Naiyuan Qing fdd5e82dfd feat(runtime): add source-authority escape hatch to the brief ...

The brief already tells agents to run `--help` for command discovery, but
nothing stated the trust precedence when a skill, the brief, or a doc seems to
contradict actual behavior. Add one line to the Available Commands escape-hatch
note: trust the live CLI (`--help`/`--output json`) and the checked-out source
over source-traced prose that can lag the code, and verify on any conflict or
confusion. Kept in the always-on brief (universal, needed before any skill
loads) rather than duplicated into each skill; per-skill source-map pointers
remain the specific layer.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>

2026-06-03 17:05:58 +08:00

..

cmd

feat(cli): add skill content file and stdin input (#3652)

2026-06-02 17:25:37 +08:00

internal

feat(runtime): add source-authority escape hatch to the brief

2026-06-03 17:05:58 +08:00

migrations

feat(workspace): add per-workspace logo upload (#2760)

2026-06-01 16:48:05 +02:00

pkg

feat: add opencode thinking variants

2026-06-02 13:15:14 +08:00

go.mod

fix(skills): parse multi-line YAML frontmatter in SKILL.md (#3495) (#3543)

2026-06-01 19:35:01 +08:00

go.sum

…

sqlc.yaml

…