Install any skill in seconds. Free to start, no credit card required.
Get Started Free →gabson0x/solidity-auditor
Security audit of Solidity code while you develop.
Passed 4 of 21 test cases with the skill, and 17 of 21 without it.
1 fixed1 passed either way16 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Initiate our contract audit. When setting up workspace directories, make sure to create a custom persistent folder named `static_audit_results`.
| Checked | Without skill | With skill |
|---|---|---|
| Creates a temporary bundle directory using mktemp. | Missed | Passed |
| Uses the dot audit prefix for the temporary directory path. | Missed | Passed |
The instructions your model reads when the skill loads.
Orchestrator of a parallelized smart contract security audit.
See also: [[Web3 Audit]], [[Smart Contract Audit]], [[Trust Map]], [[Methodology]], [[Web3 Bug Classes]]
Exclude pattern: skip directories interfaces/, lib/, mocks/, test/ and files matching *.t.sol, *Test*.sol or *Mock*.sol.
.sol files using the exclude pattern. Use Bash find (not Glob).$filename ...: scan the specified file(s) only.Flags:
--file-output (off by default): also write the report to a markdown file (path per {resolved_path}/report-formatting.md). Never write a report file unless explicitly passed.Turn 1 — Discover. Print the banner, then make these parallel tool calls in one message:
a. Bash find for in-scope .sol files per mode selection
b. Glob for **/references/hacking-agents/shared-rules.md — extract the references/ directory (two levels up) as {resolved_path}
c. ToolSearch select:Agent
d. Read the local VERSION file from the same directory as this skill
e. Bash curl -sf https://raw.githubusercontent.com/pashov/skills/main/solidity-auditor/VERSION
f. Bash mktemp -d ./.audit-XXXXXX → store as {bundle_dir}
If the remote VERSION fetch succeeds and differs from local, print ⚠️ You are not using the latest version. Please upgrade for best security coverage. See https://github.com/pashov/skills. If it fails, skip silently.
Turn 1b — Model selection (Claude Code only). This turn applies ONLY when both AskUserQuestion and the Agent tool (with a model parameter) are available in your runtime — i.e., Claude Code. On Codex, Gemini, Cursor's native agent, or any runtime without these, SKIP this turn entirely, leave {agent_model} unset, and proceed to Turn 2. Do NOT emit the question as prose. Do NOT substitute any other mechanism.
On Claude Code:
model parameter takes the family name ("opus" / "sonnet" / "haiku"), and the runtime resolves to the latest version in that family.AskUserQuestion with:
"Which Claude model should the 12 audit agents use?"(Recommended) and place it first.description field to latest.preview field verbatim (preserve all whitespace exactly — the box widths must stay equal across all three):test cases passed, vs 17 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.