opencode-onboard 0.3.3 → 0.4.1

package/content/.agents/session-log.json

@@ -0,0 +1,41 @@
+[
+  {
+    "ts": "2026-05-04T21:04:09.899Z",
+    "agent": "lead",
+    "member": null,
+    "agentType": null,
+    "team": null,
+    "action": "started",
+    "sessionId": "ses_20b31c36cffeBfsYI2hJ1BNcM5"
+  },
+  {
+    "ts": "2026-05-04T21:04:26.180Z",
+    "agent": "lead",
+    "member": null,
+    "agentType": null,
+    "team": null,
+    "action": "skill-loaded",
+    "skill": "ob-userstory-gh",
+    "source": "read-skill-file"
+  },
+  {
+    "ts": "2026-05-04T21:04:47.306Z",
+    "agent": "lead",
+    "member": null,
+    "agentType": null,
+    "team": null,
+    "action": "completed",
+    "filesEdited": 0,
+    "skills": [
+      "ob-userstory-gh"
+    ],
+    "usage": {
+      "inputTokensReported": null,
+      "outputTokensReported": null,
+      "totalTokensReported": null,
+      "tokenEstimateLow": 3469,
+      "tokenEstimateHigh": 6940,
+      "method": "heuristic"
+    }
+  }
+]

package/content/.agents/skills/ob-default/SKILL.md

@@ -0,0 +1,21 @@
+Fallback skill, used when no other skill matches. Still loads ob-global for baseline rules.
+
+## When used
+
+- No other skill matches the user's request
+- Task is unclear or ambiguous
+- Load ob-global first for baseline rules
+
+## Approach
+
+1. **Understand the ask**, Clarify if ambiguous
+2. **Check existing context**, Read DESIGN.md, ARCHITECTURE.md first
+3. **Start small**, MVP, iterate
+4. **Verify**, Run tests + build before claiming done
+5. **Report results**, Show what was done, what remains
+
+## Communication
+
+- Ask for clarification if unclear
+- Report blockers immediately
+- Show progress when asked

package/content/.agents/skills/ob-generic-guardrails/SKILL.md

@@ -0,0 +1,32 @@
+Generic guardrails, foundational rules that all agents follow. Users add specialized guardrails skills for specific concerns.
+
+## Git
+
+- NEVER commit or push to main
+- NEVER force push
+- NEVER merge PRs (human-only)
+- Feature branches only: `feature/*` or `bugfix/*`
+
+## Secrets
+
+- NEVER read or output .env files
+- NEVER log credentials, API keys, tokens
+- NEVER commit secrets to git
+
+## Code
+
+- Run tests before marking done
+- Run lint/build before pushing
+- Keep changes small and focused
+
+## Security
+
+- Validate all inputs
+- Escape all outputs
+- No hardcoded credentials
+
+## Communication
+
+- Ask for clarification if unclear
+- Report blockers immediately
+- Show progress when asked

package/content/.agents/skills/ob-global/SKILL.md

@@ -0,0 +1,49 @@
+Generic skill, common project-level guidance loaded by all agents. Provides baseline rules; specialized skills add specific concerns.
+
+## When loaded
+
+Load this skill first in any session. All other skills add to it, never replace it.
+
+## Context
+
+- Load DESIGN.md first for design principles and guidelines.
+- Load ARCHITECTURE.md for system architecture and component interactions.
+
+## Source Roots
+
+<!-- OB-SOURCE-ROOTS-START -->
+Source roots are generated during onboarding from the user's source-scope selection.
+Read and analyze code ONLY from those generated roots.
+
+If multiple roots are generated, each root is an independent git repository. Branch, commit, push, and PR operations must be handled per repository.
+<!-- OB-SOURCE-ROOTS-END -->
+
+## Git Guardrails
+
+- NEVER commit or push to main
+- NEVER force push
+- NEVER merge PRs (human-only)
+- Feature branches only: `feature/*` or `bugfix/*`
+
+## Secrets Guardrails
+
+- NEVER read or output .env files
+- NEVER log credentials, API keys, tokens
+- NEVER commit secrets to git
+
+## Code Quality
+
+- Run tests before marking done
+- Run lint/build before pushing
+- Keep changes small and focused
+- Ask for clarification if unclear
+
+## Token Optimization Rules
+
+<!-- OB-RTK-START -->
+RTK rules are generated here when RTK is selected during onboarding.
+<!-- OB-RTK-END -->
+
+<!-- OB-CAVEMAN-START -->
+Caveman rules are generated here when Caveman is selected during onboarding.
+<!-- OB-CAVEMAN-END -->

