@raquezha/norpiv 0.0.6 → 0.0.7

package/README.md

@@ -2,6 +2,10 @@
 
 RPIV: a gated workflow for reliable AI coding agents.
 
+RPIV is one implementation of the broader `nothing` Workflow Contract. The contract defines the generic shape for workflows such as RPIV and Research, focusing on 3 Real Modes (Chat, Research, RPIV) tracked by `.workflow/active.json`.
+
+Standalone package usage still works: `@raquezha/norpiv` includes the RPIV skills, `distill`, and helper scripts needed for handoff. The local Research workflow lives separately under `packages/workflows/noresearch`. The platform-level contract lives in the source repo at <https://github.com/raquezha/nothing/blob/main/docs/workflow.md>.
+
 ## 🔁 The Lifecycle
 
 The RPIV engine splits task execution into separate, focused phases:
@@ -112,6 +116,8 @@ Obsidian note → /triage → RPIV             (only when ready to commit)
 
 `distill` is the missing layer before RPIV. Use `pi --notes` to load it.
 
+Research is a separate local workflow bundle in `packages/workflows/noresearch` and is loaded by the full `nothing` setup with `pi --research`.
+
 ## 🚀 Quick Start Example
 
 1. **Activate the RPIV Hat** from the full `nothing` setup:

package/frame/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: frame
+workflow: rpiv
+workflowPhase: frame
 description: Define the task brief inside the active WORK.md. Use after /triage to convert issue data into a clear Problem or Proposal brief without creating separate PROBLEM.md or PRD.md files.
 ---
 
@@ -8,7 +10,7 @@ description: Define the task brief inside the active WORK.md. Use after /triage
 Turn raw task context into the stable "what/why" brief.
 
 ## Guardrails
-- READ: `.workflow/active_task.json`, `.workflow/tasks/[active_task]/WORK.md`, and `.reposcry/AI_CONTEXT.md` when present.
+- READ: `.workflow/active.json` / `.workflow/active_task.json`, active `WORK.md`, and `.reposcry/AI_CONTEXT.md` when present.
 - WRITE: `WORK.md` -> `[BRIEF]` section and append to `[LOG]` only; optional `.reposcry/AI_CONTEXT.md` when RepoScry is installed.
 - NEVER: create `PROBLEM.md`, `PRD.md`, or extra planning files.
 - NEVER: overwrite `[PLAN]` or `[GRILL]`.

package/grill-with-docs/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: grill-with-docs
+workflow: rpiv
+workflowPhase: grill-with-docs
 description: Stress-test the active WORK.md brief against docs, code, and domain language. Use after /frame before planning to clarify assumptions and update durable docs only when decisions are stable.
 ---
 
@@ -8,7 +10,7 @@ description: Stress-test the active WORK.md brief against docs, code, and domain
 Challenge the brief before planning. This replaces passive ubiquitous-language collection with active clarification.
 
 ## Guardrails
-- READ: `.workflow/active_task.json`, active `WORK.md` `[BRIEF]`, `CONTEXT.md`, relevant `docs/agents/*`, and `.reposcry/AI_CONTEXT.md` when present.
+- READ: `.workflow/active.json` / `.workflow/active_task.json`, active `WORK.md` `[BRIEF]`, `CONTEXT.md`, relevant `docs/agents/*`, and `.reposcry/AI_CONTEXT.md` when present.
 - WRITE: `WORK.md` -> append to `[GRILL]` and `[LOG]` only; durable docs only when a stable rule is confirmed.
 - NEVER: edit `[BRIEF]` silently; propose brief changes if contradictions are found.
 - NEVER: plan or implement during grilling.

package/implement/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: implement
+workflow: rpiv
+workflowPhase: implement
 description: Implement the next approved vertical slice from the active WORK.md and prepare a Draft PR/MR. Use when the plan is approved and the user explicitly asks to implement.
 ---
 
@@ -8,7 +10,7 @@ description: Implement the next approved vertical slice from the active WORK.md
 Execute one functional vertical slice and hand it to the human for review.
 
 ## Guardrails
-- READ: `.workflow/active_task.json` then active `WORK.md` `[PLAN]`, `[BRIEF]`, and relevant `[LOG]` evidence.
+- READ: `.workflow/active.json` / `.workflow/active_task.json` then active `WORK.md` `[PLAN]`, `[BRIEF]`, and relevant `[LOG]` evidence.
 - WRITE: code changes and `WORK.md` -> append to `[LOG]` only; optional `.reposcry/` cache refresh when RepoScry is installed.
 - NEVER: edit `[BRIEF]` or `[GRILL]`.
 - NEVER: implement without explicit user instruction.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@raquezha/norpiv",
-  "version": "0.0.6",
+  "version": "0.0.7",
   "description": "Bundled RPIV workflow skills for Pi, Claude, and Codex-style coding agents",
   "type": "commonjs",
   "bin": {

package/plan/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: plan
+workflow: rpiv
+workflowPhase: plan
 description: Create or revise vertical implementation slices in the active WORK.md. Use after /grill-with-docs to produce a concise, reviewable plan for implementation.
 ---
 
@@ -8,7 +10,7 @@ description: Create or revise vertical implementation slices in the active WORK.
 Map the "how" into tracer-bullet vertical slices.
 
