Skip to content
#3in Agent infra & security

Stroq

A local audit and hook-based guard for coding-agent sessions.

Stroq homepage, captured November 7, 2026.
Public homepage: GitHub - AGGIB/Stroq: Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky c
  • The Stroq card in a terminal, on an example machine: Hoo, an orange pixel owl, beside the counts for 30 days of agent sessions (105 commands your agent ran, 1 that came from text it read, 1 key that left the machine, 1 r
    The Stroq card in a terminal, on an example machine: Hoo, an orange pixel owl, beside the counts for 30 days of agent sessions (105 commands your agent ran, 1 that came from text i
  • Stroq console, Live screen: the last 8 recorded actions, 4 allowed, 1 asked you, 2 denied, 1 flagged, and a denied action opened into what the agent read, what it did, the decision and the rule Captured November 7, 2026.
    Stroq console, Live screen: the last 8 recorded actions, 4 allowed, 1 asked you, 2 denied, 1 flagged, and a denied action opened into what the agent read, what it did, the decision

Stroq is a local, open-source audit and hook-based guard for Claude Code, Codex, and Cursor sessions. Show HN was November 5, 2026, with 92 points. The repository dates to September 2026.

Why this rank

The November 5, 2026 Show HN post describes a local, open-source audit and hook-based guard for Claude Code, Codex, and Cursor sessions.

Best for

A local audit of Claude Code, Codex, and Cursor sessions

Pricing

Free and open source.

Official source: Stroq. Checked . Confirm the current price on that site.

How we rank tools

Sources

Before you commit

  • The repository dates to September 2026. Show HN was November 5, 2026.

Compare related use cases

Weekly, one email

Only for this list. Unsubscribe any time.