package/content/.agents/skills/ob-pullrequest-az/SKILL.md

@@ -8,16 +8,6 @@ metadata:
   version: "1.0"
 ---
 
-**RTK - MANDATORY**
-
-Use `rtk` wrapper for ALL CLI commands:
-- `rtk git add` NOT `git add`
-- `rtk git commit` NOT `git commit`
-- `rtk git push` NOT `git push`
-- `rtk az repos pr create` NOT `az repos pr create`
-- `rtk az repos pr work-item add` NOT `az repos pr work-item add`
-- `rtk az devops invoke` NOT `az devops invoke`
-
 **Browser MCP tools are FORBIDDEN for all Azure DevOps operations.**
 Browser tools are ONLY permitted for screenshots of the LOCAL running app on `localhost` URLs.
 
@@ -30,7 +20,7 @@ Triggered when devops-manager is in ship mode after implementation is complete.
 ### Step 1: Verify feature branch
 
 ```bash
-rtk git branch --show-current
+git branch --show-current
 ```
 
 Branch must be `feature/{id}-{slug}`. NEVER push to `main`.
@@ -48,15 +38,15 @@ Save to: `openspec/changes/{change-name}/images/{feature}.png`
 ### Step 3: Commit and push
 
 ```bash
-rtk git add .
-rtk git commit -m "feat(#{id}): {description}"
-rtk git push origin feature/{id}-{slug}
+git add .
+git commit -m "feat(#{id}): {description}"
+git push origin feature/{id}-{slug}
 ```
 
 ### Step 4: Create PR
 
 ```bash
-rtk az repos pr create \
+az repos pr create \
   --repository {repo} \
   --source-branch feature/{id}-{slug} \
   --target-branch main \
@@ -67,7 +57,7 @@ rtk az repos pr create \
 ### Step 5: Link work item (MANDATORY, run sequentially, not in parallel)
 
 ```bash
-rtk az repos pr work-item add --id {pr-id} --work-items {workitem-id}
+az repos pr work-item add --id {pr-id} --work-items {workitem-id}
 ```
 
 ### Step 6: Post screenshot comment
@@ -79,7 +69,7 @@ https://dev.azure.com/{org}/{project}/_apis/git/repositories/{repo}/items?path=o
 
 Post via:
 ```bash
-rtk az devops invoke \
+az devops invoke \
   --area git --resource pullRequestThreads \
   --route-parameters project={project} repositoryId={repo} pullRequestId={pr-id} \
   --http-method POST --api-version 7.1 --in-file body.json
@@ -107,13 +97,13 @@ Triggered when user says "I've added comments to the PR" or "check PR feedback".
 
 If PR link provided, extract ID from URL. Otherwise:
 ```bash
-rtk az repos pr list --repository {repo} --status active --top 1
+az repos pr list --repository {repo} --status active --top 1
 ```
 
 ### Step 2: Read comment threads
 
 ```bash
-rtk az devops invoke \
+az devops invoke \
   --area git --resource pullRequestThreads \
   --route-parameters project={project} repositoryId={repo} pullRequestId={id} \
   --http-method GET --api-version 7.1
@@ -131,7 +121,7 @@ rtk az devops invoke \
 ### Step 4: Update openspec (if spec-update)
 
 ```bash
-rtk git branch --show-current
+git branch --show-current
 # feature/193208-roles-crud → change: us-193208-roles-crud
 ```
 
@@ -140,7 +130,7 @@ Update: `openspec/changes/{change}/proposal.md`, `design.md`, or `tasks.md` as a
 ### Step 5: Reply to each thread
 
 ```bash
-rtk az devops invoke \
+az devops invoke \
   --area git --resource pullRequestThreadComments \
   --route-parameters project={project} repositoryId={repo} pullRequestId={id} threadId={tid} \
   --http-method POST --api-version 7.1 --in-file reply.json

package/content/.agents/skills/ob-pullrequest-gh/SKILL.md

@@ -8,16 +8,6 @@ metadata:
   version: "1.0"
 ---
 
-**RTK - MANDATORY**
-
-Use `rtk` wrapper for ALL CLI commands:
-- `rtk git add` NOT `git add`
-- `rtk git commit` NOT `git commit`
-- `rtk git push` NOT `git push`
-- `rtk gh pr create` NOT `gh pr create`
-- `rtk gh pr comment` NOT `gh pr comment`
-- `rtk gh api` NOT `gh api`
-
 **ALL GitHub data MUST come from `gh` CLI. NEVER use webfetch, HTTP requests, or browser MCP tools for GitHub operations, even if gh CLI fails. If `gh` is unavailable, report as a blocker.**
 Always pass `--repo {owner}/{repo}` explicitly, never rely on git context to resolve the repo.
 
