planning: observe step, task dispatcher, tool parallel annotations, graceful degradation

- agents: agentSpawn uses 'task prime', postTurn uses 'task list' (observe step)
- scripts/x/task: dispatcher routes to bd (beads) or todo.sh based on availability
- prompts/tools-todosh.md: prime context for todo.sh fallback
- tools: add '# ollie:parallel read' annotation to file_read, file_glob, file_grep,
  file_grep, memory_recall, reasoning_think, denote_view
- core: update submodule ref

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

agents/coding.json

@@ -1,5 +1,5 @@
 {
-	"prompt": "You are a coding agent.\n\n# Code modification\n\n- Never modify code you haven't read. Read the file first, understand the context, then change it.\n- When modifying a file, also read files it imports or depends on, and files that depend on it.\n- When asked to understand or explain code, explore broadly — enumerate source files, read all relevant files, don't stop at entry points or documentation.\n- Reference specific code locations as `file_path:line_number`.\n\n# Discipline\n\n- Only make changes that are directly requested or clearly necessary.\n- Don't add features, refactor code, or make improvements beyond what was asked.\n- Don't add error handling for scenarios that can't happen. Trust internal code; only validate at system boundaries.\n- Don't create abstractions for one-time operations. Three similar lines is better than a premature abstraction.\n- Don't add docstrings, comments, or type annotations to code you didn't change.\n- If something is unused after your changes, delete it completely. No backwards-compatibility hacks, no `// removed` comments.\n- Never create files unless necessary for the task. Prefer editing existing files.\n\n# Good output\n\n- Code you produce should compile and, where applicable, pass existing tests without modification.\n- Changes should be minimal and surgical — a diff that is hard to argue with.\n- If you are uncertain whether a change is correct, say so explicitly rather than committing to a guess.\n\n# Security\n\n- Do not introduce security vulnerabilities: command injection, XSS, SQL injection, path traversal, etc.\n- If you notice insecure code you wrote, fix it immediately.",
+	"prompt": "You are a coding agent.\n\n# Code modification\n\n- Never modify code you haven't read. Read the file first, understand the context, then change it.\n- When modifying a file, also read files it imports or depends on, and files that depend on it.\n- When asked to understand or explain code, explore broadly \u2014 enumerate source files, read all relevant files, don't stop at entry points or documentation.\n- Reference specific code locations as `file_path:line_number`.\n\n# Discipline\n\n- Only make changes that are directly requested or clearly necessary.\n- Don't add features, refactor code, or make improvements beyond what was asked.\n- Don't add error handling for scenarios that can't happen. Trust internal code; only validate at system boundaries.\n- Don't create abstractions for one-time operations. Three similar lines is better than a premature abstraction.\n- Don't add docstrings, comments, or type annotations to code you didn't change.\n- If something is unused after your changes, delete it completely. No backwards-compatibility hacks, no `// removed` comments.\n- Never create files unless necessary for the task. Prefer editing existing files.\n\n# Good output\n\n- Code you produce should compile and, where applicable, pass existing tests without modification.\n- Changes should be minimal and surgical \u2014 a diff that is hard to argue with.\n- If you are uncertain whether a change is correct, say so explicitly rather than committing to a guess.\n\n# Security\n\n- Do not introduce security vulnerabilities: command injection, XSS, SQL injection, path traversal, etc.\n- If you notice insecure code you wrote, fix it immediately.",
 	"mcpServers": {
 		"superpowers-mcp-server": {
 			"command": "superpowers-mcp-server",
@@ -15,7 +15,7 @@
 	],
 	"hooks": {
 		"agentSpawn": [
-			"bd prime 2>/dev/null || true",
+			"task prime 2>/dev/null || true",
 			"$OLLIE/x/elevate-adapter-start 2>/dev/null || true",
 			"$OLLIE/x/prime tools-file",
 			"$OLLIE/x/prime tools-reasoning",
@@ -27,7 +27,7 @@
 			"true"
 		],
 		"postTurn": [
-			"true"
+			"task list 2>/dev/null || true"
 		]
 	}
 }

agents/default.json

@@ -4,7 +4,7 @@
 	],
 	"hooks": {
 		"agentSpawn": [
-			"bd prime 2>/dev/null || true",
+			"task prime 2>/dev/null || true",
 			"$OLLIE/x/elevate-adapter-start 2>/dev/null || true",
 			"$OLLIE/x/prime tools-file",
 			"$OLLIE/x/prime tools-reasoning",
@@ -15,7 +15,7 @@
 			"true"
 		],
 		"postTurn": [
-			"true"
+			"task list 2>/dev/null || true"
 		]
 	}
 }

agents/devops.json

@@ -5,7 +5,7 @@
 	],
 	"hooks": {
 		"agentSpawn": [
-			"bd prime 2>/dev/null || true",
+			"task prime 2>/dev/null || true",
 			"$OLLIE/x/elevate-adapter-start 2>/dev/null || true",
 			"$OLLIE/x/prime tools-file",
 			"$OLLIE/x/prime tools-reasoning",
@@ -17,7 +17,7 @@
 			"true"
 		],
 		"postTurn": [
-			"true"
+			"task list 2>/dev/null || true"
 		]
 	}
 }

agents/greybeard.json

@@ -5,7 +5,7 @@
 	],
 	"hooks": {
 		"agentSpawn": [
-			"bd prime 2>/dev/null || true",
+			"task prime 2>/dev/null || true",
 			"$OLLIE/x/elevate-adapter-start 2>/dev/null || true",
 			"$OLLIE/x/prime tools-file",
 			"$OLLIE/x/prime tools-reasoning",
@@ -16,7 +16,7 @@
 			"true"
 		],
 		"postTurn": [
-			"true"
+			"task list 2>/dev/null || true"
 		]
 	}
 }

agents/qa.json

@@ -5,7 +5,7 @@
 	],
 	"hooks": {
 		"agentSpawn": [
-			"bd prime 2>/dev/null || true",
+			"task prime 2>/dev/null || true",
 			"$OLLIE/x/elevate-adapter-start 2>/dev/null || true",
 			"$OLLIE/x/prime tools-file",
 			"$OLLIE/x/prime tools-reasoning",
@@ -16,7 +16,7 @@
 			"true"
 		],
 		"postTurn": [
-			"true"
+			"task list 2>/dev/null || true"
 		]
 	}
 }

agents/reviewer.json

@@ -5,7 +5,7 @@
 	],
 	"hooks": {
 		"agentSpawn": [
-			"bd prime 2>/dev/null || true",
+			"task prime 2>/dev/null || true",
 			"$OLLIE/x/elevate-adapter-start 2>/dev/null || true",
 			"$OLLIE/x/prime tools-file",
 			"$OLLIE/x/prime tools-reasoning",
@@ -16,7 +16,7 @@
 			"true"
 		],
 		"postTurn": [
-			"true"
+			"task list 2>/dev/null || true"
 		]
 	}
 }

agents/writer.json

@@ -5,7 +5,7 @@
 	],
 	"hooks": {
 		"agentSpawn": [
-			"bd prime 2>/dev/null || true",
+			"task prime 2>/dev/null || true",
 			"$OLLIE/x/elevate-adapter-start 2>/dev/null || true",
 			"$OLLIE/x/prime tools-file",
 			"$OLLIE/x/prime tools-reasoning",
@@ -16,7 +16,7 @@
 			"true"
 		],
 		"postTurn": [
-			"true"
+			"task list 2>/dev/null || true"
 		]
 	}
 }

core

@@ -1 +1 @@
-Subproject commit 77dd5c6168e16a4e070d59715ffefc1d523d702e
+Subproject commit 6abf0cdb3d27a7728cc3156f4a80b52e0d6f8978

prompts/tools-todosh.md

@@ -0,0 +1,32 @@
+# Task Tracking (todo.sh)
+
+No `.beads` directory found. Task tracking is available via `todo.sh`.
+
+todo.sh uses a plain-text `todo.txt` file. Tasks are numbered lines; numbers
+shift after deletions, so always re-list before referencing by number.
+
+## Core commands
+
+| Command | Effect |
+|---|---|
+| `todo.sh add "TASK +project @context"` | Add a task |
+| `todo.sh list [TERM]` | List open tasks (optionally filtered) |
+| `todo.sh listall [TERM]` | List all tasks including done |
+| `todo.sh do NR` | Mark task NR complete |
+| `todo.sh del NR` | Delete task NR |
+| `todo.sh pri NR A` | Set priority A–Z on task NR |
+| `todo.sh append NR "TEXT"` | Append text to task NR |
+| `todo.sh replace NR "NEW TEXT"` | Replace task NR entirely |
+
+## Conventions
+
+- `+project` tags group related tasks
+- `@context` tags indicate where/how (e.g. `@code`, `@review`, `@shell`)
+- Priority `(A)` is highest; unprioritised tasks sort below all lettered ones
+
+## Session close protocol
+
+Before ending the session, mark completed tasks done:
+```
+todo.sh do NR
+```

scripts/x/task

@@ -0,0 +1,26 @@
+#!/bin/bash
+# Task dispatcher: routes to bd (beads) or todo.sh depending on availability.
+# Usage: task prime | task list
+
+cmd="${1:-list}"
+
+dir="$PWD"
+while [ "$dir" != "/" ]; do
+    if [ -d "$dir/.beads" ]; then
+        case "$cmd" in
+            prime) exec bd prime ;;
+            list)  exec bd list --status open ;;
+        esac
+    fi
+    [ ! -e "$dir/.git" ] && break
+    dir="$(dirname "$dir")"
+done
+
+if command -v todo.sh >/dev/null 2>&1; then
+    case "$cmd" in
+        prime) exec prime tools-todosh ;;
+        list)  exec todo.sh list ;;
+    esac
+fi
+
+exit 0

tools/denote_view

@@ -1,4 +1,5 @@
 #!/bin/bash
+# ollie:parallel read
 # capabilities: agent-kb
 # description: View a denote document by identifier
 # Usage: view_denote.sh --id <denote:identifier|identifier>

tools/file_glob

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# ollie:parallel read
 # description: Find files by name/path pattern, sorted by modification time (newest first)
 # Args: <pattern> [path]
 

tools/file_grep

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+# ollie:parallel read
 # description: Search file contents using ripgrep
 # Args: <pattern> [--path=<dir>] [--mode=files_with_matches|content|count] [--glob=<pattern>] [--type=<type>] [-i] [-n] [-A <n>] [-B <n>] [-C <n>] [--multiline] [--head=<n>] [--offset=<n>]
 

tools/file_read

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# ollie:parallel read
 # description: Read a file from the local filesystem with optional offset and line limit
 # Args: <file_path> [offset] [limit]
 

tools/memory_recall

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# ollie:parallel read
 # description: Search memories by keyword, tag, or title
 # Args: <query>
 

tools/reasoning_think

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# ollie:parallel read
 # description: Internal reasoning scratchpad; think through complex problems before acting
 # Args: <thought>