@jiggai/recipes 0.4.17 → 0.4.18

package/docs/releasing.md

@@ -1,42 +1,135 @@
 # Releasing `@jiggai/recipes`
 
-This repo is published to npm as `@jiggai/recipes`.
+This repo publishes to npm as:
 
-## Prereqs (one-time)
+```text
+@jiggai/recipes
+```
 
-1) In GitHub repo settings, add an Actions secret:
+This is the practical release guide.
 
-- Name: `NPM_TOKEN`
-- Value: an npm access token with publish rights for the `@jiggai` scope
+---
 
-2) Ensure `package.json` has the correct name/version and `publishConfig.access = "public"`.
+## Before you release
 
-## Release flow (recommended)
+Make sure these are true:
+- `package.json` version is correct
+- `openclaw.plugin.json` version matches
+- tests pass
+- the branch/PR you intend to release is actually the one merged to `main`
 
-1) Update `package.json` version on `main` and commit it.
+Useful checks:
 
-Typical:
+```bash
+npm test
+npm view @jiggai/recipes version
+node -p "require('./package.json').version"
+cat openclaw.plugin.json
+```
 
-- `npm version patch` (or `minor` / `major`)
+---
 
-This creates a commit and a git tag (by default `vX.Y.Z`).
+## Recommended release flow
 
-2) Push the commit + tag:
+From `main`:
 
-- `git push origin main --follow-tags`
+```bash
+git checkout main
+git pull --ff-only
+npm version patch
+```
 
-3) GitHub Actions will run the `Publish` workflow on tag push and publish to npm.
+Or use `minor` / `major` when appropriate:
 
-## Manual publish (local machine)
+```bash
+npm version minor
+npm version major
+```
 
-If you have npm auth configured locally (i.e. `npm whoami` works), you can publish directly:
+Then push commit + tag:
 
-- `npm ci`
-- `npm run lint`
-- `npm test`
-- `npm publish`
+```bash
+git push origin main --follow-tags
+```
 
-## Verify
+GitHub Actions will run the normal publish workflow.
 
-- `npm view @jiggai/recipes version`
-- In a clean OpenClaw install, upgrade the extension and confirm the expected behavior is present.
+---
+
+## Manual local publish
+
+If you are intentionally publishing from your local machine:
+
+```bash
+npm ci
+npm run lint
+npm test
+npm publish
+```
+
+You will need local npm auth:
+
+```bash
+npm whoami
+```
+
+---
+
+## Verify after publishing
+
+Check the published version:
+
+```bash
+npm view @jiggai/recipes version
+```
+
+Then test a fresh install or upgrade path:
+
+```bash
+openclaw plugins install @jiggai/recipes
+openclaw gateway restart
+openclaw recipes list
+```
+
+---
+
+## Important note about local patches
+
+If you maintain a local controller-specific patch (for example, workflow posting behavior), publishing a clean package does **not** mean that patch is part of the public release unless you intentionally merged it.
+
+So after publishing, you may need to:
+- reapply your local patch
+- relink/reinstall the plugin
+- tell your assistant to turn the local posting path back on
+
+If you use a patch file or gist for that workflow, keep it handy as part of your release checklist.
+
+---
+
+## About canary publishes
+
+If canary publishing is paused in the repo workflow config, PR activity will not automatically publish canary builds.
+
+That is separate from the normal release workflow.
+
+---
+
+## Minimum safe release checklist
+
+```bash
+# sync to main
+git checkout main
+git pull --ff-only
+
+# run checks
+npm test
+
+# bump version
+npm version patch
+
+# push
+git push origin main --follow-tags
+
+# verify published version
+npm view @jiggai/recipes version
+```

package/openclaw.plugin.json

@@ -2,7 +2,7 @@
   "id": "recipes",
   "name": "Recipes",
   "description": "Markdown recipes that scaffold agents and teams (workspace-local).",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "configSchema": {
     "type": "object",
     "additionalProperties": false,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jiggai/recipes",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "description": "ClawRecipes plugin for OpenClaw (markdown recipes -> scaffold agents/teams)",
   "main": "index.ts",
   "type": "commonjs",