@@ -30,7 +20,7 @@ Triggered when devops-manager is in ship mode after implementation is complete.
 ### Step 1: Verify feature branch
 
 ```bash
-rtk git branch --show-current
+git branch --show-current
 ```
 
 Branch must be `feature/{id}-{slug}`. NEVER push to `main`.
@@ -48,15 +38,15 @@ Save to: `openspec/changes/{change-name}/images/{feature}.png`
 ### Step 3: Commit and push
 
 ```bash
-rtk git add .
-rtk git commit -m "feat(#{id}): {description}"
-rtk git push origin feature/{slug}
+git add .
+git commit -m "feat(#{id}): {description}"
+git push origin feature/{slug}
 ```
 
 ### Step 4: Create PR
 
 ```bash
-rtk gh pr create \
+gh pr create \
   --base main \
   --head feature/{slug} \
   --title "feat: {title}" \
@@ -67,7 +57,7 @@ rtk gh pr create \
 
 Resolve commit SHA (the commit that includes screenshots):
 ```bash
-rtk git rev-parse HEAD
+git rev-parse HEAD
 ```
 
 Build blob URL for each image (preferred, stable in PR discussion):
@@ -77,7 +67,7 @@ https://github.com/{owner}/{repo}/blob/{sha}/openspec/changes/{change}/images/{f
 
 Post comment:
 ```bash
-rtk gh pr comment {pr-number} --repo {owner}/{repo} --body $'## Screenshots\n\n![{feature}]({blob-url})'
+gh pr comment {pr-number} --repo {owner}/{repo} --body $'## Screenshots\n\n![{feature}]({blob-url})'
 ```
 
 ---
@@ -90,16 +80,16 @@ Triggered when user says "I've added comments to the PR" or "check PR feedback".
 
 If PR link provided, extract number from URL. Otherwise:
 ```bash
-rtk gh pr list --repo {owner}/{repo} --state open --limit 1
+gh pr list --repo {owner}/{repo} --state open --limit 1
 ```
 
 ### Step 2: Read comment threads
 
 ```bash
-rtk gh pr view {pr-number} --repo {owner}/{repo} --comments
+gh pr view {pr-number} --repo {owner}/{repo} --comments
 # Or structured output:
-rtk gh api repos/{owner}/{repo}/pulls/{pr-number}/comments
-rtk gh api repos/{owner}/{repo}/pulls/{pr-number}/reviews
+gh api repos/{owner}/{repo}/pulls/{pr-number}/comments
+gh api repos/{owner}/{repo}/pulls/{pr-number}/reviews
 ```
 
 ### Step 3: Categorize feedback
@@ -114,7 +104,7 @@ rtk gh api repos/{owner}/{repo}/pulls/{pr-number}/reviews
 ### Step 4: Update openspec (if spec-update)
 
 ```bash
-rtk git branch --show-current
+git branch --show-current
 # feature/add-user-auth → change: add-user-auth
 ```
 
@@ -124,12 +114,12 @@ Update: `openspec/changes/{change}/proposal.md`, `design.md`, or `tasks.md` as a
 
 ```bash
 # Reply to a review comment
-rtk gh api repos/{owner}/{repo}/pulls/{pr-number}/comments/{comment-id}/replies \
+gh api repos/{owner}/{repo}/pulls/{pr-number}/comments/{comment-id}/replies \
   --method POST \
   --field body="Acknowledged, applying this change now."
 
