feat: three more agents, tool allowlists, and a README that records the tiers

Committed as-authored to establish a recoverable baseline before the
client-neutral architecture port rewrites these paths. No content is changed
here; this is the working tree as it stood.

- `plan-reviewer`, `pr-creator` and `release-notes` join the set.
- `refactor-scan` and `security-scanner` gain explicit `tools:` allowlists, so a
  review agent can no longer edit or write.
- The README's agent table records each agent's model tier and read-only status,
  and documents how to invoke the three new ones.

One gap is left as-is rather than fixed mid-baseline: `pr-creator` declares no
`tools:`, so it inherits the full tool pool while every sibling review agent is
constrained. It is also the only agent here that legitimately needs to write.

.claude/agents/refactor-scan.md

@@ -2,6 +2,7 @@
 name: refactor-scan
 description: Assesses refactoring opportunities after tests pass. Use proactively during TDD's third step (REFACTOR) or reactively to evaluate code quality improvements.
 model: sonnet
+tools: Read, Grep, Glob, Bash
 ---
 
 # Refactor Scan Agent