[eldhothomas1]

Summary

Type of change

• Skill change (.claude/skills/<name>/) — eval fixtures updated below
• Tool / bridge contract (tools/<system>/*.md)
• Python package (tools/*/ with pyproject.toml)
• Groovy reference impl
• Cross-cutting (RFC, AGENTS.md, sandbox, privacy-LLM)
• Documentation (docs/, README.md, CONTRIBUTING.md)
• Project template (projects/_template/)
• CI / dev loop (prek, workflows, validators)
• Other:

Test plan

• prek run --all-files passes
• For Python packages touched: uv run pytest / ruff check / mypy passes
• For Groovy bridges touched: command-line invocation tested end-to-end
• For skill changes: eval suite passes for the affected skill
  (PYTHONPATH=tools/skill-evals/src python3 -m skill_evals.runner tools/skill-evals/evals/<skill>/)
• For skill behaviour changes: a new or updated eval fixture is included in this PR
  (a regression test for the bug fixed / the behaviour added — see CONTRIBUTING.md)
• Other:

RFC-AI-0004 compliance

• HITL — any new mutation is gated on explicit user confirmation
• Sandbox — no new unrestricted host access; network reach declared in the adapter
• Vendor neutrality — placeholders (<PROJECT>, <tracker>, <upstream>, <security-list>) used in all skill / tool prose (the check-placeholders prek hook is the mechanical gate)
• Conversational + correctable — agentic-override path documented if behaviour is adopter-tunable
• Write-access discipline — no autonomous outbound messages; drafts only, sent on confirmation
• Privacy LLM — private content does not reach a non-approved LLM; redactor invoked where needed

Linked issues

Notes for reviewers (optional)

[potiuk]

Checking the new copy before it replaces the old one is a good guard, and the rollback on a failed mv is right; the copy step and the check need a little more so the refresh works on a sandboxed marketplace install. Separately, the PR description is the untouched template: please fill in the ## Summary (what changed and why, with the issue it fixes) and ## Test plan, as CONTRIBUTING.md asks, and note that CI has not run yet because the workflows are waiting for a maintainer's approval.

Smaller observations

• See inline comments on plugins/magpie-setup/skills/setup/upgrade.md:430, plugins/magpie-setup/skills/setup/upgrade.md:431, plugins/magpie-setup/skills/setup/upgrade.md:420.

---

This review was drafted by an AI-assisted tool and
confirmed by an Apache Magpie maintainer. The findings
below are observations, not blockers; an Apache Magpie
maintainer — a real person — will take the next look at the
PR. If you think a finding is mis-applied, please reply on
the PR and a maintainer will weigh in.

More on how Apache Magpie handles maintainer review:
Contributing guide.

[potiuk]

On a marketplace install source_dir is under ~/.claude/plugins/cache/, which config.md Step 2a notes is read-denied to a sandboxed shell. This cp -RL then fails and the refresh never happens on exactly the setup it is for. Please say how the copy is made there (the file tool, or a command for the user).

[potiuk]

Please run the same check config does, without the cwd on sys.path: PYTHONPATH="$temp" python3 -P -m setup_preflight --skill magpie-setup --no-welcome. -c puts the working directory ahead of $temp, and an import alone does not prove the checker runs.

[potiuk]

<plugin-cache>, <installed-skill-dir> and <personal_dir from …> are not used anywhere else; AGENTS.md asks not to invent placeholders. The section already names both directories in prose, so the snippet can refer to those.