package/recipes/default/clinic-team.md

@@ -1,521 +0,0 @@
----
-id: clinic-team
-name: Clinic Team
-version: 0.1.0
-description: A small clinic operations team (intake, scheduling, billing, compliance, patient education) coordinated via a shared workspace.
-kind: team
-cronJobs:
-  - id: lead-triage-loop
-    name: "Lead triage loop"
-    schedule: "*/30 7-23 * * 1-5"
-    timezone: "America/New_York"
-    message: "Automated lead triage loop (Clinic Team): triage inbox/tickets, assign work, and update notes/status.md."
-    enabledByDefault: false
-  - id: execution-loop
-    name: "Execution loop"
-    schedule: "*/30 7-23 * * 1-5"
-    timezone: "America/New_York"
-    message: "Automated execution loop (Clinic Team): make progress on in-progress tickets and update notes/status.md."
-    enabledByDefault: false
-requiredSkills: []
-team:
-  teamId: clinic-team
-agents:
-  - role: lead
-    name: Clinic Administrator / Lead
-    tools:
-      profile: "coding"
-      allow: ["group:fs", "group:web", "group:runtime"]
-      deny: ["exec"]
-  - role: intake
-    name: Patient Intake / Front Desk
-    tools:
-      profile: "coding"
-      allow: ["group:fs", "group:web"]
-      deny: ["exec"]
-  - role: scheduler
-    name: Scheduling Coordinator
-    tools:
-      profile: "coding"
-      allow: ["group:fs", "group:web"]
-      deny: ["exec"]
-  - role: billing
-    name: Billing & Insurance
-    tools:
-      profile: "coding"
-      allow: ["group:fs", "group:web"]
-      deny: ["exec"]
-  - role: compliance
-    name: Compliance / Privacy
-    tools:
-      profile: "coding"
-      allow: ["group:fs", "group:web"]
-      deny: ["exec"]
-  - role: educator
-    name: Patient Education Writer
-    tools:
-      profile: "coding"
-      allow: ["group:fs", "group:web"]
-      deny: ["exec"]
-
-templates:
-  sharedContext.memoryPolicy: |
-    # Team Memory Policy (File-first)
-
-    Quick link: see `shared-context/MEMORY_PLAN.md` for the canonical “what goes where” map.
-
-    This team is run **file-first**. Chat is not the system of record.
-
-    ## Where to write things
-    - Ticket = source of truth for a unit of work.
-    - `notes/plan.md` + `shared-context/priorities.md` are **lead-curated**.
-    - `notes/status.md` is **append-only** and updated after each work session (3–5 bullets).
-    - `shared-context/agent-outputs/` is **append-only** logs/output.
-
-    ## End-of-session checklist (everyone)
-    After meaningful work:
-    1) Update the ticket with what changed + how to verify + rollback.
-    2) Add a dated note in the ticket `## Comments`.
-    3) Append 3–5 bullets to `notes/status.md`.
-    4) Append logs/output to `shared-context/agent-outputs/`.
-
-  sharedContext.plan: |
-    # Plan (lead-curated)
-
-    - (empty)
-
-  sharedContext.status: |
-    # Status (append-only)
-
-    - (empty)
-
-  sharedContext.memoryPlan: |
-    # Memory Plan (Team)
-
-    This team is file-first. Chat is not the system of record.
-
-    ## Source of truth
-    - Tickets (`work/*/*.md`) are the source of truth for a unit of work.
-
-    ## Team knowledge memory (Kitchen UI)
-    - `shared-context/memory/team.jsonl` (append-only)
-    - `shared-context/memory/pinned.jsonl` (append-only, curated/high-signal)
-
-    Policy:
-    - Lead may pin to `pinned.jsonl`.
-    - Non-leads propose memory items via ticket comments or role outputs; lead pins.
-
-    ## Per-role continuity memory (agent startup)
-    - `roles/<role>/MEMORY.md` (curated long-term)
