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 skills add hec-ovi/blockchain-skill --skill agent-soliditygit clone --depth 1 https://github.com/hec-ovi/blockchain-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hec-ovi/blockchain-skill/agent-solidity)<a href="https://agentmods.dev/skills/hec-ovi/blockchain-skill/agent-solidity"><img src="https://agentmods.dev/badge/skills/hec-ovi/blockchain-skill/agent-solidity.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00122 | $0.01970 |
| Opus 5 | $0.00061 | $0.00985 |
| Sonnet 5 | $0.00024 | $0.00394 |
| Haiku 4.5 | $0.00012 | $0.00197 |
Grade A, and why
agent-solidity 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 6d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-solidity
Deployed code is public, immutable, and holds money strangers will try to take. There is no patch release. So contract work runs as a walk that is handed to you one step at a time and refuses to advance until the current step has produced something real.
Instructions only. Every action is the agent-wallet CLI: one process, exit. Most verbs print a JSON envelope {ok, data, error, meta}; contract-step prints the step as plain text because it is instructions for you to read. On ok:false follow error.hint.
Start here
Node >= 22.18. Skill packs ship dist/agent-wallet.mjs (no npm install, no Solidity toolchain).
Resolve CLI once (first hit wins; reuse it):
command -v agent-wallet
test -x .noob/skills/agent-wallet/agent-wallet && echo .noob/skills/agent-wallet/agent-wallet
test -f .noob/skills/agent-wallet/dist/agent-wallet.mjs && echo "node .noob/skills/agent-wallet/dist/agent-wallet.mjs"
test -x ./agent-wallet && echo ./agent-wallet
Then open the walk. This is the first thing you do, before writing any Solidity:
agent-wallet contract-step
That prints the mode picker. Pick one, then run contract-step --mode <mode> and follow each step's NEXT line. One step per action. Never fetch ahead, never batch, never write .sol before step 40 tells you to, never touch a chain before step 95.
Mirror the walk in your todo list: one task per step, exactly one in progress.
Only signing verbs need AGENT_WALLET_PASSPHRASE (see the agent-wallet skill). Everything up to deployment needs no key, no funds and no network.
When to use which
| Intent | Mode |
|---|---|
| "Write me a contract that ..." | build |
| "Is this contract safe?", "audit this", "review 0x..." | review |
| Source already written and reviewed, just deploy it | ship |
agent-wallet contract-step --mode build # start, or resume where you left off
agent-wallet contract-step --mode build --step 45-compile # jump to a step, or loop back
agent-wallet contract-step --list # every mode and its steps
agent-wallet contract-step --status # where the walk stands, what blocks it
agent-wallet contract-step --mode build --reset # throw the walk away and start over
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.
- 6d ago First seen · 122 lines · 122 tokens per session scan A 4d9c003f6b30
agent-solidity is a skill published in the GitHub repository hec-ovi/blockchain-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 1,970 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
bch-development
Bitcoin Cash (BCH) API implementation rules. Critical pattern for embedding Bitcoin struct and overriding BCH-specific methods. Use when working on BCH-related code in internal/infrastructure/api/btc/bch/.
wallet-cli
How to run watch, keygen, and sign wallet CLI commands. Use when executing wallet commands or testing wallet functionality.
btc-terminology
Critical Bitcoin terminology rules to prevent confusion between bech32m (encoding) and taproot (address type). Use when working on BTC-related code, config files, or shell scripts.
solidity-development
Solidity smart contract development workflow. Use when modifying smart contracts in apps/eth-contracts/contracts/.
bytesagain-wallet-tracker
Crypto wallet analytics reference — address formats, on-chain analytics, transaction tracing, hardware wallets, and approval revocation.
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.