What the reviewer found

A multi-agent coding workflow doc (beads issue tracker) for a project run by many concurrent AI agents. The flagged HTML comment is a visible section marker, the credential text is a 'never ship secrets' rule, rm -rf/git reset --hard are explicitly forbidden, and the user-agent line is benign guidance for the project's own web requests.

What was read

The file as it ships in Dicklesworthstone/beads_viewer:

• AGENTS.md

What the static scan said

The scan flagged 4things. The reviewer kept 0 and dismissed 4 as false.

• P2Hidden instructions — false positive
• PE3Reaches for credential files — false positive
• RMRecursive force delete — false positive
• NETMakes network calls — false positive

How this review was made

Sonnet 5 read the files above on 7 September 2026 and answered three questions: is it dangerous to whoever installs it, is each scanner finding real, and what should the installer know. The verdict is bound to the file's hash; when the file changes, it is scanned afresh and reviewed again. A script that changes while the definition does not is not re-reviewed — that is a known gap. How the scan and the review work.

Produced by agentmods.dev · Sonnet 5 · 7 September 2026