@openrig/cli 0.2.0 → 0.3.0

package/daemon/docs/reference/agent-spec.md

@@ -46,7 +46,7 @@ imports:
 profiles:
   default:
     uses:
-      skills: [using-superpowers, openrig-user, development-team, test-driven-development, mental-model-ha]
+      skills: [using-superpowers, openrig-user, development-team, test-driven-development, systematic-debugging]
       guidance: []
       subagents: []
       hooks: []
@@ -91,7 +91,7 @@ profiles:
     preferences:
       runtime: claude-code
     uses:
-      skills: [openrig-user, mental-model-ha, vault-user]
+      skills: [openrig-user, systematic-debugging, vault-user]
       guidance: []
       subagents: []
       hooks: []
@@ -216,7 +216,7 @@ imports:
   - ref: local:../../shared
 ```
 
-This gives access to the full pool of shared skills (openrig-user, mental-model-ha, development-team, etc.) and agents select the ones they need via profile `uses`.
+This gives access to the full pool of shared skills (openrig-user, systematic-debugging, development-team, etc.) and agents select the ones they need via profile `uses`.
 
 ---
 
@@ -230,7 +230,7 @@ profiles:
       runtime: claude-code
       model: claude-opus-4-6
     uses:
-      skills: [openrig-user, mental-model-ha, vault-user]
+      skills: [openrig-user, systematic-debugging, vault-user]
       guidance: [role]
       subagents: []
       hooks: []
@@ -258,7 +258,7 @@ The `uses` block selects which resources from the `resources` pool (including im
 
 ```yaml
 uses:
-  skills: [openrig-user, mental-model-ha, vault-user]
+  skills: [openrig-user, systematic-debugging, vault-user]
   guidance: [role]
   subagents: []
   hooks: [pre-commit]
@@ -410,9 +410,9 @@ The only required file is `agent.yaml`. Everything else is referenced by paths i
 | Agent | Location | Imports | Profile Skills | Purpose |
 |-------|----------|---------|---------------|---------|
 | `shared` | `specs/agents/shared/` | none | — (resource pool only) | Shared skill pool for all built-in agents |
-| `implementer` | `specs/agents/development/implementer/` | `shared` | openrig-user, development-team, test-driven-development, mental-model-ha, etc. | TDD implementation agent |
+| `implementer` | `specs/agents/development/implementer/` | `shared` | openrig-user, development-team, test-driven-development, systematic-debugging, etc. | TDD implementation agent |
 | `qa` | `specs/agents/development/qa/` | `shared` | openrig-user, development-team, etc. | Quality assurance agent |
 | `orchestrator` | `specs/agents/orchestration/orchestrator/` | `shared` | openrig-user, orchestration-team, etc. | Rig orchestration lead |
 | `reviewer` | `specs/agents/review/reviewer/` | `shared` | openrig-user, review-team, etc. | Independent code reviewer |
-| `vault-specialist` | `specs/agents/apps/vault-specialist/` | `shared` | openrig-user, mental-model-ha, vault-user | Vault domain specialist |
+| `vault-specialist` | `specs/agents/apps/vault-specialist/` | `shared` | openrig-user, systematic-debugging, vault-user | Vault domain specialist |
 | `design` | `specs/agents/design/` | none | — | Product designer |

package/daemon/docs/reference/agent-startup-guide.md

@@ -61,7 +61,7 @@ Skills are delivered to agents through two parallel paths:
 
 Both paths are important. The spec projection ensures the files are physically present. The startup instruction ensures the agent knows to read them. This redundancy is intentional — it handles cases where one path fails.
 
-Example: An implementer agent's startup guidance says "Load the following skills: openrig-user, test-driven-development, mental-model-ha" — AND the agent spec's profile uses those same skill IDs. The agent gets the files from projection and the instruction to read them from guidance.
+Example: An implementer agent's startup guidance says "Load the following skills: openrig-user, test-driven-development, systematic-debugging" — AND the agent spec's profile uses those same skill IDs. The agent gets the files from projection and the instruction to read them from guidance.
 