 # Or post a general PR comment
-rtk gh pr comment {pr-number} --body "Updated design.md to reflect feedback."
+gh pr comment {pr-number} --body "Updated design.md to reflect feedback."
 ```
 
 ---

package/content/.agents/skills/ob-userstory-az/SKILL.md

@@ -8,12 +8,6 @@ metadata:
   version: "3.1"
 ---
 
-**RTK - MANDATORY**
-
-Use `rtk` wrapper for ALL CLI commands:
-- `rtk az boards work-item show` NOT `az boards work-item show`
-- `rtk openspec new change` NOT `openspec new change`
-
 **Browser MCP tools are FORBIDDEN for all Azure DevOps operations.**
 
 ---
@@ -40,7 +34,7 @@ Create with scopes: **Work Items (Read & Write)** + **Code (Read & Write)**
 
 2. **Fetch Work Item**
    ```bash
-   rtk az boards work-item show --id 193208
+   az boards work-item show --id 193208
    ```
    Do NOT use `--organization` flag (uses default org).
 
@@ -54,7 +48,7 @@ Create with scopes: **Work Items (Read & Write)** + **Code (Read & Write)**
 
 4. **Create OpenSpec Change**
    ```bash
-   rtk openspec new change "us-{id}-{slug}"
+   openspec new change "us-{id}-{slug}"
    ```
 
 ---
@@ -66,28 +60,28 @@ Use these for ALL DevOps operations, browser MCP is FORBIDDEN.
 ### Work Items
 ```bash
 # Read work item
-rtk az boards work-item show --id <id>
+az boards work-item show --id <id>
 
 # Update work item state
-rtk az boards work-item update --id <id> --state "Active"
+az boards work-item update --id <id> --state "Active"
 ```
 
 ### PR Threads (Comments)
 ```bash
 # Read all threads
-rtk az devops invoke \
+az devops invoke \
   --area git --resource pullRequestThreads \
   --route-parameters project={project} repositoryId=<repo> pullRequestId=<id> \
   --http-method GET --api-version 7.1
 
 # Post new comment thread (requires body.json)
-rtk az devops invoke \
+az devops invoke \
   --area git --resource pullRequestThreads \
   --route-parameters project={project} repositoryId=<repo> pullRequestId=<id> \
   --http-method POST --api-version 7.1 --in-file body.json
 
 # Reply to existing thread
-rtk az devops invoke \
+az devops invoke \
   --area git --resource pullRequestThreadComments \
   --route-parameters project={project} repositoryId=<repo> pullRequestId=<id> threadId=<tid> \
   --http-method POST --api-version 7.1 --in-file reply.json
@@ -165,7 +159,7 @@ After outputting the above, the lead MUST run `/opsx-propose` to generate the pr
 ## Guardrails
 
 - ✅ Parse Azure DevOps URL and create OpenSpec change
-- ✅ Use `rtk` for all Azure CLI operations
+- ✅ Use `az` CLI for all Azure DevOps operations
 - ✅ Always run `/opsx-propose` after parsing, never skip to implementation
 - ✅ Always stop and confirm with user after propose, before running `/opsx-apply`
 - ❌ Browser MCP tools for Azure DevOps operations, FORBIDDEN

package/content/.agents/skills/ob-userstory-gh/SKILL.md

@@ -8,14 +8,6 @@ metadata:
   version: "1.1"
 ---
 
-**RTK - MANDATORY**
-
-Use `rtk` wrapper for ALL CLI commands:
-- `rtk gh issue view` NOT `gh issue view`
-- `rtk gh issue list` NOT `gh issue list`
-- `rtk gh issue edit` NOT `gh issue edit`
-- `rtk openspec new change` NOT `openspec new change`
-
 **ALL GitHub data MUST come from `gh` CLI. NEVER use webfetch, HTTP requests, or browser MCP tools to fetch GitHub URLs, even if gh CLI fails. If `gh` is unavailable, report it as a blocker.**
 
 ---
@@ -41,7 +33,7 @@ gh auth status
 
 2. **Fetch Issue**, always pass `--repo` explicitly, never rely on git context:
    ```bash
-   rtk gh issue view 42 --repo {owner}/{repo} --json number,title,body,labels,milestone,state
+   gh issue view 42 --repo {owner}/{repo} --json number,title,body,labels,milestone,state
    ```
    If this returns an auth error or 404, report as a blocker, do NOT fall back to webfetch or web search.
 
