[codex] Add agent infrastructure documentation

[LarytheLord]

What changed

• added a new Infrastructure/README.md guide for clean-room agent runtime patterns across Open Paws projects
• linked the new infrastructure section from the root documentation index
• updated CLAUDE.md so contributors can discover the new docs alongside the existing knowledge, prediction, generation, and automation sections

Why

We now have agent-related implementation work happening across the scanner, platform, and tooling repos. This PR gives those efforts a shared architecture document and records the clean-room reuse policy so future work stays aligned.

Impact

• contributors have one place to understand how scanner export, quest ingestion, and tool-sensitivity work fit together
• the organization has a documented boundary between reusable product patterns and copied proprietary code
• future repo work can plug into a shared runtime direction instead of growing in isolation

Validation

• git diff --check

Notes

• this is documentation-only and does not change application behavior

Summary by CodeRabbit

• Documentation
  • Introduced comprehensive Agent Infrastructure documentation detailing clean-room agent runtime, orchestration patterns, sensitivity-aware tool safety frameworks, and human review mechanisms for high-impact actions
  • Documented implementation roadmap and key success criteria for infrastructure deployment
  • Updated main navigation to include new infrastructure guide

[coderabbitai]

📝 Walkthrough

Walkthrough

This pull request introduces documentation for a clean-room agent infrastructure pattern by adding a comprehensive Infrastructure/README.md file and updating the root documentation indexes. The documentation outlines core principles for agent runtime, orchestration, tool-safety patterns, and success criteria across three repository implementation tracks.

Changes

Cohort / File(s)	Summary
Documentation Index Updates README.md, CLAUDE.md	Added new "Agent Infrastructure" sections with references and links to the infrastructure documentation.
Agent Infrastructure Documentation Infrastructure/README.md	New comprehensive guide documenting clean-room agent infrastructure principles, shared runtime patterns, implementation tracks across repositories, and safety boundaries with success criteria.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~5 minutes

Poem

🐰 Hop, skip, and a bound,
New docs have been found!
Clean rooms for our agents so bright,
Infrastructure paths, now in sight—
Safety and orchestration, all done right! 🌟

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and specifically summarizes the main change: adding documentation for agent infrastructure across the Open Paws project.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch codex/agent-infrastructure-docs

---

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

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@Infrastructure/README.md`:
- Around line 47-51: The repeated use of "right" reduces readability; update one
of the phrases—either change "right layer" or "right sandbox"—to a synonym
(e.g., "appropriate," "ideal," or "proper") in the Infrastructure/README.md
section that includes "right layer for approval boundaries, operator controls,
and durable workflow state" and the "LarytheLord/Open-Paws-Tools-Platform"
paragraph to improve flow while keeping meaning intact.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro

Run ID: 3781c874-0c25-4fb1-a697-682f2ef30606

📥 Commits

Reviewing files that changed from the base of the PR and between 627493d and 868f655.

📒 Files selected for processing (3)

• CLAUDE.md
• Infrastructure/README.md
• README.md

[coderabbitai]

🧹 Nitpick | 🔵 Trivial

Consider varying word choice for better readability.

The word "right" appears twice in close proximity (lines 47 and 51: "right layer" and "right sandbox"). While not incorrect, using a synonym in one instance would make the text flow more smoothly.

✨ Proposed alternative wording

-The tools platform is the right sandbox for experimenting with more agentic UX before it is promoted into production systems. The first clean-room pattern to establish here is a central tool registry that can drive:
+The tools platform is the appropriate sandbox for experimenting with more agentic UX before it is promoted into production systems. The first clean-room pattern to establish here is a central tool registry that can drive:

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	This is the right layer for approval boundaries, operator controls, and durable workflow state.
	### `LarytheLord/Open-Paws-Tools-Platform`
	The tools platform is the right sandbox for experimenting with more agentic UX before it is promoted into production systems. The first clean-room pattern to establish here is a central tool registry that can drive:
	This is the right layer for approval boundaries, operator controls, and durable workflow state.
	### `LarytheLord/Open-Paws-Tools-Platform`
	The tools platform is the appropriate sandbox for experimenting with more agentic UX before it is promoted into production systems. The first clean-room pattern to establish here is a central tool registry that can drive:

🧰 Tools

🪛 LanguageTool

[style] ~51-~51: You have already used ‘right’ in nearby sentences. Consider using an alternative word to let your writing stand out and sound more polished.
Context: ...ls-Platform` The tools platform is the right sandbox for experimenting with more age...

(REP_RIGHT)

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In `@Infrastructure/README.md` around lines 47 - 51, The repeated use of "right"
reduces readability; update one of the phrases—either change "right layer" or
"right sandbox"—to a synonym (e.g., "appropriate," "ideal," or "proper") in the
Infrastructure/README.md section that includes "right layer for approval
boundaries, operator controls, and durable workflow state" and the
"LarytheLord/Open-Paws-Tools-Platform" paragraph to improve flow while keeping
meaning intact.