 ### The File Types
 
@@ -301,7 +301,7 @@ Don't put project documentation inside the role guidance. The role is about the
 
 In a startup file or guidance, include a line like:
 ```
-You have the following skills loaded: openrig-user, test-driven-development, mental-model-ha. Use them.
+You have the following skills loaded: openrig-user, test-driven-development, systematic-debugging. Use them.
 ```
 This prompts the agent to actually invoke the skills, not just have them as passive context.
 

package/daemon/docs/reference/project-workspace.md

@@ -0,0 +1,102 @@
+# Project Workspace Contract
+
+OpenRig's Project UI is a file-backed view over a workspace root. The folder
+shape is intentionally simple so humans and agents can create or repair it
+without daemon-internal knowledge.
+
+## Default Shape
+
+`rig config init-workspace` creates the default workspace at
+`~/.openrig/workspace` unless `--root` or `workspace.root` points elsewhere.
+
+```text
+workspace/
+  README.md
+  STEERING.md
+  missions/
+    README.md
+    idea-ledger/
+      README.md
+      PROGRESS.md
+      slices/
+        capture-product-ideas/
+          README.md
+          PROGRESS.md
+          IMPLEMENTATION-PRD.md
+        triage-product-ideas/
+          README.md
+          PROGRESS.md
+          IMPLEMENTATION-PRD.md
+    handoff-loop/
+      README.md
+      PROGRESS.md
+      slices/
+        route-work-packets/
+          README.md
+          PROGRESS.md
+          IMPLEMENTATION-PRD.md
+        verify-loop-evidence/
+          README.md
+          PROGRESS.md
+          IMPLEMENTATION-PRD.md
+  progress/
+  field-notes/
+  specs/
+```
+
+## UI Mapping
+
+- `workspace.root` maps to the Project workspace.
+- `workspace.root/missions/<mission-id>` maps to a Project mission.
+- `workspace.root/missions/<mission-id>/slices/<slice-id>` maps to a Project slice.
+- Mission `PROGRESS.md` frontmatter supplies the mission status badge when the
+  file root is allowlisted.
+- Slice `README.md`, `PROGRESS.md`, and `IMPLEMENTATION-PRD.md` frontmatter
+  supply display name, lifecycle status, mission id, and queue linkage hints.
+
+Mission and slice ids should be stable kebab-case strings. Keep slice ids
+unique inside the workspace so `/project/slice/<slice-id>` resolves without
+ambiguity.
+
+## Queue Mapping
+
+Queue items attach to a slice when their body or tags mention one of:
+
+- the slice id;
+- the mission id;
+- the legacy `rail-item` value in slice frontmatter.
+
+For new work, include both mission and slice ids in the queue item body or
+tags. Example:
+
+```text
+Mission: idea-ledger
+Slice: capture-product-ideas
+```
+
+This makes Story, Queue, Tests, and Topology tabs line up with the filesystem
+slice without adding a separate project database schema.
+
+## Compatibility
+
+The default discovery root is `workspace.slices_root=<workspace.root>/missions`.
+The slice indexer also supports legacy flat roots such as
+`workspace.slices_root=<workspace.root>/slices`, where each direct child folder
+is a slice. Flat roots remain readable, but the mission-aware shape is the
+default setup contract.
+
+## Repair Checklist
+
+If Project shows a mission discovery warning:
+
+1. Run `rig config get workspace.root --show-source`.
+2. Run `rig config get workspace.slices_root --show-source`.
+3. Confirm `workspace.slices_root` points at a folder containing mission
+   directories with `slices/` children.
+4. Confirm `files.allowlist` includes `workspace:<workspace.root>` so the UI
+   can read mission `PROGRESS.md`.
+5. If the workspace is missing, run `rig config init-workspace` after operator
+   approval.
+
+No daemon restart is required for most config reads. Restart when changing
+startup-time roots such as `files.allowlist` or progress scan roots.

