AGENTS.md § Gates is the one gate list; cli_contract.GATES and docs verify hold it

The gate list contradicted itself across AGENTS.md, instructions/gates.md and the
command records' gate names. The Rebase-Review Gate is now listed, `new project`'s
exit 42 is no longer a pseudo-gate, gates.md and the explanation page link to the one
list instead of counting, and a register plus a docs verify check keep the three in step.

Files changed:
- AGENTS.md
- CHANGES.md
- VERSION
- docs/explanation/why-gates-are-code.md
- docs/reference/commands/pages.md
- docs/reference/commands/types-instructions-and-docs.md
- docs/reference/exit-codes.md
- instructions/gates.md
- tools/CONTRACT.md
- tools/chemenu/cli_contract.py
- tools/chemenu/commands/docs_verify.py
- tools/chemenu/commands/doctor.py
- tools/chemenu/commands/git_publish.py
- tools/chemenu/commands/new_page.py
- tools/chemenu/errors.py
- tools/chemenu/mcp/server.py
- tools/chemenu/tests/test_cli_contract.py
- tools/chemenu/tests/test_docs_verify.py
- tools/chemenu/tests/test_git_publish.py
- tools/chemenu/tests/test_reference_doc.py

Co-Authored-By: Claude Code <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SnAJ7Z3CpVD3PRbN73QtU2

docs/reference/commands/pages.md

@@ -85,7 +85,6 @@ tools/wikitool new project --name "Homelab migration" --set responsibility=infra
 - Atomic: `new <type>`: Yes - single file write. `new project`: **No** for the tracker-configured case - a tracker-project write (or its human-clearance request) happens before the kb/ page write, so a failure between the two leaves a tracker project with no page (a state `review`'s check 3 already reports), never a page with no tracker project. Still a single file write when no tracker is configured
 - Counts toward the session call budget: yes
 - Can reach the network: no
-- Gates: human-intervention-required (`new project` only) - see [exit codes and gates](../exit-codes.md)
 
 **Exit codes**