@@ -55,7 +47,7 @@ gh auth status
 
 4. **Create OpenSpec Change**
    ```bash
-   rtk openspec new change "gh-{number}-{slug}"
+   openspec new change "gh-{number}-{slug}"
    ```
 
 ---
@@ -67,13 +59,13 @@ Use these for ALL GitHub operations, browser MCP and webfetch are FORBIDDEN. Alw
 ### Issues
 ```bash
 # Read issue
-rtk gh issue view <number> --repo {owner}/{repo}
+gh issue view <number> --repo {owner}/{repo}
 
 # List open issues
-rtk gh issue list --repo {owner}/{repo} --state open --limit 10
+gh issue list --repo {owner}/{repo} --state open --limit 10
 
 # Update issue
-rtk gh issue edit <number> --repo {owner}/{repo} --add-label "in-progress"
+gh issue edit <number> --repo {owner}/{repo} --add-label "in-progress"
 ```
 
 ---
@@ -129,7 +121,7 @@ After outputting the above, the lead MUST run `/opsx-propose` to generate the pr
 ## Guardrails
 
 - ✅ Parse GitHub Issue URL and create OpenSpec change
-- ✅ Use `rtk gh` for all GitHub CLI operations
+- ✅ Use `gh` CLI for all GitHub operations
 - ✅ Always run `/opsx-propose` after parsing, never skip to implementation
 - ✅ Always stop and confirm with user after propose, before running `/opsx-apply`
 - ❌ `webfetch` or HTTP requests to GitHub URLs, FORBIDDEN, use `gh` CLI only

package/content/.opencode/commands/opsx-apply.md

@@ -13,14 +13,14 @@ Implement tasks from an OpenSpec change using the ensemble agent team.
    If a name is provided, use it. Otherwise:
    - Infer from conversation context if the user mentioned a change
    - Auto-select if only one active change exists
-   - If ambiguous, run `rtk openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
+   - If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
 
    Always announce: "Using change: <name>" and how to override (e.g., `/opsx-apply <other>`).
 
 2. **Check status to understand the schema**
 
    ```bash
-   rtk openspec status --change "<name>" --json
+   openspec status --change "<name>" --json
    ```
 
    Parse the JSON to understand:
@@ -30,7 +30,7 @@ Implement tasks from an OpenSpec change using the ensemble agent team.
 3. **Get apply instructions**
 
    ```bash
-   rtk openspec instructions apply --change "<name>" --json
+   openspec instructions apply --change "<name>" --json
    ```
 
    This returns:
@@ -58,7 +58,7 @@ Implement tasks from an OpenSpec change using the ensemble agent team.
 
 6. **Implement via ensemble team**
 
-   NEVER implement tasks directly. Always delegate to specialists via ensemble.
+   NEVER implement tasks directly. Always delegate to engineer workers via ensemble.
    Do NOT touch any source files before the team is running, not even a single edit.
 
    Steps MUST be followed in order. Do not skip any step.
@@ -86,20 +86,40 @@ Implement tasks from an OpenSpec change using the ensemble agent team.
       DO NOT call team_claim yourself, only agents claim tasks.
       DO NOT proceed to 6d until team_tasks_add succeeds.
 
-   **Step 6d.** Discover relevant skills, then spawn specialists.
-
-      Before spawning, scan `.agents/skills/` and read each `SKILL.md` description line.
-      Match skills to agents by domain:
-      - front-engineer: UI, components, framework skills (e.g. next-best-practices, browser-automation)
-      - back-engineer: API, data, service skills
-      - infra-engineer: cloud, pipeline, deployment skills
-      - quality-engineer: testing, coverage skills
+   **Step 6d.** Discover available agents, assign tasks by best fit, then spawn workers.
+
+      Agent discovery and assignment rule:
+      - Read `.agents/agents/*.md` and use each agent's `description` and `## Abilities` to understand specialization.
+      - For each task ID, choose the best-fit agent based on task domain (backend, frontend, infra, testing, etc.).
+      - Prefer specialized agents when available; use `basic-engineer` as fallback only.
+      - Only spawn agents that have assigned task IDs.
+
+      REQUIRED assignment algorithm (do not skip):
+      1. Build candidate list from `.agents/agents/*.md` excluding `devops-manager`.
+      2. Classify each task by domain using task text (api/backend, ui/frontend, infra/devops, testing/qa).
+      3. For each task, score every candidate agent:
+         - +3 if agent description explicitly matches domain
+         - +2 if agent `## Abilities` include domain-relevant skills
+         - +1 if prior tasks of same domain already assigned to that agent (cohesion)
+      4. Assign task to highest-score agent.
+      5. Use `basic-engineer` ONLY when no specialized agent has positive score.
+      6. If all tasks go to `basic-engineer`, you MUST explain why no specialist matched.
+
+      HARD RULES:
+      - NEVER assign a task to `basic-engineer` if a specialized agent has higher score.
+      - NEVER skip agent discovery from `.agents/agents/*.md`.
+      - ALWAYS include assignment rationale in spawn prompt: "Selected because <domain match>".
+
+      Skill loading is worker-driven:
+      - The spawned agent MUST load `@ob-global` first.
+      - Then it MUST load skills from its own `## Abilities` for the claimed task domain.
 
