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/etherscan/skills/etherscan-transaction-debuggernpx skills add etherscan/skills --skill etherscan-transaction-debuggergit clone --depth 1 https://github.com/etherscan/skillsWhat 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 | $0.00155 | $0.02139 |
| Opus 5 | $0.00077 | $0.01069 |
| Sonnet 5 | $0.00031 | $0.00428 |
| Haiku 4.5 | $0.00015 | $0.00214 |
Grade A, and why
etherscan-transaction-debugger 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 2d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Etherscan Transaction Debugger
Turn Etherscan's transaction, contract, token, and label data into a clear execution story that users can verify directly on the explorer. Preserve raw hashes and addresses, make important claims auditable, and never make trace completeness sound stronger than the available data.
Inputs
Require a 32-byte transaction hash. Accept a second hash for a focused comparison.
Determine the chain from the user, a chain-specific explorer URL, transaction data, or surrounding context. Ask only when the hash is valid on multiple candidate chains or cannot be found. Default to Ethereum only when no chain clue exists, and state the assumption.
Treat the expected outcome, protocol name, and requested audience as optional. Infer a useful explanation level when omitted:
simple: short, nontechnical outcome.standard: outcome, important calls, and asset changes.developer: decoded calldata, call semantics, proxy path, and failure evidence.support: customer-ready explanation plus escalation notes.security: permissions, callbacks, delegate calls, recipients, and evidence-backed anomalies.
Core Workflow
- Validate the hash and resolve the chain.
- Use Etherscan as the primary data and verification surface. Collect live transaction, receipt, status, internal-operation, contract, ABI, verified source, proxy, label, token, and explorer-link evidence. Prefer the Etherscan CLI when installed; use
scripts/collect_transaction_data.pyfor a reproducible evidence bundle. Read references/evidence-collection.md when collection fails, the CLI is unavailable, or deep trace data is needed. - Establish facts before interpreting intent: sender, destination, status, block time, top-level value and calldata, gas used, effective gas price, logs, created contract, and returned errors.
- Decode the top-level method and important logs with verified ABIs. Resolve proxy and implementation roles before attributing behavior. Read references/execution-semantics.md for proxies, call types, callbacks, asset movements, and common patterns.
- Build only the execution path supported by evidence. Label inferred edges and omitted low-value details. Never call Etherscan internal transactions a complete call trace.
- Reconcile native, ERC-20, ERC-721, and ERC-1155 movements; approvals; operator permissions; ownership or role changes; and proxy upgrades. Calculate the execution gas fee as
gasUsed * effectiveGasPriceusing integers. Include L1 data or blob fees when the receipt provides them, and report a total transaction fee only when every applicable component is known. - If the transaction failed or contains a suspicious child failure, read references/failure-analysis.md and identify the narrowest supported root cause.
- Cross-check the narrative against the receipt status, logs, values, addresses, and trace. Read references/reporting.md before producing security, support, comparison, or low-confidence reports.
- Create an Etherscan evidence trail: link the transaction and each important address, contract, implementation, token, and relevant explorer view on the correct Etherscan-family explorer.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 269 B
- assets/transaction-report-template.md 616 B
- references/evidence-collection.md 4.4 KB
- references/execution-semantics.md 3.7 KB
- references/failure-analysis.md 3.0 KB
- references/regression-cases.md 1.5 KB
- references/reporting.md 4.1 KB
- scripts/collect_transaction_data.py 9.6 KB runs code
- scripts/summarize_transaction.py 13 KB runs code
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.
- 2d ago First seen · 118 lines · 155 tokens per session scan A ec9c45e51693
etherscan-transaction-debugger is a skill published in the GitHub repository etherscan/skills (21 stars, last pushed 15d ago), licensed MIT. It adds 155 tokens to every session and 2,139 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
nostr-expert
Nostr protocol implementation patterns in Quartz (AmethystMultiplatform's KMP Nostr library). Use when working with: (1) Nostr events (creating, parsing, signing), (2) Event kinds and tags, (3) NIP implementations (80+ NIP packages in quartz/), (4) Event builders and TagArrayBuilder DSL, (5) Nostr cryptography…
nip85-trusted-assertions
The NIP-85 trusted-assertions model in Quartz (nip85TrustedAssertions/) — kind 10040 trust-provider lists, kind 30382 contact cards / user assertions, 30383 event assertions, 30384 addressable assertions, 30385 external-id assertions. Use when building or parsing these events, working with the typed tags (RankTag…
ansem-crypto
Use when evaluating crypto narratives, attention rotation, memecoin cycles, Solana-style ecosystem momentum, social distribution, and reflexive retail flows in an Ansem-style crypto market framework.
arthur-hayes-liquidity
Use when evaluating crypto markets through an Arthur Hayes-style liquidity lens: dollar liquidity, funding, risk appetite, cycle psychology, and macro-driven crypto positioning.
ledger-wallet-cli
Official Ledger wallet-cli - USB-based CLI for Ledger hardware wallet flows (account discover, receive, balances, operations, send, swap quote/execute/status, genuine-check, assets token / token-by-id) and the Ledger Key Ring (ring init/encrypt/decrypt/keys/destroy — LKRP-backed encryption of files and text). Use for…