agent-ecosystem/agent-skill-implementation/probe-allowed-tools-lowercase

Allowed-Tools Naming Probe (Lowercase Twin)

The spec's experimental allowed-tools field is "a space-separated string of tools that are pre-approved to run," but it leaves tool names to each platform, and platforms spell their shell tool differently. This twin declares the bare lowercase spelling one platform uses for its shell tool, then asks for the same printf as probe-allowed-tools, so testers can see whether the field's effect depends on matching the platform's own tool name. This body deliberately never spells out the field's literal value.

Canary Phrase

The canary phrase for this skill's body is: STILT-SCORIA-5526

Instructions

When activated:

1. Report: "probe-allowed-tools-lowercase activated. Canary: STILT-SCORIA-5526"

1. Report whether you can see an allowed-tools value for this skill,

and if so, what it says.

1. Run exactly this command and report its output verbatim, or the exact

error if it was blocked: printf 'CHOUGH-%s-7180\n' 'TUFA'

1. Report whether the command ran without any permission prompt or

approval step, as far as you can observe.