package/daemon/specs/agents/apps/vault-specialist/agent.yaml

@@ -11,7 +11,7 @@ imports:
 profiles:
   default:
     uses:
-      skills: [using-superpowers, openrig-user, mental-model-ha, systematic-debugging, verification-before-completion, vault-user]
+      skills: [using-superpowers, openrig-user, systematic-debugging, verification-before-completion, vault-user]
       guidance: []
       subagents: []
       hooks: []

package/daemon/specs/agents/apps/vault-specialist/guidance/role.md

@@ -28,7 +28,6 @@ You have the following skills loaded:
 
 - `using-superpowers` — general agent capabilities
 - `openrig-user` — OpenRig CLI and topology operations
-- `mental-model-ha` — compaction and restore discipline
 - `systematic-debugging` — structured debugging approach
 - `verification-before-completion` — evidence before claims
 - `vault-user` — Vault-specific operations and domain knowledge

package/daemon/specs/agents/conveyor/builder/agent.yaml

@@ -0,0 +1,35 @@
+name: conveyor-builder
+version: "1.0"
+description: Conveyor builder - executes the planned packet and prepares proof for review
+
+defaults:
+  runtime: claude-code
+
+imports:
+  - ref: local:../../shared
+
+profiles:
+  default:
+    uses:
+      skills: [openrig-user, development-team, test-driven-development, systematic-debugging, executing-plans, verification-before-completion]
+      guidance: []
+      subagents: []
+      hooks: []
+      runtime_resources: [shared:claude-default-settings, shared:claude-default-mcp, shared:codex-default-config]
+
+resources:
+  guidance:
+    - id: role
+      path: guidance/role.md
+    - id: startup-context
+      path: startup/context.md
+
+startup:
+  files:
+    - path: guidance/role.md
+      delivery_hint: send_text
+      required: true
+    - path: startup/context.md
+      delivery_hint: send_text
+      required: true
+  actions: []

package/daemon/specs/agents/conveyor/builder/guidance/role.md

@@ -0,0 +1,31 @@
+# Role: Conveyor Builder
+
+You are the build station for the `conveyor` starter rig. Your job is to
+execute the planner's packet, keep edits bounded, and produce proof that a
+reviewer can inspect.
+
+## Skills Loaded
+
+- `openrig-user`
+- `development-team`
+- `test-driven-development`
+- `systematic-debugging`
+- `executing-plans`
+- `verification-before-completion`
+
+## Responsibilities
+
+- Read the plan before editing or producing an artifact.
+- Keep implementation scope aligned to the packet.
+- Run the verification commands that fit the change.
+- Hand off to `review-reviewer@conveyor` with changed files, commands run, and
+  residual risks.
+- If review sends work back, address the specific finding and preserve the
+  evidence trail.
+
+## Principles
+
+- Do the smallest useful build step that satisfies the plan.
+- Tests and proof are part of the work product.
+- Do not claim success without reproducible verification.
+- Keep handoffs factual so the review station can move quickly.

package/daemon/specs/agents/conveyor/builder/startup/context.md

@@ -0,0 +1,9 @@
+# Startup Context
+
+Run `rig whoami --json` before making topology claims. Confirm that your
+session is `build-builder@conveyor`.
+
+Default workflow role: `builder`.
+
+Receive planned packets from `plan-planner@conveyor`. Send proof-ready work to
+`review-reviewer@conveyor`. Rework packets may also arrive from review.

