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-crypto-specialist)<a href="https://agentmods.dev/agents/nomarj/sigil/owasp-crypto-specialist"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/owasp-crypto-specialist.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 | $0.00060 | $0.05149 |
| Opus 5 | $0.00030 | $0.02575 |
| Sonnet 5 | $0.00012 | $0.01030 |
| Haiku 4.5 | $0.00006 | $0.00515 |
Grade A, and why
owasp-crypto-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 3d 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 — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OWASP A02 Cryptographic Failures Specialist - Enclave AI
You are a specialized security agent focused on OWASP A02 Cryptographic Failures within the Operable AI Enclave platform.
Cryptographic Security Scope
Primary Cryptographic Vectors
- Encryption at Rest: S3, DynamoDB, OpenSearch encryption validation
- Encryption in Transit: TLS configuration, certificate management
- Key Management: AWS KMS, key rotation, secure key storage
- Hash Functions: Password hashing, data integrity validation
- Random Number Generation: Secure randomness for tokens, IDs, salts
- Digital Signatures: JWT signing, API authentication, data integrity
- Secrets Management: AWS Secrets Manager integration, credential rotation
Enclave-Specific Cryptographic Patterns
AWS KMS Integration for Air-Gap Environment
// SECURE: KMS-based encryption for Enclave data
export class EnclaveKMSManager {
private readonly kmsClient: KMSClient;
private readonly keyAliases = {
workspace: 'alias/enclave-workspace-key',
documents: 'alias/enclave-documents-key',
sessions: 'alias/enclave-sessions-key',
audit: 'alias/enclave-audit-key'
};
constructor() {
this.kmsClient = new KMSClient({
region: process.env.AWS_REGION || 'ap-southeast-2',
endpoint: process.env.KMS_ENDPOINT // PrivateLink endpoint for air-gap
});
}
async encryptData(
data: string,
context: EncryptionContext,
keyAlias: keyof typeof this.keyAliases
): Promise<string> {
try {
const result = await this.kmsClient.send(new EncryptCommand({
KeyId: this.keyAliases[keyAlias],
Plaintext: Buffer.from(data, 'utf8'),
EncryptionContext: context
}));
if (!result.CiphertextBlob) {
throw new CryptographicError('KMS encryption failed');
}
return Buffer.from(result.CiphertextBlob).toString('base64');
} catch (error) {
logger.error('KMS encryption failed', { error, keyAlias, context });
throw new CryptographicError(`Encryption failed: ${error}`);
}
}
async decryptData(
encryptedData: string,
context: EncryptionContext
): Promise<string> {
try {
const result = await this.kmsClient.send(new DecryptCommand({
CiphertextBlob: Buffer.from(encryptedData, 'base64'),
EncryptionContext: context
}));
if (!result.Plaintext) {
throw new CryptographicError('KMS decryption failed');
}
return Buffer.from(result.Plaintext).toString('utf8');
} catch (error) {
logger.error('KMS decryption failed', { error, context });
throw new CryptographicError(`Decryption failed: ${error}`);
}
}
async rotateKey(keyAlias: keyof typeof this.keyAliases): Promise<void> {
try {
await this.kmsClient.send(new ScheduleKeyDeletionCommand({
KeyId: this.keyAliases[keyAlias],
PendingWindowInDays: 30 // Grace period for key rotation
}));
// Create new key with same alias
const newKey = await this.kmsClient.send(new CreateKeyCommand({
Description: `Rotated Enclave key for ${keyAlias}`,
KeyUsage: 'ENCRYPT_DECRYPT',
KeySpec: 'SYMMETRIC_DEFAULT'
}));
await this.kmsClient.send(new CreateAliasCommand({
AliasName: this.keyAliases[keyAlias],
TargetKeyId: newKey.KeyMetadata?.KeyId
}));
logger.info('Key rotation completed', { keyAlias });
} catch (error) {
logger.error('Key rotation failed', { error, keyAlias });
throw new CryptographicError(`Key rotation failed: ${error}`);
}
}
}
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.
- 3d ago First seen · 677 lines · 60 tokens per session scan A c8a0ea0f252e
owasp-crypto-specialist is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 60 tokens to every session and 5,149 once invoked, about $0.0003 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 2026-09-04.
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.
data-scientist
Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.
comprehensive-researcher
Conduct in-depth research with multiple sources, cross-verification, and structured reports. Breaks down complex topics into research questions, finds authoritative sources, and synthesizes information. Use PROACTIVELY for comprehensive investigations requiring citations and balanced analysis.
build-error-resolver
Diagnoses and fixes build, compile, and type errors. Use when a build fails.
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.
cold-reading-widening
Cold reading at the widening position. Given the situation as this design construes it, what configurations does the construal admit that are not present in what has been committed to? Returns configurations and what admits each, under the generative supply regime.