-    - `roles/<role>/memory/YYYY-MM-DD.md` (daily log)
-
-    ## Plan vs status (team coordination)
-    - `notes/plan.md` + `shared-context/priorities.md` are lead-curated
-    - `notes/status.md` is append-only roll-up (everyone appends)
-
-    ## Outputs / artifacts
-    - `roles/<role>/agent-outputs/` (append-only)
-    - `shared-context/agent-outputs/` (optional team-level)
-
-    ## Role work loop contract (safe-idle)
-    - No-op unless explicit queued work exists for the role.
-    - If work happens, write back in order: ticket → `notes/status.md` → `roles/<role>/agent-outputs/`.
-
-  sharedContext.priorities: |
-    # Priorities (lead-curated)
-
-    - (empty)
-
-  sharedContext.agentOutputsReadme: |
-    # Agent Outputs (append-only)
-
-    Put raw logs, command output, and investigation notes here.
-    Prefer filenames like: `YYYY-MM-DD-topic.md`.
-
-  lead.tools: |
-    # TOOLS.md
-
-    # Agent-local notes (paths, conventions, env quirks).
-
-  tools: |
-    # TOOLS.md
-
-    # Agent-local notes (paths, conventions, env quirks).
-
-  status: |
-    # STATUS.md
-
-    - (empty)
-
-  notes: |
-    # NOTES.md
-
-    - (empty)
-
-  lead.soul: |
-    # SOUL.md
-
-    You are the Team Lead / Dispatcher for {{teamId}}.
-
-    Core job:
-    - Convert new requests into scoped tickets.
-    - Assign work to Dev or DevOps.
-    - Monitor progress and unblock.
-    - Report completions.
-  lead.agents: |
-    # AGENTS.md
-
-    Team: {{teamId}}
-    Shared workspace: {{teamDir}}
-
-    ## Guardrails (read → act → write)
-
-    Before you act:
-    1) Read:
-       - `notes/plan.md`
-       - `notes/status.md`
-       - `shared-context/priorities.md`
-       - the relevant ticket(s)
-
-    After you act:
-    1) Write back:
-       - Update tickets with decisions/assignments.
-       - Keep `notes/status.md` current (3–5 bullets per active ticket).
-
-    ## Curator model
-
-    You are the curator of:
-    - `notes/plan.md`
-    - `shared-context/priorities.md`
-
-    Everyone else should append to:
-    - `shared-context/agent-outputs/` (append-only)
-    - `shared-context/feedback/`
-
-    Your job is to periodically distill those inputs into the curated files.
-
-    ## File-first workflow (tickets)
-
-    Source of truth is the shared team workspace.
-
-    Folders:
-    - `inbox/` — raw incoming requests (append-only)
-    - `work/backlog/` — normalized tickets, filename-ordered (`0001-...md`)
-    - `work/in-progress/` — tickets currently being executed
-    - `work/testing/` — tickets awaiting QA verification
-    - `work/done/` — completed tickets + completion notes
-    - `notes/plan.md` — current plan / priorities (curated)
-    - `notes/status.md` — current status snapshot
-    - `shared-context/` — shared context + append-only outputs
-
-    ### Ticket numbering (critical)
-    - Backlog tickets MUST be named `0001-...md`, `0002-...md`, etc.
-    - The developer pulls the lowest-numbered ticket assigned to them.
-
-    ### Ticket format
-    See `TICKETS.md` in the team root. Every ticket should include:
-    - Context
-    - Requirements
-    - Acceptance criteria
-    - Owner (dev/devops)
-    - Status
-
-    ### Your responsibilities
-    - For every new request in `inbox/`, create a normalized ticket in `work/backlog/`.
-    - Curate `notes/plan.md` and `shared-context/priorities.md`.
-    - Keep `notes/status.md` updated.
-    - When work is ready for QA, move the ticket to `work/testing/` and assign it to the tester.
