diff --git a/docs/dev/ADR-008-IMPLEMENTATION-PLAN.md b/docs/dev/ADR-008-IMPLEMENTATION-PLAN.md
index 7bbf7456f..901a949e1 100644
--- a/docs/dev/ADR-008-IMPLEMENTATION-PLAN.md
+++ b/docs/dev/ADR-008-IMPLEMENTATION-PLAN.md
@@ -1,6 +1,6 @@
 # ADR-008 Implementation Plan
 
-**Related ADR:** [ADR-008-sf-tools-over-mcp-for-provider-parity.md](/Users/jeremymcspadden/Github/sf-2/docs/ADR-008-sf-tools-over-mcp-for-provider-parity.md)
+**Related ADR:** [ADR-008-sf-tools-over-mcp-for-provider-parity.md](./ADR-008-sf-tools-over-mcp-for-provider-parity.md)
 **Status:** Draft
 **Date:** 2026-04-09
 
diff --git a/docs/dev/ADR-009-IMPLEMENTATION-PLAN.md b/docs/dev/ADR-009-IMPLEMENTATION-PLAN.md
index 2ac1363aa..f65c3ff4b 100644
--- a/docs/dev/ADR-009-IMPLEMENTATION-PLAN.md
+++ b/docs/dev/ADR-009-IMPLEMENTATION-PLAN.md
@@ -1,6 +1,6 @@
 # ADR-009 Implementation Plan
 
-**Related ADR:** [ADR-009-orchestration-kernel-refactor.md](/Users/jeremymcspadden/Github/sf-2/docs/dev/ADR-009-orchestration-kernel-refactor.md)  
+**Related ADR:** [ADR-009-orchestration-kernel-refactor.md](./ADR-009-orchestration-kernel-refactor.md)  
 **Status:** Draft  
 **Date:** 2026-04-14  
 **Target Window:** 8-10 waves (incremental, no big-bang rewrite)
diff --git a/src/resources/extensions/sf/prompts/parallel-research-slices.md b/src/resources/extensions/sf/prompts/parallel-research-slices.md
index 3162e648b..fed88350f 100644
--- a/src/resources/extensions/sf/prompts/parallel-research-slices.md
+++ b/src/resources/extensions/sf/prompts/parallel-research-slices.md
@@ -14,7 +14,7 @@ Dispatch ALL slices simultaneously using the `subagent` tool in **parallel mode*
 
 1. Call `subagent` exactly once with the JSON payload below
 2. Wait for ALL subagents to complete
-3. Verify each slice's RESEARCH file was written (check the `.sf/{{mid}}/` directory)
+3. Verify each slice's RESEARCH file was written (check the `.sf/milestones/{{mid}}/slices/<sliceId>/` directory for `<sliceId>-RESEARCH.md`)
 4. If any subagent failed to write its RESEARCH file, re-run it individually
 5. Report which slices completed research and which (if any) failed
 
diff --git a/src/resources/extensions/sf/prompts/validate-milestone.md b/src/resources/extensions/sf/prompts/validate-milestone.md
index 6d2659b14..19dd12df9 100644
--- a/src/resources/extensions/sf/prompts/validate-milestone.md
+++ b/src/resources/extensions/sf/prompts/validate-milestone.md
@@ -36,8 +36,8 @@ artifacts, not just trust the SUMMARY prose.
 ```
 subagent({
   parentTrace: "Slice claims to audit:\n" +
-               "- S01: <one-line claim> (.sf/{{milestoneId}}/S01-SUMMARY.md)\n" +
-               "- S02: <one-line claim> (.sf/{{milestoneId}}/S02-SUMMARY.md)\n" +
+               "- S01: <one-line claim> (.sf/milestones/{{milestoneId}}/slices/S01/S01-SUMMARY.md)\n" +
+               "- S02: <one-line claim> (.sf/milestones/{{milestoneId}}/slices/S02/S02-SUMMARY.md)\n" +
                "- ...",
   tasks: [
     { agent: "reviewer", task: "<Reviewer A prompt below>" },
@@ -49,7 +49,7 @@ subagent({
 
 **Reviewer A — Requirements Coverage**
 Agent: `reviewer`
-Prompt: "Review milestone {{milestoneId}} requirements coverage. Working directory: {{workingDirectory}}. Read `.sf/{{milestoneId}}/REQUIREMENTS.md` (or equivalent requirements file). For each requirement, check the slice SUMMARY files in `.sf/{{milestoneId}}/` to determine if it is: COVERED (clearly demonstrated), PARTIAL (mentioned but not fully demonstrated), or MISSING (no evidence). Output a markdown table with columns: Requirement | Status | Evidence. End with a one-line verdict: PASS if all covered, NEEDS-ATTENTION if partials exist, FAIL if any missing."
+Prompt: "Review milestone {{milestoneId}} requirements coverage. Working directory: {{workingDirectory}}. Read `.sf/REQUIREMENTS.md` (project-level). For each requirement, check the slice SUMMARY files in `.sf/milestones/{{milestoneId}}/slices/<sliceId>/<sliceId>-SUMMARY.md` to determine if it is: COVERED (clearly demonstrated), PARTIAL (mentioned but not fully demonstrated), or MISSING (no evidence). Output a markdown table with columns: Requirement | Status | Evidence. End with a one-line verdict: PASS if all covered, NEEDS-ATTENTION if partials exist, FAIL if any missing."
 
 **Reviewer B — Cross-Slice Integration**
 Agent: `reviewer`
@@ -57,7 +57,7 @@ Prompt: "Review milestone {{milestoneId}} cross-slice integration. Working direc
 
 **Reviewer C — Assessment & Acceptance Criteria**
 Agent: `reviewer`
-Prompt: "Review milestone {{milestoneId}} assessment evidence and acceptance criteria. Working directory: {{workingDirectory}}. Read `.sf/{{milestoneId}}/CONTEXT.md` for acceptance criteria. Check for ASSESSMENT files in each slice directory. Verify each acceptance criterion maps to either a passing assessment result or clear SUMMARY evidence. Then review the inlined milestone verification classes from planning. For each non-empty planned class, output a markdown table: Class | Planned Check | Evidence | Verdict. Use the exact class names `Contract`, `Integration`, `Operational`, and `UAT` whenever those classes are present. If no verification classes were planned, say that explicitly. Output two sections: `Acceptance Criteria` with a checklist `[ ] Criterion | Evidence`, and `Verification Classes` with the table. End with a one-line verdict: PASS if all criteria and verification classes are covered, NEEDS-ATTENTION if gaps exist."
+Prompt: "Review milestone {{milestoneId}} assessment evidence and acceptance criteria. Working directory: {{workingDirectory}}. Read `.sf/milestones/{{milestoneId}}/{{milestoneId}}-CONTEXT.md` for acceptance criteria. Check for ASSESSMENT files in each slice directory. Verify each acceptance criterion maps to either a passing assessment result or clear SUMMARY evidence. Then review the inlined milestone verification classes from planning. For each non-empty planned class, output a markdown table: Class | Planned Check | Evidence | Verdict. Use the exact class names `Contract`, `Integration`, `Operational`, and `UAT` whenever those classes are present. If no verification classes were planned, say that explicitly. Output two sections: `Acceptance Criteria` with a checklist `[ ] Criterion | Evidence`, and `Verification Classes` with the table. End with a one-line verdict: PASS if all criteria and verification classes are covered, NEEDS-ATTENTION if gaps exist."
 
 ### Step 2 — Synthesize Findings