 ## Guardrails
-- READ: `.workflow/active_task.json` then active `WORK.md` `[BRIEF]` and `[GRILL]`.
+- READ: `.workflow/active.json` / `.workflow/active_task.json` then active `WORK.md` `[BRIEF]` and `[GRILL]`.
 - WRITE: `WORK.md` -> `[PLAN]` and append to `[LOG]` only.
 - NEVER: implement code during planning.
 - NEVER: create standalone `PLAN.md`.

package/scripts/triage_helper.sh

@@ -120,13 +120,13 @@ PY
 
 write_active_pointer() {
     mkdir -p ".workflow"
-    python3 - ".workflow/active_task.json" "$TASK_FOLDER" "$SOURCE" "$ID" "$TASK_DIR" "$BRANCH_NAME" <<'PY'
+    python3 - ".workflow/active_task.json" ".workflow/active.json" "$TASK_FOLDER" "$SOURCE" "$ID" "$TASK_DIR" "$WORK_MD" "$BRANCH_NAME" "$ISO_NOW" <<'PY'
 import json
 import sys
 from pathlib import Path
 
-path, active_task, source, raw_id, task_path, branch = sys.argv[1:]
-data = {
+active_task_path, active_workflow_path, active_task, source, raw_id, task_path, state_file, branch, now = sys.argv[1:]
+legacy_data = {
     "active_task": active_task,
     "source": source,
     "id": raw_id,
@@ -135,7 +135,22 @@ data = {
     "path": task_path,
     "branch": branch,
 }
-Path(path).write_text(json.dumps(data, indent=2) + "\n")
+workflow_data = {
+    "workflow": "rpiv",
+    "id": active_task,
+    "taskId": active_task,
+    "source": source,
+    "sourceId": raw_id,
+    "stateFile": state_file,
+    "taskPath": task_path,
+    "path": task_path,
+    "branch": branch,
+    "startedAt": now,
+    "updatedAt": now,
+    "compatPointer": ".workflow/active_task.json",
+}
+Path(active_task_path).write_text(json.dumps(legacy_data, indent=2) + "\n")
+Path(active_workflow_path).write_text(json.dumps(workflow_data, indent=2) + "\n")
 PY
 }
 

package/sync/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: sync
+workflow: rpiv
+workflowPhase: sync
 description: Synchronizes local RPIV task state (WORK.md) to external trackers (Jira, GitHub, GitLab). Use this to publish progress, update implementation status, and maintain a durable audit trail between local development and remote project management tools.
 ---
 
@@ -8,7 +10,7 @@ description: Synchronizes local RPIV task state (WORK.md) to external trackers (
 Maintains consistency between local `.workflow` state and the remote source of truth using a single Pi-owned living status comment per task.
 
 ## Guardrails
-- **Pre-flight**: Always read `.workflow/active_task.json` and the active `WORK.md` before executing.
+- **Pre-flight**: Always read `.workflow/active.json` / `.workflow/active_task.json` and the active `WORK.md` before executing.
 - **Privacy**: NEVER sync secrets, environment variables, or private notes not intended for stakeholders.
 - **Integrity**: Do not modify `[BRIEF]` or `[GRILL]` sections.
 - **Idempotency**: If the remote Pi status already reflects the current local state, do not post or update.
@@ -44,7 +46,7 @@ Do **not** use latest-comment ownership as the primary decision. Latest-comment-
 ## Workflow
 
 ### 1. Discovery & State Loading
-- Identify the platform and ID from `.workflow/active_task.json`.
+- Identify the platform and ID from `.workflow/active.json` or compatibility `.workflow/active_task.json`.
 - Extract **Slices** from `[PLAN]`, **Status** from `[LOG]`, and **Artifacts** such as PR/MR links, commit hashes, and verification output.
 
 ### 2. Payload Preparation

package/triage/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: triage
+workflow: rpiv
+workflowPhase: triage
 description: "Ingest or resume a tracked/local task in the RPIV workspace. Use when starting or returning to jira:, github:, gitlab:, or local: work and you need canonical WORK.md state without duplicating the scaffold."
 ---
 
@@ -8,10 +10,10 @@ description: "Ingest or resume a tracked/local task in the RPIV workspace. Use w
 Start RPIV by creating, resuming, or explicitly reopening a task workspace.
 
