docs: two POC modes — branch vs standalone scratch project

- pocs.md: define both modes + per-POC assignment (POC-1/2 standalone at
  /workspace/alkgit-pocN, POC-3 branch mode); findings are the
  deliverable, POC source never merges to main
- sdd_process.md: phase 0 + POC Specialist sections cover both modes
- poc-specialist.md: mode determination up front, standalone environment
  section, 'stay in your lane' principle updated
- AGENTS.md: lifecycle status describes the two modes

Verified: none needed (markdown only)

docs/research/pocs.md

@@ -1,8 +1,24 @@
 # alkgit POC Plan
 
-POCs live in research worktrees (`.worktrees/research/<task-id>/`) per
-sdd_process phase 0, or as scratch experiments outside the main workspace
-tree if a worktree isn't available yet. Each POC records: hypothesis,
+## POC modes
+
+POCs are not production code — fewer constraints (comments, unwrap, error
+taxonomy are all relaxed), and their code never merges to main. Two modes,
+chosen by whether the POC touches code in this repo:
+
+- **Branch mode** (POC depends on alkgit code in the repo): create a git
+  branch off main, do the work there, then **merge the findings into the
+  research docs** on main and drop the branch — the POC code itself does
+  not merge.
+- **Standalone mode** (POC is independent of alkgit code): a scratch crate
+  or project at `/workspace/<poc-name>` (e.g. `/workspace/alkgit-poc1`),
+  outside the repo entirely. Findings are written directly into
+  `docs/research/` on main.
+
+In both modes the deliverable on main is the findings write-up, not the
+POC source. POC source is disposable once findings are recorded.
+
+Each POC records: hypothesis,
 method, result (proceed/pivot/block), and what it changes in the research
 docs.
 
@@ -68,4 +84,13 @@ for receive-pack sizing.
 
 POC-1 first (the BiStream/packetline fit is the load-bearing assumption).
 POC-2 next (the crux of fetch). POC-3 last (http shape). Each POC updates
-the corresponding research doc with results and a proceed/pivot/block note.
+the corresponding research doc with results and a proceed/pivot/block note.
+
+## Modes applied to these POCs
+
+- POC-1, POC-2: **standalone mode** — nothing in the alkgit repo exists to
+  build on yet; run as `/workspace/alkgit-poc1` and `/workspace/alkgit-poc2`.
+  (If POC-1's bridge turns out to want the workspace deps, it can flip to
+  branch mode on the repo instead — decide before writing, not after.)
+- POC-3: **branch mode** — it exercises alkhttp wiring against this repo's
+  skeleton; findings merge into `alk-stack.md`, branch is dropped after.

docs/sdd_process.md

@@ -33,10 +33,19 @@ problems need investigation.
 
 1. Capture vision and guiding principles
 2. Research Specialist investigates options (`docs/research/` or external)
-3. POC Specialist validates promising approaches (`.worktrees/research/`)
+3. POC Specialist validates promising approaches
 4. Document learnings
 5. Converge on recommended approach
 
+**POC placement (two modes)** — POC code never merges to main; the
+deliverable is the findings write-up:
+
+- **Branch mode** (POC builds on code in this repo): git branch off main,
+  work there, merge findings into research docs, drop the branch.
+- **Standalone mode** (POC independent of this repo's code): scratch
+  project at `/workspace/<poc-name>`, outside the repo. Findings go into
+  `docs/research/` on main directly.
+
 **Output**: Clear understanding of WHAT to build and WHY, with validated
 approaches
 
@@ -89,7 +98,10 @@ WHAT, ADRs explain WHY, open questions track what's unresolved.
 2. Coordinator spawns worktrees + sessions (via
    `worktree({action: "spawn", ...})` or hub `coord.spawn` when available)
    - Feature work: `.worktrees/feat/<task-id>/` → Implementation Specialist
-   - Research POCs: `.worktrees/research/<task-id>/` → POC Specialist
+   - Research POCs building on repo code: `.worktrees/research/<task-id>/`
+     → POC Specialist (branch mode)
+   - Research POCs independent of repo code: standalone scratch project at
+     `/workspace/<poc-name>` → POC Specialist (standalone mode)
 3. Coordinator injects task context into each session
 4. Agents execute tasks with self-verification
 5. On completion: agent notifies coordinator, updates task status, commits to
@@ -312,9 +324,11 @@ limited set (current, notify, status). No mode toggle required.
 **Responsibility**: Create proof-of-concepts to validate technical approaches
 before production implementation.
 
-**Mode**: Primary (works in isolated research worktree)
+**Mode**: Primary (branch mode: isolated research worktree; standalone
+mode: scratch project outside the repo)
 
-**Worktree Location**: `.worktrees/research/<task-id>/`
+**Worktree Location**: `.worktrees/research/<task-id>/` (branch mode) or
+`/workspace/<poc-name>` (standalone mode)
 
 **Tools**:
 
@@ -324,8 +338,10 @@ before production implementation.
 **Key Behaviors**:
 
 - Create minimal POCs to validate hypotheses
-- Work in isolated research worktrees
-- Document findings and recommendations
+- Branch mode: work in isolated research worktrees; standalone mode: work
+  in the scratch project only
+- Document findings and recommendations (findings are the deliverable —
+  POC source is disposable and never merges to main)
 - Timebox strictly - abandon if taking too long
 - Be honest about limitations and blockers