feat: add agent discovery and next actions

[lorenjphillips]

Summary

• Adds the singular agent meta-command with doctor and manifest.
• Adds product-accurate Coval discovery language, agent_mode.argv_prefix, and help_argv pointers so agents can use --help for exhaustive flags instead of relying on duplicated context.
• Adds context to every resource namespace and routes contexts before auth.
• Adds centralized next-action constructors and applies safe follow-up actions across resource commands.
• Keeps the skills profile explicitly unimplemented for now; no skill catalog, repo URL, or remote source is embedded in the binary.

Testing

• cargo fmt
• cargo clippy --all-targets -- -D warnings
• cargo test

Stacked PR 2 of 5. Base is feat/aci-1-agent-mode-foundation. No version bump or release changes.

[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: 1f0631f2-2a13-4622-8153-a3b1c1c9c334

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-2-discovery-context-next-actions

---

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

[callumreid]

looks like rust to me!