package/daemon/specs/agents/conveyor/lead/agent.yaml

@@ -0,0 +1,35 @@
+name: conveyor-lead
+version: "1.0"
+description: Conveyor intake lead - receives work, keeps station handoffs clear, and closes packets
+
+defaults:
+  runtime: claude-code
+
+imports:
+  - ref: local:../../shared
+
+profiles:
+  default:
+    uses:
+      skills: [openrig-user, orchestration-team, backlog-capture, writing-plans, executing-plans, verification-before-completion, brainstorming]
+      guidance: []
+      subagents: []
+      hooks: []
+      runtime_resources: [shared:claude-default-settings, shared:claude-default-mcp, shared:codex-default-config]
+
+resources:
+  guidance:
+    - id: role
+      path: guidance/role.md
+    - id: startup-context
+      path: startup/context.md
+
+startup:
+  files:
+    - path: guidance/role.md
+      delivery_hint: send_text
+      required: true
+    - path: startup/context.md
+      delivery_hint: send_text
+      required: true
+  actions: []

package/daemon/specs/agents/conveyor/lead/guidance/role.md

@@ -0,0 +1,34 @@
+# Role: Conveyor Lead
+
+You are the intake and close seat for the `conveyor` starter rig. Your job is
+to receive new work packets, keep the station pipeline understandable, and
+close work with useful evidence when the review station says the packet is
+ready.
+
+## Skills Loaded
+
+- `openrig-user`
+- `orchestration-team`
+- `backlog-capture`
+- `writing-plans`
+- `executing-plans`
+- `verification-before-completion`
+- `brainstorming`
+
+## Responsibilities
+
+- Turn rough incoming requests into queue packets that a planner can act on.
+- Keep the active workflow instance honest: current owner, next owner, and
+  terminal state should always be visible through OpenRig surfaces.
+- Watch for backpressure. If planning, build, or review is backed up, stop
+  feeding new packets and help clear the queue.
+- Close completed packets only after the review station has supplied evidence.
+- Escalate unclear requirements instead of inventing hidden scope.
+
+## Principles
+
+- Handoffs are durable queue motion, not private chat.
+- The starter rig should teach a new user how OpenRig coordinates work.
+- Keep packets small enough that every station can finish its turn.
+- Prefer explicit closure notes over vague status updates.
+- Do not embed private release topology assumptions in this generic starter.

package/daemon/specs/agents/conveyor/lead/startup/context.md

@@ -0,0 +1,15 @@
+# Startup Context
+
+Run `rig whoami --json` before making topology claims. Confirm that your
+session is `intake-lead@conveyor`.
+
+Default workflow role: `intake` and `closer`.
+
+Primary partners:
+
+- Planning: `plan-planner@conveyor`
+- Build: `build-builder@conveyor`
+- Review: `review-reviewer@conveyor`
+
+Use `rig send` for transient coordination and queue/workflow commands for
+durable packet motion.

package/daemon/specs/agents/conveyor/planner/agent.yaml

@@ -0,0 +1,35 @@
+name: conveyor-planner
+version: "1.0"
+description: Conveyor planner - turns accepted packets into small executable plans
+
+defaults:
+  runtime: codex
+
+imports:
+  - ref: local:../../shared
+
+profiles:
+  default:
+    uses:
+      skills: [openrig-user, requirements-writer, context-builder, writing-plans, verification-before-completion]
+      guidance: []
+      subagents: []
+      hooks: []
+      runtime_resources: [shared:claude-default-settings, shared:claude-default-mcp, shared:codex-default-config]
+
+resources:
+  guidance:
+    - id: role
+      path: guidance/role.md
+    - id: startup-context
+      path: startup/context.md
+
+startup:
+  files:
+    - path: guidance/role.md
+      delivery_hint: send_text
+      required: true
+    - path: startup/context.md
+      delivery_hint: send_text
+      required: true
+  actions: []

package/daemon/specs/agents/conveyor/planner/guidance/role.md

@@ -0,0 +1,29 @@
+# Role: Conveyor Planner
+
+You are the planning station for the `conveyor` starter rig. Your job is to
+convert an accepted work packet into a bounded plan that the build station can
+execute without guessing.
+
+## Skills Loaded
+
+- `openrig-user`
+- `requirements-writer`
+- `context-builder`
+- `writing-plans`
+- `verification-before-completion`
+
+## Responsibilities
+
+- Read the packet, identify the concrete outcome, and name any missing input.
+- Produce a short plan with expected files, commands, and verification.
+- Keep the plan small enough for one build turn.
+- Hand off to `build-builder@conveyor` with the plan and any constraints the
+  builder must preserve.
+- Mark blockers honestly if the packet cannot be planned from available input.
+
+## Principles
+
+- A useful plan removes ambiguity; it does not expand scope.
+- The build station should know exactly what completion means.
+- Prefer one verifiable outcome over a broad work theme.
+- Keep workflow evidence readable for a new OpenRig user.

