Agent Claude Code
L1 mode - deep analysis of consensus safety/liveness invariants, non-determinism sources, Byzantine-scenario reasoning, and cross-client state divergence.
not rated 306
+3 20d ago A 36 tokens
original MIT
Agent Claude Code
Zero-state return, dust analysis, boundary conditions with real constants.
not rated 306
+3 20d ago A 16 tokens
original MIT
Agent Claude Code
External call side effects, cross-chain timing windows, MEV analysis.
not rated 306
+3 20d ago A 17 tokens
original MIT
Agent Claude Code
L1 mode - deep analysis of p2p / RPC / mempool attack surfaces, DoS vectors, pre-auth panic paths, peer scoring, eclipse attacks.
not rated 306
+3 20d ago A 37 tokens
original MIT
Agent Claude Code
Cross-function state mutation tracing, constraint enforcement verification.
not rated 306
+3 20d ago A 14 tokens
original MIT
Agent Claude Code
Deep analysis of token entry/exit paths, donation attacks, type separation.
not rated 306
+3 20d ago A 18 tokens
original MIT
Agent Claude Code
Synthesizes findings from multiple research agents into prioritized hypotheses.
not rated 306
+3 20d ago A 16 tokens
original MIT
Agent Claude Code
Writes and runs PoC tests to verify hypotheses. Returns CONFIRMED or FALSEPOSITIVE.
not rated 306
+3 20d ago A 23 tokens
original MIT
Skill Claude CodeCodex
Trigger Pattern Always (Aptos Move) - foundational security check - Inject Into Breadth agents, depth agents.
not rated 306
+3 20d ago A SkillSpector: pass 25 tokens
original MIT
Skill Claude CodeCodex
Trigger Pattern Always (Aptos Move) - Move VM aborts on shift = bit width - Inject Into Breadth agents, depth-edge-case.
not rated 306
+3 20d ago A SkillSpector: pass 35 tokens
original MIT
Skill Claude CodeCodex
Trigger Protocol has privileged roles (admin, operator, governance, resource account owner) - Covers Single points of failure, privilege escalation, external governance dependen...
not rated 306
+3 20d ago A SkillSpector: pass 35 tokens
original MIT
Skill Claude CodeCodex
Trigger Pattern wormhole|layerzero|ccip|bridge|crosschain|vaa|guardian|emitter|relay|remotechain|payload|nonce.sequence - Inject Into Breadth agents, depth-external.
not rated 306
+3 20d ago A SkillSpector: warn 47 tokens
original MIT
Skill Claude CodeCodex
Trigger EXTERNALLIB flag detected (protocol uses third-party Move dependencies) - Used by Breadth agents, depth-external.
not rated 306
+3 20d ago A SkillSpector: warn 28 tokens
original MIT
Skill Claude CodeCodex
Trigger Pattern MONETARYPARAMETER flag (required) - Inject Into Breadth agents (merged via M4 hierarchy).
not rated 306
+3 20d ago A SkillSpector: pass 28 tokens
original MIT
Skill Claude CodeCodex
Trigger Pattern Any external module interaction detected in attacksurface.md - Inject Into Breadth agents (merged via M5 hierarchy).
not rated 306
+3 20d ago A SkillSpector: pass 30 tokens
original MIT
Skill Claude CodeCodex
Trigger Pattern FLASHLOAN flag (required) or BALANCEDEPENDENT flag (optional complement) - Inject Into Breadth agents, depth-token-flow, depth-edge-case.
not rated 306
+3 20d ago A SkillSpector: warn 40 tokens
original MIT
Skill Claude CodeCodex
Trigger Pattern Always (run during recon TASK 0, not breadth) - Inject Into Recon agent only (metabuffer.md enrichment).
not rated 306
+3 20d ago A SkillSpector: pass 31 tokens
original MIT
Skill Claude CodeCodex
Trigger FASTANDARD flag detected (protocol uses FungibleAsset standard) - Used by Breadth agents, depth-token-flow.
not rated 306
+3 20d ago A SkillSpector: warn 29 tokens
original MIT
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...
not rated 306
+3 20d ago A SkillSpector: warn 43 tokens
original MIT
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.
not rated 306
+3 20d ago A SkillSpector: pass 36 tokens
original MIT
Skill Claude CodeCodex
Trigger Pattern ORACLE flag (required) - Inject Into Breadth agents, depth-external, depth-edge-case.
not rated 306
+3 20d ago A SkillSpector: warn 25 tokens
original MIT
Skill Claude CodeCodex
Trigger REENTRANCY flag detected (dynamic dispatch, closures, dispatchable FA, function values) - Used by Breadth agents, depth-state-trace.
not rated 306
+3 20d ago A SkillSpector: warn 37 tokens
original MIT
Skill Claude CodeCodex
Type Thought-template (instantiate before use) - Trigger Pattern Always (Aptos Move) -- ConstructorRef/TransferRef/MintRef/BurnRef lifecycle.
not rated 306
+3 20d ago A SkillSpector: pass 35 tokens
original MIT
Skill Claude CodeCodex
Trigger Pattern SEMITRUSTEDROLE flag (required) - Inject Into Breadth agents, depth-state-trace.
not rated 306
+3 20d ago A SkillSpector: warn 29 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: