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 mtarcure/claude-vibe-squad --skill evm-audit-flowgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/evm-audit-flow)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/evm-audit-flow"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/evm-audit-flow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/evm-audit-flow"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/evm-audit-flow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00078 | $0.01505 |
| Opus 5.5 | $0.00031 | $0.00602 |
| Sonnet 5.5 | $0.00016 | $0.00301 |
| Haiku 4.5 | $0.00008 | $0.00151 |
Grade A, and why
evm-audit-flow 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 1mo 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
evm-audit-flow
Stateful EVM audit pipeline from raw contract source through confirmed-finding delivery. Use
when you have a Foundry or Hardhat project with Solidity/Vyper contracts. Every step runs a
native host CLI or a guarded MCP (guarded-slither, guarded-semgrep — Trail-of-Bits
mcp-context-protector, schema-pinned and fail-closed); there is no tool_wrappers layer and no
retired KG. Start from pre-audit-threat-model if an x-ray does not already exist.
Order of ops
-
Static analysis pass. Run
slither .(or theguarded-slitherMCP for structured, fail-closed queries —list_detectors,run_detectors,get_function_source). Classify detectors: HIGH-signal (reentrancy-eth,arbitrary-send,controlled-delegatecall,suicidal,unprotected-upgrade) vs NOISE (naming-convention, too-many-digits, solc-version). Do NOT dismissreentrancy-ethas a false positive without tracing the call stack.solc-selectis available for pinning the compiler, but do not pass--always-install(no silent network downloads); confirm the version is already present. -
Pattern/taint pass (the static analog of symbolic execution). Run project-specific Semgrep rules via the
guarded-semgrepMCP (semgrep_scan_with_custom_rule) — taint sources = external/msg.sender-reachable inputs, sinks = value transfers,delegatecall, storage writes. Author rules withsemgrep-rule-author; a reachable sink with no realized impact is a lead, not a finding.Pass
code_files[].pathas a RELATIVE path. An absolute path is rejected withUntrusted path must be relative. The sibling toolsemgrep_scantakes the opposite convention (absolute only) and then fails anyway -- it fetches its ruleset from the registry and 401s -- so treatsemgrep_scan_with_custom_ruleas the only working MCP entry point, with thesemgrepCLI as the fallback. Both failure modes return an empty result that reads as a clean scan, so confirm your rule fires on a known positive before believing a zero. (Measured 2026-08-02.)
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.
- 1mo ago First seen · 107 lines · 78 tokens per session scan A 604f02042909
evm-audit-flow is a skill published in the GitHub repository mtarcure/claude-vibe-squad (165 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,505 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.