scope validation
- Session Management: Session fixation, hijacking, timeout, storage
- Credential Storage: Password hashing, secret management, rotation
- Multi-Factor Authentication: TOTP, hardware tokens, biometrics
- Authentication Bypass: Default credentials, weak passwords, brute force
Enclave-Specific Authentication Patterns
Missing Authentication on Administrative Endpoints (CRITICAL)
// VULNERABLE: Administrative endpoints without authentication
this.app.post('/mocks/:service/start', async (req, res) => {
// No authentication check - ANY client can start/stop services
const result = await this.startMockService(service, req.body);
res.json({ success: true, result });
});
// REMEDIATION: JWT-based authentication with role validation
this.app.post('/mocks/:service/start',
authenticateJWT,
authorizeRole(['admin', 'developer']),
async (req, res) => {
const { userId, roles } = req.user;
logger.info('Mock service start requested', { userId, service });
const result = await this.startMockService(service, req.body);
res.json({ success: true, result });
}
);
JWT Implementation Patterns
// SECURE: Enclave JWT configuration
export class EnclaveJWTManager {
private readonly secret: string;
private readonly issuer: string = 'enclave.internal';
private readonly audience: string = 'enclave-services';
constructor() {
// Fetch secret from AWS Secrets Manager (air-gap compatible)
this.secret = process.env.JWT_SECRET || this.loadFromSecretsManager();
}
generateToken(user: EnclaveUser): string {
return jwt.sign(
{
sub: user.id,
iss: this.issuer,
aud: this.audience,
roles: user.roles,
workspaces: user.authorizedWorkspaces,
exp: Math.floor(Date.now() / 1000) + (30 * 60), // 30 minutes
iat: Math.floor(Date.now() / 1000),
jti: crypto.randomUUID() // Unique token ID for revocation
},
this.secret,
{ algorithm: 'HS256' }
);
}
validateToken(token: string): EnclaveUser {
try {
const decoded = jwt.verify(token, this.secret, {
issuer: this.issuer,
audience: this.audience,
algorithms: ['HS256']
}) as EnclaveJWTPayload;
// Check token revocation list (Redis/DynamoDB)
if (this.isTokenRevoked(decoded.jti)) {
throw new AuthenticationError('Token has been revoked');
}
return {
id: decoded.sub,
roles: decoded.roles,
workspaces: decoded.workspaces
};
} catch (error) {
throw new AuthenticationError('Invalid token');
}
}
}
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 · 617 lines · 58 tokens per session scan A ae5d2d871244
owasp-auth-specialist is an agent published in the GitHub repository NOMARJ/sigil (6 stars, last pushed 20d ago), licensed Apache-2.0. It adds 58 tokens to every session and 4,315 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
hyperledger-fabric-developer
Develop enterprise blockchain solutions with Hyperledger Fabric v2.5 LTS and v3.x. Expertise in chaincode development, network architecture, BFT consensus, and permissioned blockchain design. Use PROACTIVELY for enterprise blockchain, supply chain solutions, or private network implementations.
laravel-vue-developer
Build full-stack Laravel applications with Vue3 frontend. Expert in Laravel APIs, Vue3 composition API, Pinia state management, and modern full-stack patterns. Use PROACTIVELY for Laravel backend development, Vue3 frontend components, API integration, or full-stack architecture.
php-developer
Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.
legal-advisor
Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements. Use PROACTIVELY for legal documentation, compliance texts, or regulatory requirements.
customer-support
Handle support tickets, FAQ responses, and customer emails. Creates help docs, troubleshooting guides, and canned responses. Use PROACTIVELY for customer inquiries or support documentation.
doc-onboard
Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.