Agent
L1 mode - deep analysis of consensus safety/liveness invariants, non-determinism sources, Byzantine-scenario reasoning, and cross-client state divergence.
281 1mo ago A 36 tokens
original MIT
Agent
External call side effects, cross-chain timing windows, MEV analysis.
281 1mo ago A 17 tokens
original MIT
Agent
L1 mode - deep analysis of p2p / RPC / mempool attack surfaces, DoS vectors, pre-auth panic paths, peer scoring, eclipse attacks.
281 1mo ago A 37 tokens
original MIT
ARCHITECTURE
04safe-global/safe-client-gateway
Agent
SPDX-License-Identifier: FSL-1.1-MIT -->.
50 yesterday A 0 tokens
remarks
05safe-global/safe-client-gateway
Agent
SPDX-License-Identifier: FSL-1.1-MIT -->.
50 yesterday A 0 tokens
security
06safe-global/safe-client-gateway
Agent
SPDX-License-Identifier: FSL-1.1-MIT -->.
50 yesterday A 0 tokens
ChainGPT-org/chaingpt-claude-skill
Agent
Solidity contract specialist for the generate → audit → fix → deploy lifecycle. Use when writing, reviewing, auditing, or deploying smart contracts. Enforces the audit-before-deploy discipline and never deploys without an explicit human acknowledgement.
16 2d ago A 51 tokens
original MIT
defi-trader
08ChainGPT-org/chaingpt-claude-skill
Agent
Disciplined DeFi execution specialist for swaps, bridges, lending, LP/yield moves, and perps order prep. Use when the user wants to actually DO something on-chain. Runs mandatory pre-flight checks, respects every custody gate, and never sets acknowledgeMainnet or signs from the agent wallet without explicit human…
16 2d ago A 74 tokens
original MIT
ChainGPT-org/chaingpt-claude-skill
Agent
Read-only Web3 research analyst. Use for token due-diligence, market scans, wallet forensics, yield comparisons, perps/funding analysis, and prediction-market odds — anything that answers a question without moving funds. It cannot build or sign transactions, so it is safe to run unattended.
16 2d ago A 66 tokens
original MIT
Agent
Specialist for inline assembly / Yul. Reviews memory layout, return-data handling, dirty-bits, opcode usage. Use whenever significant assembly is present.
9 1mo ago A 36 tokens
original MIT
attacker
11Agent
Adversarial reviewer. Reads contract code with one goal — find a way to steal, brick, or grief. Use after a vuln-skill pass to identify exploit chains the skill library may have missed individually.
9 1mo ago A 45 tokens
original MIT
Agent
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
9 1mo ago A 35 tokens
original MIT
debugger
13Agent
Isolate failures, identify root cause, and choose the smallest safe fix path.
5 5mo ago A 0 tokens
original MIT
implementer
14Agent
Make bounded code changes that follow the plan exactly.
5 5mo ago A 0 tokens
original MIT
reviewer
15Agent
Validate correctness, regressions, architecture fit, and missing tests.
5 5mo ago A 0 tokens
original MIT
api-ts-dev
16Agent Claude Code
TypeScript API specialist — Hono routes, Effect-TS services, Drizzle ORM schemas, A2A protocol. Use for any work in api-ts/.
3 yesterday A 36 tokens
original Apache-2.0
swap-debug
17Agent Claude Code
Cross-chain swap debugger — trace failed transactions, diagnose quote errors, debug bridge issues, analyze token security problems, debug RPC/balance issues. Use when investigating swap/transaction/balance failures.
3 yesterday A 41 tokens
original Apache-2.0
autopilot
18Agent
Autopilot is a trading agent that decides, commits, trades and publishes on its own. It runs on the execution infrastructure we already had (multi-chain swap routing, managed wallets, policy gates, token security) and adds the part that was missing: a loop that forms a thesis, refuses or takes the trade against…
3 yesterday A 0 tokens
original Apache-2.0
Agent
Quantum Shield Project - Strategic Decision Framework.
0 4d ago A 0 tokens
original MIT