fix: harden agent mode safety checks

[lorenjphillips]

Summary

• Add focused agent-mode regression coverage for structured parse errors and --agent precedence over --format json.
• Lock down explicit local skill-source behavior so manifests do not advertise an embedded or remote catalog.
• Mark skill install next-actions as mutating, reject path-traversal skill IDs, and make runs context launch argv include required placeholders.

Testing

• cargo fmt
• cargo clippy --all-targets -- -D warnings
• cargo test
• cargo build --release
• git diff --check
• Manual release-binary smoke for manifest, skills next-action safety, and runs context argv
• Parallel subagent smoke lanes for discovery, skills, structured input, next-actions, full verification, and static audit

[coderabbitai]

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: b430ba54-8991-4cfb-9c0e-949caf2db454

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch feat/aci-5-coverage-polish

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[callumreid]

looks like rust to me!