package/daemon/specs/agents/conveyor/planner/startup/context.md

@@ -0,0 +1,12 @@
+# Startup Context
+
+Run `rig whoami --json` before making topology claims. Confirm that your
+session is `plan-planner@conveyor`.
+
+Default workflow role: `planner`.
+
+Receive packets from `intake-lead@conveyor`. Send executable plans to
+`build-builder@conveyor`.
+
+Keep planning outputs concise: objective, assumptions, steps, verification, and
+handoff notes.

package/daemon/specs/agents/conveyor/reviewer/agent.yaml

@@ -0,0 +1,35 @@
+name: conveyor-reviewer
+version: "1.0"
+description: Conveyor reviewer - checks build output, asks for rework, or clears the packet for close
+
+defaults:
+  runtime: codex
+
+imports:
+  - ref: local:../../shared
+
+profiles:
+  default:
+    uses:
+      skills: [openrig-user, review-team, plan-review, systematic-debugging, verification-before-completion]
+      guidance: []
+      subagents: []
+      hooks: []
+      runtime_resources: [shared:claude-default-settings, shared:claude-default-mcp, shared:codex-default-config]
+
+resources:
+  guidance:
+    - id: role
+      path: guidance/role.md
+    - id: startup-context
+      path: startup/context.md
+
+startup:
+  files:
+    - path: guidance/role.md
+      delivery_hint: send_text
+      required: true
+    - path: startup/context.md
+      delivery_hint: send_text
+      required: true
+  actions: []

package/daemon/specs/agents/conveyor/reviewer/guidance/role.md

@@ -0,0 +1,29 @@
+# Role: Conveyor Reviewer
+
+You are the review station for the `conveyor` starter rig. Your job is to check
+the builder's output against the plan, surface concrete findings, and either
+send targeted rework back to build or clear the packet for close.
+
+## Skills Loaded
+
+- `openrig-user`
+- `review-team`
+- `plan-review`
+- `systematic-debugging`
+- `verification-before-completion`
+
+## Responsibilities
+
+- Review the plan, the claimed output, and the verification evidence.
+- Lead with blocking findings when behavior is wrong or proof is missing.
+- Keep non-blocking polish separate from correctness.
+- Send rework to `build-builder@conveyor` only when there is a concrete fix.
+- When the packet is ready, hand it to `intake-lead@conveyor` for close with a
+  compact evidence summary.
+
+## Principles
+
+- Review protects the user from false proof.
+- A finding needs a repro, file reference, command result, or observed behavior.
+- Do not nitpick style unless it changes correctness, safety, or maintainability.
+- The goal is clear motion: rework if needed, close when proven.

package/daemon/specs/agents/conveyor/reviewer/startup/context.md

@@ -0,0 +1,10 @@
+# Startup Context
+
+Run `rig whoami --json` before making topology claims. Confirm that your
+session is `review-reviewer@conveyor`.
+
+Default workflow role: `reviewer`.
+
+Receive proof-ready packets from `build-builder@conveyor`. Send targeted rework
+back to build when needed. Send clean packets to `intake-lead@conveyor` for
+closure.

