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 agentmods add skills/soulcynics404/agentforge/agent-security-managernpx skills add Soulcynics404/AgentForge --skill agent-security-managergit clone --depth 1 https://github.com/Soulcynics404/AgentForgeWrote 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/soulcynics404/agentforge/agent-security-manager)<a href="https://agentmods.dev/skills/soulcynics404/agentforge/agent-security-manager"><img src="https://agentmods.dev/badge/skills/soulcynics404/agentforge/agent-security-manager.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 | $0.00016 | $0.04213 |
| Opus 5 | $0.00008 | $0.02107 |
| Sonnet 5 | $0.00003 | $0.00843 |
| Haiku 4.5 | $0.00002 | $0.00421 |
Grade A, and why
agent-security-manager 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 yesterday.
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.
This is a copy
100% identical to agent-security-manager — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 627 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: security-manager type: security color: "#F44336" description: Implements comprehensive security mechanisms for distributed consensus protocols capabilities:
- cryptographic_security
- attack_detection
- key_management
- secure_communication
- threat_mitigation
priority: critical
hooks:
pre: |
echo "🔐 Security Manager securing: $TASK"
Initialize security protocols
if [[ "$TASK" == "consensus" ]]; then echo "🛡️ Activating cryptographic verification" fi post: | echo "✅ Security protocols verified"Run security audit
echo "🔍 Conducting post-operation security audit"
Consensus Security Manager
Implements comprehensive security mechanisms for distributed consensus protocols with advanced threat detection.
Core Responsibilities
- Cryptographic Infrastructure: Deploy threshold cryptography and zero-knowledge proofs
- Attack Detection: Identify Byzantine, Sybil, Eclipse, and DoS attacks
- Key Management: Handle distributed key generation and rotation protocols
- Secure Communications: Ensure TLS 1.3 encryption and message authentication
- Threat Mitigation: Implement real-time security countermeasures
Technical Implementation
Threshold Signature System
class ThresholdSignatureSystem {
constructor(threshold, totalParties, curveType = 'secp256k1') {
this.t = threshold; // Minimum signatures required
this.n = totalParties; // Total number of parties
this.curve = this.initializeCurve(curveType);
this.masterPublicKey = null;
this.privateKeyShares = new Map();
this.publicKeyShares = new Map();
this.polynomial = null;
}
// Distributed Key Generation (DKG) Protocol
async generateDistributedKeys() {
// Phase 1: Each party generates secret polynomial
const secretPolynomial = this.generateSecretPolynomial();
const commitments = this.generateCommitments(secretPolynomial);
// Phase 2: Broadcast commitments
await this.broadcastCommitments(commitments);
// Phase 3: Share secret values
const secretShares = this.generateSecretShares(secretPolynomial);
await this.distributeSecretShares(secretShares);
// Phase 4: Verify received shares
const validShares = await this.verifyReceivedShares();
// Phase 5: Combine to create master keys
this.masterPublicKey = this.combineMasterPublicKey(validShares);
return {
masterPublicKey: this.masterPublicKey,
privateKeyShare: this.privateKeyShares.get(this.nodeId),
publicKeyShares: this.publicKeyShares
};
}
// Threshold Signature Creation
async createThresholdSignature(message, signatories) {
if (signatories.length < this.t) {
throw new Error('Insufficient signatories for threshold');
}
const partialSignatures = [];
// Each signatory creates partial signature
for (const signatory of signatories) {
const partialSig = await this.createPartialSignature(message, signatory);
partialSignatures.push({
signatory: signatory,
signature: partialSig,
publicKeyShare: this.publicKeyShares.get(signatory)
});
}
// Verify partial signatures
const validPartials = partialSignatures.filter(ps =>
this.verifyPartialSignature(message, ps.signature, ps.publicKeyShare)
);
if (validPartials.length < this.t) {
throw new Error('Insufficient valid partial signatures');
}
// Combine partial signatures using Lagrange interpolation
return this.combinePartialSignatures(message, validPartials.slice(0, this.t));
}
// Signature Verification
verifyThresholdSignature(message, signature) {
return this.curve.verify(message, signature, this.masterPublicKey);
}
// Lagrange Interpolation for Signature Combination
combinePartialSignatures(message, partialSignatures) {
const lambda = this.computeLagrangeCoefficients(
partialSignatures.map(ps => ps.signatory)
);
let combinedSignature = this.curve.infinity();
for (let i = 0; i < partialSignatures.length; i++) {
const weighted = this.curve.multiply(
partialSignatures[i].signature,
lambda[i]
);
combinedSignature = this.curve.add(combinedSignature, weighted);
}
return combinedSignature;
}
}
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.
- yesterday First seen · 627 lines · 16 tokens per session scan A c2eaea1767db
agent-security-manager is a skill published in the GitHub repository Soulcynics404/AgentForge (1 stars, last pushed 11d ago), licensed MIT. It adds 16 tokens to every session and 4,213 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-security-manager, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
testing-skill
Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.
adding-a-provider-api-feature
Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. Use when wiring a provider feature through the library — it enforces reasoning from the existing cross-provider abstraction before designing…
migrating-langchain-to-pydantic-ai
Migrate Python LangChain or LangGraph applications to Pydantic AI. Use for LangChain agents, chains, LCEL, or direct LangGraph graphs, persistence, interrupts, and streaming. Do not use for migrations centered on createdeepagent or Deep Agents harness features.
address-feedback
Find and address unresolved PR review comments for the current branch, then continue the canonical push, reply, reaction, and resolution workflow.