 ## Guardrails
-- READ: user argument, `.workflow/active_task.json` if present, target `metadata.json`, and target `WORK.md` if resuming.
-- WRITE: `.workflow/tasks/[source-id]/WORK.md`, `.workflow/tasks/[source-id]/metadata.json`, `.workflow/active_task.json`; optional `.reposcry/` cache files only if RepoScry is installed.
+- READ: user argument, `.workflow/active.json` / `.workflow/active_task.json` if present, target `metadata.json`, and target `WORK.md` if resuming.
+- WRITE: `.workflow/tasks/[source-id]/WORK.md`, `.workflow/tasks/[source-id]/metadata.json`, `.workflow/active.json`, `.workflow/active_task.json`; optional `.reposcry/` cache files only if RepoScry is installed.
 - On **create**, initialize required guarded sections only if absent: `[BRIEF]`, `[GRILL]`, `[PLAN]`, `[LOG]`, `[META]`.
-- On **resume**, only update `.workflow/active_task.json`, metadata timestamps/state as needed, and `[META]`, then append one concise `[LOG]` entry.
+- On **resume**, only update `.workflow/active.json`, `.workflow/active_task.json`, metadata timestamps/state as needed, and `[META]`, then append one concise `[LOG]` entry.
 - NEVER: duplicate guarded sections.
 - NEVER: overwrite existing `[BRIEF]`, `[GRILL]`, or `[PLAN]` during triage.
 - NEVER: create `PROBLEM.md`, `PRD.md`, `PLAN.md`, or `EVIDENCE.md`.

package/verify/SKILL.md

@@ -1,5 +1,7 @@
 ---
 name: verify
+workflow: rpiv
+workflowPhase: verify
 description: Verify the active slice or task against WORK.md, quality gates, and review readiness. Use after implementation or manual changes to decide whether work is ready for sync, review, or post-merge-prune.
 ---
 
@@ -8,7 +10,7 @@ description: Verify the active slice or task against WORK.md, quality gates, and
 The final gate for a slice or task. Verify truth before reporting progress.
 
 ## Guardrails
-- READ: `.workflow/active_task.json`, active `WORK.md` `[BRIEF]`, `[PLAN]`, and `[LOG]`.
+- READ: `.workflow/active.json` / `.workflow/active_task.json`, active `WORK.md` `[BRIEF]`, `[PLAN]`, and `[LOG]`.
 - WRITE: `WORK.md` -> `[PLAN]` checkboxes and append to `[LOG]` only.
 - NEVER: add `Signed-off-by`; tell the human to sign if needed.
 - NEVER: transition tracker state if verification fails.

package/post-merge-prune/SKILL.md

@@ -1,55 +0,0 @@
----
-name: post-merge-prune
-description: "Post-merge branch cleanup only. Use after a PR/MR is merged and the local feature branch is stale: prune remote refs and delete local branches already merged into the target branch."
----
-
-# Skill: post-merge-prune
-
-> [!IMPORTANT]
-> **LLM INSTRUCTION**: This skill is a deliberate post-merge deletion tool. If the user invokes `post-merge-prune`, they want stale local branches removed after merge into the intended target branch. Do not offer a menu of options. Do not ask "Dry run or Execute?". Proceed directly.
-
-Use this skill after a PR/MR has been merged into its intended branch, typically `main`, to remove stale remote-tracking refs and delete the matching local branches because the work is done.
-
-## Goal
-- Switch to the intended target branch (`main` by default).
-- Prune deleted remote branches.
-- Delete local branches that are already merged into the target branch.
-- Optionally remove matching workflow task folders.
-
-## Workflow
-
-### Step 1: Go to the target branch
-- `git checkout main` (or the intended merge target)
-- If the tree is dirty, stash first.
-
-### Step 2: Prune remote-tracking refs
-- `git remote update origin --prune`
-- This removes local refs for remote branches that were deleted after merge.
-
-### Step 3: Delete merged local branches
-Iterate through local branches and delete the ones already merged into the target branch:
-- Use `git branch -d <branch>` for normal merges.
-- If `-d` refuses but `git log main..[branch]` is empty, the branch was squash-merged; use `git branch -D <branch>`.
-- Never delete the active target branch.
-
-### Step 4: Optional workflow cleanup
-If a deleted branch has a matching `.workflow/tasks/*` folder, remove it.
-If `.workflow/active_task.json` points to a deleted task, clear it.
-
-### Step 5: Verify
-- `git branch -a` should no longer show deleted refs.
-- `git branch --merged main` should only show branches you intend to keep.
-- `.workflow/tasks/` should not contain deleted tasks.
-
-## Guardrails
-- **RESOLUTION OVER REPORTING**: If merge status is unclear, check `git branch --merged main` or `git log main..branch` and resolve it.
-- **NO DRY RUNS BY DEFAULT**: Execute the cleanup unless the user explicitly asks for a preview.
-- **SMART DELETE**: If a branch is squash-merged, delete it with `git branch -D` after confirming there are no unique commits left.
-- **ACTIVE BRANCH PROTECTION**: Do not delete the current branch.
-- **UNMERGED WORK**: If a branch has unique commits and no remote, ask once before force-deleting.
-
-## Output Contract
-Return a concise report:
-- **Cleaned**: deleted branches / task folders
-- **Kept**: branches still in use
-- **Working Branch**: the branch left checked out (should be `main`)