-    - Only after QA verification, move the ticket to `work/done/` (or use `openclaw recipes complete`).
-    - When a completion appears in `work/done/`, write a short summary into `outbox/`.
-  intake.soul: |
-    # SOUL.md
-
-    You handle patient intake for {{teamId}}.
-
-    You produce clear summaries, required info checklists, and next-step instructions.
-
-  intake.agents: |
-    # AGENTS.md
-
-    Team: {teamId}
-    Shared workspace: {teamDir}
-    Role: intake
-
-    ## Guardrails (read → act → write)
-    Before you act:
-    1) Read:
-       - `notes/plan.md`
-       - `notes/status.md`
-       - relevant ticket(s) in `work/in-progress/`
-       - any relevant shared context under `shared-context/`
-
-    After you act:
-    1) Write back:
-       - Put outputs in the agreed folder (usually `outbox/` or a ticket file).
-       - Update the ticket with what you did and where the artifact is.
-
-    ## Workflow
-    - Prefer a pull model: wait for a clear task from the lead, or propose a scoped task.
-    - Keep work small and reversible.
-  scheduler.soul: |
-    # SOUL.md
-
-    You coordinate scheduling for {{teamId}}.
-
-    You reduce no-shows and keep schedules accurate.
-
-  scheduler.agents: |
-    # AGENTS.md
-
-    Team: {teamId}
-    Shared workspace: {teamDir}
-    Role: scheduler
-
-    ## Guardrails (read → act → write)
-    Before you act:
-    1) Read:
-       - `notes/plan.md`
-       - `notes/status.md`
-       - relevant ticket(s) in `work/in-progress/`
-       - any relevant shared context under `shared-context/`
-
-    After you act:
-    1) Write back:
-       - Put outputs in the agreed folder (usually `outbox/` or a ticket file).
-       - Update the ticket with what you did and where the artifact is.
-
-    ## Workflow
-    - Prefer a pull model: wait for a clear task from the lead, or propose a scoped task.
-    - Keep work small and reversible.
-  billing.soul: |
-    # SOUL.md
-
-    You manage billing and insurance workflows for {{teamId}}.
-
-    You produce step-by-step processes and clear patient-facing explanations.
-
-  billing.agents: |
-    # AGENTS.md
-
-    Team: {teamId}
-    Shared workspace: {teamDir}
-    Role: billing
-
-    ## Guardrails (read → act → write)
-    Before you act:
-    1) Read:
-       - `notes/plan.md`
-       - `notes/status.md`
-       - relevant ticket(s) in `work/in-progress/`
-       - any relevant shared context under `shared-context/`
-
-    After you act:
-    1) Write back:
-       - Put outputs in the agreed folder (usually `outbox/` or a ticket file).
-       - Update the ticket with what you did and where the artifact is.
-
-    ## Workflow
-    - Prefer a pull model: wait for a clear task from the lead, or propose a scoped task.
-    - Keep work small and reversible.
-  compliance.soul: |
-    # SOUL.md
-
-    You oversee compliance and privacy for {{teamId}}.
-
-    You flag risks and propose compliant alternatives.
-
-  compliance.agents: |
-    # AGENTS.md
-
-    Team: {teamId}
-    Shared workspace: {teamDir}
-    Role: compliance
-
-    ## Guardrails (read → act → write)
-    Before you act:
-    1) Read:
-       - `notes/plan.md`
-       - `notes/status.md`
-       - relevant ticket(s) in `work/in-progress/`
-       - any relevant shared context under `shared-context/`
-
-    After you act:
-    1) Write back:
-       - Put outputs in the agreed folder (usually `outbox/` or a ticket file).
-       - Update the ticket with what you did and where the artifact is.
