Instructions file
Instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
Instructions file
Instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
Agent
L1 mode - deep analysis of consensus safety/liveness invariants, non-determinism sources, Byzantine-scenario reasoning, and cross-client state divergence.
Agent
Zero-state return, dust analysis, boundary conditions with real constants.
Agent
External call side effects, cross-chain timing windows, MEV analysis.
Agent
L1 mode - deep analysis of p2p / RPC / mempool attack surfaces, DoS vectors, pre-auth panic paths, peer scoring, eclipse attacks.
Agent
Cross-function state mutation tracing, constraint enforcement verification.
Agent
Deep analysis of token entry/exit paths, donation attacks, type separation.
Agent
Synthesizes findings from multiple research agents into prioritized hypotheses.
Agent
Writes and runs PoC tests to verify hypotheses. Returns CONFIRMED or FALSEPOSITIVE.
Skill Claude CodeCodex
Trigger Pattern Always (Aptos Move) - foundational security check - Inject Into Breadth agents, depth agents.
Skill Claude CodeCodex
Trigger Pattern Always (Aptos Move) - Move VM aborts on shift = bit width - Inject Into Breadth agents, depth-edge-case.
Skill Claude CodeCodex
Trigger Protocol has privileged roles (admin, operator, governance, resource account owner) - Covers Single points of failure, privilege escalation, external governance dependen...
Skill Claude CodeCodex
Trigger Pattern wormhole|layerzero|ccip|bridge|crosschain|vaa|guardian|emitter|relay|remotechain|payload|nonce.sequence - Inject Into Breadth agents, depth-external.
Skill Claude CodeCodex
Trigger EXTERNALLIB flag detected (protocol uses third-party Move dependencies) - Used by Breadth agents, depth-external.
Skill Claude CodeCodex
Trigger Pattern MONETARYPARAMETER flag (required) - Inject Into Breadth agents (merged via M4 hierarchy).
Skill Claude CodeCodex
Trigger Pattern Any external module interaction detected in attacksurface.md - Inject Into Breadth agents (merged via M5 hierarchy).
Skill Claude CodeCodex
Trigger Pattern FLASHLOAN flag (required) or BALANCEDEPENDENT flag (optional complement) - Inject Into Breadth agents, depth-token-flow, depth-edge-case.
Skill Claude CodeCodex
Trigger Pattern Always (run during recon TASK 0, not breadth) - Inject Into Recon agent only (metabuffer.md enrichment).
Skill Claude CodeCodex
Trigger FASTANDARD flag detected (protocol uses FungibleAsset standard) - Used by Breadth agents, depth-token-flow.
Skill Claude CodeCodex
Trigger Protocol has migration patterns (reinitialize, V2/V3, deprecated, upgrade, legacy, Coin-to-FA) - Covers Token type mismatches, stranded assets, interface incompatibiliti...
Skill Claude CodeCodex
Lightweight core directives for Aptos Move always-required skills — injected into every breadth agent. Full methodology lives in the dedicated Move-Safety Agent.
Skill Claude CodeCodex
Trigger Pattern ORACLE flag (required) - Inject Into Breadth agents, depth-external, depth-edge-case.
Skill Claude CodeCodex
Trigger REENTRANCY flag detected (dynamic dispatch, closures, dispatchable FA, function values) - Used by Breadth agents, depth-state-trace.
Skill Claude CodeCodex
Type Thought-template (instantiate before use) - Trigger Pattern Always (Aptos Move) -- ConstructorRef/TransferRef/MintRef/BurnRef lifecycle.