Ethan Palm 4d690a2206 Name the eval job for what it measures ...

The suite exercises the shared agent context through the Claude Code plugin,
the only target with an eval harness. Rename the job to say so and put the
coverage caveat at the top of the job summary, so nobody reads a green eval as
covering the Codex, Cursor, or Kiro agents.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

2026-09-11 16:48:56 -07:00

..

build.mjs

Agent context single source (#6747)

2026-07-24 17:01:49 -07:00

check.mjs

feat: generate kiro power in agent-context (#6916)

2026-08-12 16:33:16 -07:00

eval-summary.mjs

Name the eval job for what it measures

2026-09-11 16:48:56 -07:00

lib.mjs

Write the Claude manifest to .claude-plugin/ where Claude Code reads it

2026-09-11 16:27:06 -07:00

status.mjs

Agent context single source (#6747)

2026-07-24 17:01:49 -07:00

sync-target.mjs

Agent context single source (#6747)

2026-07-24 17:01:49 -07:00