Add dev namespace access and kubectl to POLICIES.md and TOOLS.md

Each org now has a -dev namespace where agents can freely use kubectl
for testing and iteration. Production namespaces remain Flux-only.

Access model:
- Cluster-wide: read-only
- Production namespace: read-write (Flux-managed, no manual kubectl)
- Dev namespace: read-write (agents may use kubectl freely)

Co-Authored-By: Paperclip <noreply@paperclip.ing>

POLICIES.md

@@ -36,8 +36,13 @@ The following services are available in the cluster. Use them via their operator
 All infrastructure changes deploy via **Flux GitOps**. Flux reconciles the org's `infra` repo to the cluster automatically.
 
 - **The only way to change Kubernetes resources is through the infra repo.** Commit manifests, push, and Flux deploys. There is no other path.
-- **`kubectl` is read-only.** You may use `kubectl get`, `kubectl describe`, `kubectl logs`, etc. for troubleshooting and verification. You may NEVER use `kubectl apply`, `kubectl delete`, `kubectl edit`, `kubectl patch`, `kubectl create`, or any other mutating command. Flux will revert any manual changes.
-- If you need an infrastructure change, create a PR against the infra repo (or create a Paperclip issue for the agent who owns infra).
+- **`kubectl` is available** and agents have the following access:
+  - **Cluster-wide**: read-only (`get`, `list`, `watch`) across all namespaces
+  - **`privilegedescalation` namespace**: read-write (production — changes MUST go through Flux, not kubectl)
+  - **`privilegedescalation-dev` namespace**: read-write (development — agents may use kubectl freely for testing, debugging, and iteration)
+- **Production (`privilegedescalation`)**: All changes go through the infra repo and Flux. Do not `kubectl apply` to production. Flux will revert manual changes.
+- **Development (`privilegedescalation-dev`)**: Agents may `kubectl apply`, `kubectl delete`, and use any mutating commands freely. This namespace is for testing and validation before committing to the infra repo.
+- If you need a production infrastructure change, create a PR against the infra repo (or create a Paperclip issue for the agent who owns infra).
 
 ## Git Workflow
 

TOOLS.md

@@ -25,6 +25,7 @@ Auto-injected env vars:
 | `node` / `npm` / `pnpm` / `npx` | Node.js runtime and package management |
 | `python3` | Python scripting |
 | `pnpm paperclipai` | Paperclip CLI — issue/agent operations |
+| `kubectl` | Kubernetes CLI — read-only cluster-wide, read-write in `privilegedescalation` and `privilegedescalation-dev` |
 
 ## Repos