diff --git a/agent/skills/tasks/beads/SKILL.md b/agent/skills/tasks/beads/SKILL.md
deleted file mode 100644
index 91187d9..0000000
--- a/agent/skills/tasks/beads/SKILL.md
+++ /dev/null
@@ -1,78 +0,0 @@
----
-name: beads
-intent: tasks, workflow
-description: Manage tasks using the beads 9P interface. Use when creating, updating, listing, or deleting tasks/beads, or managing task dependencies.
----
-
-# Beads Task System
-
-Hierarchical task tracking via 9P. Persists to Dolt immediately.
-
-## Project Mount Discovery
-
-All beads commands listed in this skill must be run via `execute_code` tool.
-
-Find your project's beads mount:
-```bash
-MY_CWD=$(pwd)
-MOUNT=$(bash <(9p read agent/tools/beads/list_mounts.sh) | grep "$MY_CWD" | awk '{print $1}')
-```
-
-If no mount exists, create one:
-```bash
-bash <(9p read agent/tools/beads/mount_beads.sh) "$MY_CWD"
-```
-
-## Commands
-
-All beads commands listed in this skill must be run via `execute_code` tool.
-
-**CRITICAL:** All commands require `<mount>` as first argument (discovered via list_mounts.sh), except `mount_beads.sh` and `umount_beads.sh`.
-
-- Claim bead: `bash <(9p read agent/tools/beads/claim_bead.sh) <mount> bd-abc [$AGENT_ID]`
-- Complete bead: `bash <(9p read agent/tools/beads/complete_bead.sh) <mount> bd-abc`
-- Fail bead: `bash <(9p read agent/tools/beads/fail_bead.sh) <mount> bd-abc "reason"`
-- Create bead: `bash <(9p read agent/tools/beads/create_bead.sh) <mount> "title" "desc" [parent]`
-- Update bead: `bash <(9p read agent/tools/beads/update_bead.sh) <mount> bd-abc <field> <value>`
-- Add dependency: `bash <(9p read agent/tools/beads/add_dependency.sh) <mount> <child> <parent>`
-- Comment on bead: `bash <(9p read agent/tools/beads/comment_bead.sh) <mount> bd-abc "text"`
-- Label bead: `bash <(9p read agent/tools/beads/label_bead.sh) <mount> bd-abc <label>`
-- Delete bead: `bash <(9p read agent/tools/beads/delete_bead.sh) <mount> bd-abc`
-
-**Note:** Delete does not cascade. To delete a parent and all children, delete children first, then parent.
-
-## Queries
-
-- List ready beads: `bash <(9p read agent/tools/beads/list_ready_beads.sh) <mount>`
-- Read bead: `bash <(9p read agent/tools/beads/read_bead.sh) <mount> <id> json`
-- List children: `bash <(9p read agent/tools/beads/read_bead.sh) <mount> <id> children`
-- Search beads: `bash <(9p read agent/tools/beads/read_bead.sh) <mount> search <term>`
-- View history: `bash <(9p read agent/tools/beads/read_bead.sh) <mount> <id> events`
-
-## Workflow
-
-1. Find a ready task
-2. Claim the ticket being worked on
-3. Use agent-kb skill to search the knowledge base.
-4. Do work
-5. Verify all children completed
-6. Only if all children completed, complete the parent. Otherwise, work on other unblocked child tasks.
-
-## Rules
-
-- Discover your mount first using list_mounts.sh
-- Claim before working
-- Complete children before parent
-- Only parse JSON output
-- Never access `.beads/` directly
-- Comment during work (decisions, dead ends, discoveries)
-- Search past beads before starting
-
-## Description Quality
-
-Enable cold completion. Include:
-- Imperative verb + file path + `` `funcName()` `` or Acme address (`file:123,125` not `file:123-125`)
-- "How" signal (following X, same as Y) + acceptance criterion (must/should/returns)
-- Backticked identifiers + cross-ref for >150 chars
-
-Bypass lint: `IDEA:` prefix.
diff --git a/cfg/roles/default.yaml b/cfg/roles/default.yaml
index 612eed2..0bb4602 100644
--- a/cfg/roles/default.yaml
+++ b/cfg/roles/default.yaml
@@ -30,6 +30,8 @@ filesystem:
     - "{XDG_DATA_HOME}/gh/extensions"
   rw:
     - "{HOME}/.ssh/known_hosts"
+    - "{HOME}/pCloudDrive"
+    - "{HOME}/.pcloud"
     - "{HOME}/.git-credentials"
     - "{XDG_CONFIG_HOME}/git/credentials"
     - "{XDG_RUNTIME_DIR}/git/"
diff --git a/internal/p9/beads.go b/internal/p9/beads.go
index 1988346..b7707ac 100644
--- a/internal/p9/beads.go
+++ b/internal/p9/beads.go
@@ -356,6 +356,7 @@ func (b *BeadsFS) readListFromStore(store bd.Storage) ([]byte, error) {
 		*bd.Issue
 		Blockers        []string `json:"blockers,omitempty"`
 		CapabilityLevel string   `json:"capability_level,omitempty"`
+		CommentCount    int      `json:"comment_count,omitempty"`
 	}
 	result := make([]BeadWithBlockers, len(issues))
 	for i, issue := range issues {
@@ -374,6 +375,10 @@ func (b *BeadsFS) readListFromStore(store bd.Storage) ([]byte, error) {
 			result[i].Blockers = blockers
 		}
 		result[i].CapabilityLevel = extractCapabilityLevel(issue.Labels)
+		comments, err := store.GetIssueComments(b.ctx, issue.ID)
+		if err == nil && len(comments) > 0 {
+			result[i].CommentCount = len(comments)
+		}
 	}
 
 	return json.MarshalIndent(result, "", "  ")
@@ -609,12 +614,17 @@ func (b *BeadsFS) readBeadPropertyFromStore(store bd.Storage, beadID, property s
 			*bd.Issue
 			Blockers        []string `json:"blockers,omitempty"`
 			CapabilityLevel string   `json:"capability_level,omitempty"`
+			CommentCount    int      `json:"comment_count,omitempty"`
 		}
 		result := BeadWithBlockers{Issue: issue}
 		if blockers, err := b.getBlockersFromStore(store, beadID); err == nil {
 			result.Blockers = blockers
 		}
 		result.CapabilityLevel = extractCapabilityLevel(issue.Labels)
+		comments, err := store.GetIssueComments(b.ctx, beadID)
+		if err == nil && len(comments) > 0 {
+			result.CommentCount = len(comments)
+		}
 		return json.MarshalIndent(result, "", "  ")
 	case "comments":
 		comments, err := store.GetIssueComments(b.ctx, beadID)
diff --git a/skills/beads/SKILL.md b/skills/beads/SKILL.md
index 5ce799d..de2589f 100644
--- a/skills/beads/SKILL.md
+++ b/skills/beads/SKILL.md
@@ -48,6 +48,9 @@ All beads commands listed in this skill must be run via `execute_code` tool.
 - List all beads: `list_beads.sh <mount>`
 - Read bead: `read_bead.sh <mount> <id> <property>`
 - Read bead JSON: `read_bead.sh <mount> <id> json`
+- Read bead comments: `read_bead.sh <mount> <id> comments`
+
+**IMPORTANT:** When working on a bead, always check `comment_count` in the JSON output. If > 0, read comments for additional context, decisions, or blockers.
 
 ## Workflow