Skill Claude CodeCodex
Trigger Pattern Always required for DAML audits - Inject Into Breadth agents, depth-external, depth-edge-case.
Autonomous Web3 security audit agent for Claude Code
This repository also configures its own agents. See what plamen tells them →
Skill Claude CodeCodex
Trigger Pattern Always required for DAML audits - Inject Into Breadth agents, depth-external, depth-edge-case.
Skill Claude CodeCodex
Trigger Pattern Always required for DAML audits (self-skips if no template defines a key) - Inject Into Breadth agents, depth-state-trace.
Skill Claude CodeCodex
Trigger Pattern Always required for DAML audits - Inject Into Breadth agents, depth-edge-case.
Skill Claude CodeCodex
Trigger Pattern Always required for DAML audits (self-skips if no lock pattern present) - Inject Into Breadth agents, depth-state-trace, depth-edge-case.
Skill Claude CodeCodex
Trigger Pattern Always required for DAML audits - Inject Into Breadth agents, depth-edge-case.
Skill Claude CodeCodex
Type Thought-template (instantiate before use) - Trigger Pattern CROSSCHAINMSG flag detected (protocol RECEIVES cross-chain messages).
Skill Claude CodeCodex
Trigger 15 events detected in recon eventdefinitions.md (optional skill) - Used By breadth agents (assigned to core state or dedicated agent).
Skill Claude CodeCodex
Type Thought-template (instantiate before use) - Research basis Donation attacks via unsolicited token transfers.
Skill Claude CodeCodex
Type Thought-template (instantiate before use) - Trigger Pattern STORAGELAYOUT flag detected.
Skill Claude CodeCodex
Protocol Type Trigger accountabstraction (detected when ERC-4337 interfaces, EntryPoint, UserOperation, or Paymaster patterns found) - Inject Into Breadth agents, depth-external.
Skill Claude CodeCodex
CROSSCHAINMESSAGEINTEGRITY audits messages the contract RECEIVES (decode, auth, replay). It does NOT audit whether the bytes the contract PRODUCES on the EVM side match the layout the destination VM expects. An EVM contract that packs a Solana account list, a Borsh struct, or a Bitcoin script with the wrong field…
Skill Claude CodeCodex
Protocol Type Trigger dexintegration (detected when recon finds swap|addLiquidity|removeLiquidity|IUniswapV2Router|ISwapRouter|amountOutMin|amountOutMinimum|slippage - AND the...
Skill Claude CodeCodex
Protocol Type Trigger governance (detected when Governor, Timelock, voting, proposal, quorum, delegate patterns found) - Inject Into Breadth agents, depth-external, depth-edge-case.
Skill Claude CodeCodex
Protocol Type Trigger NAMEDEXTERNALPROTOCOL (detected when recon finds import/interface for an identifiable external protocol — not standard libraries). Researches known integration hazards of the target protocol.
Skill Claude CodeCodex
L1 trigger - audits BLS signature aggregation: subgroup check, rogue-key attack defense, aggregation order, signing-domain separation.
Skill Claude CodeCodex
L1 trigger - audits configuration constants, documented bounds, feature-gated values, and unused protocol limits for semantic drift.
Skill Claude CodeCodex
L1 trigger - audits consensus arithmetic for truncation, unused bounds, EMA direction, and threshold edge errors.
Skill Claude CodeCodex
L1 trigger - detects non-determinism, state transition completeness violations, and safety/liveness invariant breaks in consensus code. Inject into depth-consensus-invariant or depth-state-trace.
Skill Claude CodeCodex
L1 trigger - audits replay protection, transaction identity binding, and cross-layer uniqueness.
Skill Claude CodeCodex
L1 trigger - audits IBC / ibc-go cross-chain entry points for ICS-23 / Merkle proof gaps, ordered-channel sequence integrity, escrow burn mint synchronization, light-client version downgrade, and timeout/ack handler reentrancy.
Skill Claude CodeCodex
L1 trigger - audits Cosmos-SDK / CometBFT modules for consensus non-determinism, unmetered ABCI hooks, signer/state mismatches, module-account bookkeeping breaks, sdk.Dec rounding, ABCI-path panics, unregistered Msg handlers, and fee/gas overflow.
Skill Claude CodeCodex
L1 trigger - audits L1/L2 boundary bugs, precompile context assumptions, integer width mismatches at environment boundaries, and EVM-on-non-EVM drift.
Skill Claude CodeCodex
L1 supplement - audits storage / data-availability chains (Arweave / Celestia-class) for unenforced data commitments: producer commits to data inclusion but the validator never verifies the data was actually published / gossiped / sampled.
Skill Claude CodeCodex
L1 supplement - audits Go modules and Rust crates for known vulnerabilities, outdated versions, supply chain risks, and replace/patch directives.
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: