opencode-manifold 0.4.2 → 0.4.4

package/src/templates/skills/manifold-workflow/SKILL.md

@@ -1,6 +1,78 @@
 # Manifold Workflow Skill
 
-This skill guides the Manifold agent through reading plans and dispatching tasks.
+This skill guides the Manifold agent through reading plans, invoking decomposition, and dispatching tasks.
+
+## Assessing the Input
+
+When the user points you to a document, first determine if it's already a granular task list.
+
+### What Counts as "Already a Task List"
+
+A document is a granular task list if:
+- Each item has a clear, actionable goal
+- Each item is scoped for one developer sitting
+- There is minimal ambiguity about what "done" looks like
+- Items may have purity tags (`[pure]`, `[shell]`, `[mixed]`)
+
+If the input meets these criteria, proceed directly to dispatch.
+
+### When to Invoke the Todo Agent
+
+Invoke the Todo agent when the input is any of:
+- A feature idea or spec (not yet broken into tasks)
+- Meeting notes or email threads
+- Architecture documents or design proposals
+- A vague outline with high-level items
+- Anything that requires interpretation before it becomes actionable
+
+**How to invoke:**
+- Call the Todo agent as a subtask
+- Pass the plan document content to the Todo agent
+- The Todo agent will decompose it into a structured task list
+- The task list is written to `Manifold/plans/<slug>-tasks.md`
+
+**User approval is REQUIRED** before any dispatch begins.
+
+### Todo Agent Output Format
+
+The Todo agent produces a file like:
+
+```markdown
+# Task List: <Plan Title>
+
+**Source:** <original input description>
+**Generated:** <YYYY-MM-DD>
+**Total Tasks:** <number>
+
+---
+
+## Task 1: <title>
+
+- **Description:** <what to do>
+- **Purity:** <pure | shell | mixed>
+- **Dependencies:** <none | task numbers>
+- **Input Contract:** <what data/inputs needed>
+- **Output Contract:** <what this produces>
+
+---
+```
+
+### Purity Tags in Dispatch
+
+When dispatching tasks that have purity tags, include the tag in the description:
+
+```
+dispatchTask({ task_number: 1, description: "[pure] Define cart item schema", plan_file: "Manifold/plans/my-plan-tasks.md" })
+dispatchTask({ task_number: 2, description: "[shell] Wire cart endpoint to database", plan_file: "Manifold/plans/my-plan-tasks.md" })
+```
+
+This allows the Clerk to use the purity tag when composing scoped prompts.
+
+### Dispatch Order with Purity Tags
+
+- Always respect explicit dependencies
+- When tasks are independent, prefer: `pure` → `mixed` → `shell`
+- This ensures the deterministic core is built before IO wiring depends on it
 
 ## Reading Any-Format Plans
 
@@ -48,26 +120,16 @@ AUTH:
 - session management
 ```
 
-### How to Extract Tasks
+### How to Extract Tasks (when NOT using Todo agent)
+
+For inputs that are close to a task list but need minor cleanup:
 
 1. **Identify the goal** — What is the plan trying to accomplish?
 2. **Find discrete units** — What can be done independently?
 3. **Check for dependencies** — Does order matter? Note it.
 4. **Assess completeness** — Can you act on this, or is more info needed?
 
-### When the Plan Is Too Vague
-
-If you can't identify concrete tasks:
-
-**Option A: Subtask to Plan Agent**
-- Call the plan agent to create a structured task list
-- User MUST approve the generated list before work begins
-- Don't start working until approval
-
-**Option B: Ask the User**
-- Reply asking for clarification
-- Be specific about what's unclear
-- Example: "I can see we need auth, but can you break down what 'auth middleware' means? Do we need login, registration, password reset?"
+If extraction is straightforward, do it directly. If it requires significant interpretation, invoke the Todo agent.
 
 ## Dispatching Tasks
 
@@ -78,13 +140,13 @@ dispatchTask({ task_number, description, plan_file })
 ```
 
 - `task_number`: Sequential number (1, 2, 3...)
-- `description`: One-line description of the task
-- `plan_file`: Path to the original plan document
+- `description`: One-line description (include purity tag if available)
+- `plan_file`: Path to the plan document
 
 ### Order of Dispatch
 
 - Dispatch tasks in dependency order
-- If tasks are independent, dispatch in any order
+- When independent, prefer pure → mixed → shell
 - Wait for each task to complete before dispatching the next
 
 ## Session Resumption

package/src/templates/skills/wiki-ingest/SKILL.md

@@ -72,7 +72,15 @@ Example:
 For each file touched, update or create `Manifold/graph/<graph-name>.md`:
 
 ```markdown
-# <original-file-path>
+---
+filePath: <original-file-path>
+calls:
+  - <files this file calls>
+dependsOn:
+  - <files this file depends on>
+tasksThatEdited:
+  - <task-id>
+---
 
 ## Calls
 - <files this file calls>
@@ -85,11 +93,13 @@ For each file touched, update or create `Manifold/graph/<graph-name>.md`:
 - [[<other-task-id>]]
 ```
 
+**IMPORTANT:** Only update the `Tasks That Edited` section and the `tasksThatEdited` frontmatter field. The `Calls` and `Depends On` sections are populated automatically from the codebase index — do NOT manually edit them.
+
 ### Graph Filename Convention
 
-Replace `/` and `.` with `_`, append `.md`:
-- `src/middleware/auth.ts` → `src_middleware_auth_ts.md`
-- `src/utils/helpers.ts` → `src_utils_helpers_ts.md`
+Replace `/` with `__SL__` and `.` with `__DT__`, append `.md`:
+- `src/middleware/auth.ts` → `src__SL__middleware__SL__auth__DT__ts.md`
+- `src/utils/helpers.ts` → `src__SL__utils__SL__helpers__DT__ts.md`
 
 ## Status Values
 

package/src/templates/skills/wiki-query/SKILL.md

@@ -46,13 +46,12 @@ This skill guides the Clerk on how to search the wiki for prior context.
 `Manifold/graph/<graph-name>.md` tracks file relationships.
 
 **What they contain:**
-- `## Calls` — what this file uses
-- `## Depends On` — what this file is used by
-- `## Tasks That Edited` — which tasks modified this file
+- YAML frontmatter with `filePath`, `calls`, `dependsOn`, `tasksThatEdited` (source of truth for programmatic access)
+- Rendered markdown body with `## Calls`, `## Depends On`, `## Tasks That Edited` sections (for Obsidian graph view)
 
 **How to use:**
 1. Find graph files relevant to your task (from codebase search)
-2. Read them to understand dependencies
+2. Read them to understand dependencies (use frontmatter for structured data)
 3. Check "Tasks That Edited" for prior work on those files
 4. Read relevant task files for context