cairo-auditor

cairo-auditor is a command for Claude Code from keep-starknet-strange/starknet-agentic. It costs 0 tokens per session (258 once invoked), scanned A, original, MIT.

A command that starts the Cairo auditor workflow for Starknet contract code. Cairo is Starknet's smart-contract programming language, and the audit scans code for security problems.

In plain words
What is it for?
Use it for a full repository scan, a deep scan, or a targeted review of specified Cairo files, with an optional report written to a file.
Why use it?
It provides a repeatable security review before code is merged or deployed, including a deeper adversarial mode when needed.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the starknet-agentic-skills plugin — 19 skills, 2 commands, 1 plugin shipped together

Good fit Use it for a full repository scan, a deep scan, or a targeted review of specified Cairo files, with an optional report written to a file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/keep-starknet-strange/starknet-agentic/cairo-auditor
Install

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.

Clone the repo
git clone --depth 1 https://github.com/keep-starknet-strange/starknet-agentic

Made for: Claude Code.

Or install starknet-agentic-skills, the plugin that ships this one along with the rest of its 19 skills, 2 commands, 1 plugin.

Wrote 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.

agentmods badge for cairo-auditor

README.md
[![agentmods](https://agentmods.dev/badge/commands/keep-starknet-strange/starknet-agentic/cairo-auditor/github.svg)](https://agentmods.dev/commands/keep-starknet-strange/starknet-agentic/cairo-auditor)
Your own site
<a href="https://agentmods.dev/commands/keep-starknet-strange/starknet-agentic/cairo-auditor"><img src="https://agentmods.dev/badge/commands/keep-starknet-strange/starknet-agentic/cairo-auditor/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.

agentmods 80×15 button for cairo-auditor

Your own site · 80×15
<a href="https://agentmods.dev/commands/keep-starknet-strange/starknet-agentic/cairo-auditor"><img src="https://agentmods.dev/badge/commands/keep-starknet-strange/starknet-agentic/cairo-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 258 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00258
Opus 5 $0.00000 $0.00129
Sonnet 5 $0.00000 $0.00052
Haiku 4.5 $0.00000 $0.00026

Measured 9d ago against content hash dea5ab6ef7d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cairo-auditor 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 9d 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.

commands/cairo-auditor.md · 31 lines

What it actually says

Cairo Auditor

Run the bundled cairo-auditor skill from this plugin.

Arguments passed by user: $ARGUMENTS

Behavior

  1. Invoke the installed skill starknet-agentic-skills:cairo-auditor.
  2. Forward $ARGUMENTS exactly as provided.
  3. Keep the skill's existing mode semantics:
    • no args: default full-repo scan
    • deep: adversarial/deep mode
    • file paths: targeted scan for explicit files
    • --file-output: write report file in addition to terminal output
  4. If the namespaced invocation is unavailable in this session, retry with the short form cairo-auditor.

Quick Examples

  • /cairo-auditor
  • /cairo-auditor deep
  • /cairo-auditor src/contracts/vault.cairo
  • /cairo-auditor src/contracts/vault.cairo --file-output
Changes

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.

  1. 9d ago First seen · 31 lines · 0 tokens per session scan A dea5ab6ef7d3

Subscribe to this mod's changes

cairo-auditor is a command published in the GitHub repository keep-starknet-strange/starknet-agentic (80 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 258 tokens. 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.