package/daemon/specs/agents/development/implementer/agent.yaml

@@ -11,7 +11,7 @@ imports:
 profiles:
   default:
     uses:
-      skills: [using-superpowers, openrig-user, development-team, test-driven-development, mental-model-ha, systematic-debugging, verification-before-completion, writing-plans, executing-plans]
+      skills: [using-superpowers, openrig-user, development-team, test-driven-development, systematic-debugging, verification-before-completion, writing-plans, executing-plans]
       guidance: []
       subagents: []
       hooks: []

package/daemon/specs/agents/development/implementer/guidance/role.md

@@ -9,7 +9,6 @@ Load these packaged skills now before editing:
 - `openrig-user`
 - `development-team`
 - `test-driven-development`
-- `mental-model-ha`
 - `systematic-debugging`
 - `writing-plans`
 - `executing-plans`

package/daemon/specs/agents/orchestration/orchestrator/agent.yaml

@@ -11,7 +11,7 @@ imports:
 profiles:
   default:
     uses:
-      skills: [using-superpowers, openrig-user, orchestration-team, mental-model-ha, systematic-debugging, verification-before-completion, writing-plans, executing-plans, brainstorming]
+      skills: [using-superpowers, openrig-user, orchestration-team, systematic-debugging, verification-before-completion, writing-plans, executing-plans, brainstorming]
       guidance: []
       subagents: []
       hooks: []

package/daemon/specs/agents/orchestration/orchestrator/guidance/role.md

@@ -8,7 +8,6 @@ Load these packaged skills now before doing substantive work:
 - `using-superpowers`
 - `openrig-user`
 - `orchestration-team`
-- `mental-model-ha`
 - `systematic-debugging`
 - `brainstorming`
 - `writing-plans`
@@ -39,8 +38,8 @@ Then run:
 
 ## Communication
 
-- Send messages to agents via tmux or rigged send
-- Read agent output via rigged capture
+- Send messages to agents via tmux or `rig send`
+- Read agent output via `rig capture`
 - Use the chatroom for broadcast announcements
 - Keep the human informed of progress at natural milestones
 

package/daemon/specs/agents/shared/agent.yaml

@@ -24,8 +24,6 @@ resources:
       path: skills/core/openrig-operator
     - id: claude-compact-in-place
       path: skills/claude-compact-in-place
-    - id: mental-model-ha
-      path: skills/mental-model-ha
     - id: systematic-debugging
       path: skills/process/systematic-debugging
     - id: test-driven-development

package/daemon/specs/agents/shared/skills/core/openrig-user/SKILL.md

@@ -8,6 +8,31 @@ description: Use when operating OpenRig with the `rig` CLI and you need the ship
 This is an as-built guide to the shipped `rig` CLI.
 Use current code and `rig ... --help` as ground truth if anything here ever conflicts with older planning docs.
 
+This is not the config-layer or builder guide. Use the substrate control-plane guidance for `rigx`
+and experimental overlays. Use the OpenRig builder guidance when changing OpenRig behavior,
+doctrine, or release posture.
+
+## Runtime-Gated Coordination Primitives
+
+OpenRig v0.2.0 includes the bundled PL-004 Coordination Primitive System: Phase A `rig stream` /
+`rig queue`, Phase B `rig project` / `rig view`, Phase C `rig watchdog`, and Phase D `rig workflow`
+/ `workflow-keepalive`.
+
+Do not confuse package/source truth with active daemon truth. These commands are shipped product
+surfaces in v0.2.0+, but they need a v0.2.0+ daemon and matching SQLite schema at runtime.
+
+Default posture:
+
+- Treat daemon `rig queue`, `rig stream`, `rig project`, `rig view`, `rig watchdog`, and
+  `rig workflow` as the product coordination surfaces when the active daemon is v0.2.0 or newer.
+- Use temporary substrate overlays such as `rigx queue`, `rigx stream`, `rigx project`, and
+  `rigx view-proto` only where the current OpenRig workstream explicitly says that legacy/control
+  layer is still in use.
+- If a daemon-backed coordination command fails, debug the command/runtime/schema edge directly;
+  do not assume the right workaround is to drop back to a config-layer primitive.
+- Do not perform daemon stop/start, production DB copy/mutation, release, publish, or other
+  consequence-boundary actions unless the operator/workstream has granted that specific gate.
+
 ## Core Loop
 
 Most work in OpenRig reduces to this loop: