Restructure CLAUDE.md into modular rules + add pr-shepherd command (#750)

* refactor: restructure CLAUDE.md into modular rules and add pr-shepherd command

Trim CLAUDE.md from 710 lines to 92 by moving detailed guidance into
path-scoped `.claude/rules/` files that load on demand. Add a new
`/pr-shepherd` command that consolidates the full PR lifecycle
(review, fix, quality gate, CI fix loop, merge) into one workflow.

Changes:
- CLAUDE.md: keep only essentials (build commands, code style, architecture,
  module specs, config reference, debugging)
- .claude/rules/review-discipline.md: 15+ review rules, scoped to src/**/*.rs
- .claude/rules/database.md: dual-backend rules with SQL dialect translation
  table, scoped to src/db/** and migrations/**
- .claude/rules/safety-and-sandbox.md: safety layer and sandbox rules, scoped
  to src/safety/**, src/sandbox/**, src/secrets/**
- .claude/rules/testing.md: test tiers and patterns, scoped to src/** and tests/**
- .claude/rules/tools.md: tool architecture and implementation pattern, scoped
  to src/tools/** and tools-src/**
- .claude/commands/pr-shepherd.md: 7-phase PR lifecycle command that subsumes
  review-pr, respond-pr, ship, and manual CI fix loops

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address review feedback on CLAUDE.md restructure

- Restore project structure tree in CLAUDE.md (zmanian blocking)
- Create .claude/rules/skills.md with trust model, SKILL.md format,
  selection pipeline, and skill tools (zmanian blocking)
- Restore configuration section with key env vars (zmanian medium)
- Restore "Adding a New Channel" guide (zmanian medium)
- Add heartbeat mention to Workspace & Memory section (zmanian low)
- Fix pr-shepherd: replace `git add -A` with specific file staging (zmanian)
- Fix pr-shepherd: ask user for merge strategy instead of hardcoding --squash (zmanian)
- Fix pr-shepherd: replace `--watch` with polling + 10min timeout (zmanian)
- Fix testing.md: "skipped if DB is unreachable" not "expected to fail" (Copilot)

[skip-regression-check]

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address review comments on PR #750

- Narrow `crate::` import rule: `super::` is fine in tests and intra-module refs
- Fix capabilities file naming: `<name>.capabilities.json` sidecar, not bare `capabilities.json`
- Update mechanical verification checklist to match narrowed import rule

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* refactor: move Bedrock docs from CLAUDE.md to src/llm/CLAUDE.md

Bedrock provider details (auth, config, feature flag) belong in the
LLM module spec, not the top-level guide. Added file map entry,
provider table row, and dedicated section in src/llm/CLAUDE.md.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* refactor: move env var config block out of CLAUDE.md

Replace 20-line config block with one-liner pointing to .env.example
and src/llm/CLAUDE.md. Config details are only needed during deployment,
not everyday coding.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: use gh pr checkout for fork-safe PR checkout in pr-shepherd

Replaces git fetch/checkout with gh pr checkout {number} which
handles both same-repo and fork-based PRs automatically.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* fix: address Copilot review round 5 on PR #750

- Add gh pr list and gh pr checkout to pr-shepherd allowed-tools
- Align crate:: import rule in pr-shepherd with updated CLAUDE.md guidance
- Fix vector type in database.md: BLOB (flexible dims), not F32_BLOB(1536)
- Update MCP limitation: stdio/HTTP/Unix transports exist, no streaming

Co-Authored-By: Claude Opus 4.6 <[email protected]>

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>

src/llm/CLAUDE.md

@@ -19,6 +19,7 @@ Multi-provider LLM integration with circuit breaker, retry, failover, and respon
 | `rig_adapter.rs` | Adapter bridging rig-core `CompletionModel` → `LlmProvider`; used by OpenAI, Anthropic, Ollama, Tinfoil |
 | `smart_routing.rs` | `SmartRoutingProvider` — 13-dimension complexity scorer routes cheap vs primary model |
 | `recording.rs` | `RecordingLlm` — trace capture for E2E replay testing (`IRONCLAW_RECORD_TRACE`) |
+| `bedrock.rs` | AWS Bedrock provider via native Converse API (feature-gated: `--features bedrock`) |
 
 ## Provider Selection
 
@@ -32,6 +33,18 @@ Set via `LLM_BACKEND` env var:
 | `ollama` | Ollama local | `OLLAMA_BASE_URL` |
 | `openai_compatible` | Any OpenAI-compatible endpoint | `LLM_BASE_URL`, `LLM_API_KEY`, `LLM_MODEL` |
 | `tinfoil` | Tinfoil TEE inference | `TINFOIL_API_KEY`, `TINFOIL_MODEL` |
+| `bedrock` | AWS Bedrock (requires `--features bedrock`) | `BEDROCK_REGION`, `BEDROCK_MODEL`, `AWS_PROFILE` |
+
+## AWS Bedrock Provider
+
+Uses the native Converse API via `aws-sdk-bedrockruntime` (`bedrock.rs`). Requires `--features bedrock` at build time — not in default features due to heavy AWS SDK dependencies.
+
+**Auth:** Standard AWS credential chain — IAM credentials (`AWS_ACCESS_KEY_ID`/`AWS_SECRET_ACCESS_KEY`), SSO profiles (`AWS_PROFILE`), or instance roles. The SDK resolves auth automatically from the environment.
+
+**Config:**
+- `BEDROCK_REGION` — AWS region (default: `us-east-1`)
+- `BEDROCK_MODEL` — Required model ID (e.g., `anthropic.claude-opus-4-6-v1`)
+- `BEDROCK_CROSS_REGION` — Optional cross-region inference prefix (`us`, `eu`, `apac`, `global`)
 
 ## NEAR AI Provider Gotchas