Preserve Setup context and reference loading after launcher refusal, disclose the failure before editing, and limit Claude skill-directory substitution to SKILL.md. Add plugin-path and denied-launcher behavior regressions. Addresses part of #744 without closing its remaining scope.
AI assistance: Cursor on the original contribution; Codex on maintainer-directed follow-up fixes and validation.
Keep allowed-tools in shared source and suppress it only for Claude output and the plugin. Verified against current main with provider builds, local tests, real plugin loader checks, and an activation-only Claude A/B test reproducing the original denial and successful fixed activation. AI-assisted implementation and verification under maintainer direction.
* Plugin rewrite: follow Setup step 1 to the engine launcher
The plugin subtree rewrite still keyed on the Node-era Setup sentence
and allowed-tools line, so bun run build:release failed its drift check
on main after #714 merged (Sync Generated Provider Output run
33902030478). The fallback sentence, its plugin replacement, the
pre-approval line removal, and the drift verifier now follow the
launcher form, and the launcher path is quoted so a base directory with
spaces survives, with the verb left outside the quotes.
Co-Authored-By: Claude Code <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Vau2X53xGTjjTCXWMVBoNY
* Tests: pin the legacy node pre-approval rejection too
Co-Authored-By: Claude Code <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Vau2X53xGTjjTCXWMVBoNY
---------
Co-authored-by: Claude Code <noreply@anthropic.com>
Makes plugin instructions execute the installed plugin copy, safely quotes paths containing spaces, removes the broad Node pre-approval, and ships guarded generated plugin output.\n\nAI-assisted maintainer conflict resolution, review, and validation by Codex under maintainer direction.
Abdul WahabandGitHub