-
-    ## Workflow
-    - Prefer a pull model: wait for a clear task from the lead, or propose a scoped task.
-    - Keep work small and reversible.
-  educator.soul: |
-    # SOUL.md
-
-    You write patient education materials for {{teamId}}.
-
-    You write at an accessible reading level and include practical next steps.
-
-  educator.agents: |
-    # AGENTS.md
-
-    Output:
-    - Handouts/FAQs → work/patient-education/
-    - After-visit summaries → work/patient-education/after-visit/
-
-
-  # Auto-added blanks to ensure every role can scaffold every declared file.
-
-  # --- role: lead ---
-  lead.status: |
-    # STATUS.md
-    
-    - (empty)
-
-  lead.notes: |
-    # NOTES.md
-    
-    - (empty)
-
-
-  # --- role: intake ---
-  intake.tools: |
-    # TOOLS.md
-    
-    - (empty)
-
-  intake.status: |
-    # STATUS.md
-    
-    - (empty)
-
-  intake.notes: |
-    # NOTES.md
-    
-    - (empty)
-
-
-  # --- role: scheduler ---
-  scheduler.tools: |
-    # TOOLS.md
-    
-    - (empty)
-
-  scheduler.status: |
-    # STATUS.md
-    
-    - (empty)
-
-  scheduler.notes: |
-    # NOTES.md
-    
-    - (empty)
-
-
-  # --- role: billing ---
-  billing.tools: |
-    # TOOLS.md
-    
-    - (empty)
-
-  billing.status: |
-    # STATUS.md
-    
-    - (empty)
-
-  billing.notes: |
-    # NOTES.md
-    
-    - (empty)
-
-
-  # --- role: compliance ---
-  compliance.tools: |
-    # TOOLS.md
-    
-    - (empty)
-
-  compliance.status: |
-    # STATUS.md
-    
-    - (empty)
-
-  compliance.notes: |
-    # NOTES.md
-    
-    - (empty)
-
-
-  # --- role: educator ---
-  educator.tools: |
-    # TOOLS.md
-    
-    - (empty)
-
-  educator.status: |
-    # STATUS.md
-    
-    - (empty)
-
-  educator.notes: |
-    # NOTES.md
-    
-    - (empty)
-
-
-files:
-  - path: SOUL.md
-    template: soul
-    mode: createOnly
-  - path: AGENTS.md
-    template: agents
-    mode: createOnly
-  - path: TOOLS.md
-    template: tools
-    mode: createOnly
-  - path: STATUS.md
-    template: status
-    mode: createOnly
-  - path: NOTES.md
-    template: notes
-    mode: createOnly
-
-  # Memory / continuity (team-level)
-  - path: notes/memory-policy.md
-    template: sharedContext.memoryPolicy
-    mode: createOnly
-  - path: notes/plan.md
-    template: sharedContext.plan
-    mode: createOnly
-  - path: notes/status.md
-    template: sharedContext.status
-    mode: createOnly
-  - path: shared-context/priorities.md
-    template: sharedContext.priorities
-    mode: createOnly
-  - path: shared-context/agent-outputs/README.md
-    template: sharedContext.agentOutputsReadme
-    mode: createOnly
-
-
-tools:
-  profile: "messaging"
-  allow: ["group:fs", "group:web"]
-  deny: ["exec"]
----
-
-# Clinic Team Recipe
-
-Bundled team recipe.
-
-## Files
-- Creates a shared team workspace under `~/.openclaw/workspace-<teamId>/` (example: `~/.openclaw/workspace-clinic-team-team/`).
-- Creates per-role directories under `roles/<role>/` for: `SOUL.md`, `AGENTS.md`, `TOOLS.md`, `STATUS.md`, `NOTES.md`.
-- Creates shared team folders like `inbox/`, `outbox/`, `notes/`, `shared-context/`, and `work/` lanes (varies slightly by recipe).
-
-## Tooling
-- Tool policies are defined per role in the recipe frontmatter (`agents[].tools`).
-- Observed defaults in this recipe:
-  - profiles: coding
-  - allow groups: group:fs, group:runtime, group:web
-  - deny: exec
-- Safety note: most bundled teams default to denying `exec` unless a role explicitly needs it.
-