       Each team_spawn MUST include the agent field (required, causes NOT NULL error if omitted).
 
       The spawn prompt must contain exactly:
       1. Their name and role on this team
       2. Which tasks are theirs, list the task IDs and content from the board
+      2.1 Why they were selected for those tasks (domain/abilities match)
       3. Key context they need (summarized from context files, do NOT tell them to read files themselves)
       4. The 6 OpenCode tools they have available (these are OpenCode tools, NOT shell commands, call them directly as tools, never via bash):
          team_claim, team_tasks_complete, team_tasks_list, team_tasks_add, team_message, team_broadcast
@@ -109,21 +129,18 @@ Implement tasks from an OpenSpec change using the ensemble agent team.
       Keep spawn prompts under 600 tokens. Do not describe team internals or how ensemble works.
       Only spawn agents whose tasks are actually needed by this change. Skip agents with no tasks.
 
-      First spawn all agents (wait for each team_spawn to confirm before the next):
+      Spawn one or more best-fit workers (parallel when dependencies allow):
       ```
-      team_spawn name:"back" agent:"back-engineer" prompt:"..."
-      (wait for result)
-      team_spawn name:"front" agent:"front-engineer" prompt:"..."
-      (wait for result)
-      team_spawn name:"infra" agent:"infra-engineer" prompt:"..."
-      (wait for result)
+      team_spawn name:"eng-1" agent:"backend-engineer" prompt:"..."
+      team_spawn name:"eng-2" agent:"frontend-engineer" prompt:"..."
+      team_spawn name:"eng-3" agent:"basic-engineer" prompt:"..."
       ```
 
-      Then immediately send each spawned agent a start message to kick them off:
+      Then immediately send each spawned worker a start message with exact task IDs:
       ```
-      team_message to:"back" text:"Start now. Read all skills listed in your prompt first, confirm loaded skills, then claim your first task with team_claim."
-      team_message to:"front" text:"Start now. Read all skills listed in your prompt first, confirm loaded skills, then claim your first task with team_claim."
-      team_message to:"infra" text:"Start now. Read all skills listed in your prompt first, confirm loaded skills, then claim your first task with team_claim."
+      team_message to:"eng-1" text:"Start now. Load @ob-global first, then use your agent `## Abilities` for these tasks: [task-<id1>] ... Claim each task ID before starting."
+      team_message to:"eng-2" text:"Start now. Load @ob-global first, then use your agent `## Abilities` for these tasks: [task-<id2>] ... Claim each task ID before starting."
+      team_message to:"eng-3" text:"Start now. Load @ob-global first, then use your agent `## Abilities` for these tasks: [task-<id3>] ... Claim each task ID before starting."
       ```
 
    **Step 6e.** After sending start messages, tell the user what is running, then STOP and wait.
@@ -135,18 +152,18 @@ Implement tasks from an OpenSpec change using the ensemble agent team.
       If team_merge blocks ("overlapping local changes"), commit or stash your local changes first, then retry.
       Fix any other blockers reported.
 
-7. **Quality check**
+7. **Verification check**
 
-   Spawn quality engineer with worktree:false (read-only, no file edits):
-   ```
-   team_spawn name:"quality" agent:"quality-engineer" worktree:false prompt:"<verification scope, context summary, run tests + build + lint + verify acceptance criteria, no task claiming required in this phase, send results to lead when done>"
-   ```
-   Wait for message → team_results → fix blockers → team_shutdown (no team_merge needed, worktree:false)
+   Run verification tasks (tests/build/lint) using a worker suited for verification scope:
+   - either same engineer workers
+   - or a dedicated verifier worker if your project defines one
+
+   Wait for results → fix blockers.
 
 8. **Mark tasks complete in openspec**
 
    Update tasks.md: `- [ ]` → `- [x]` for each completed task.
-   Run `rtk openspec status --change "<name>" --json` to confirm.
+   Run `openspec status --change "<name>" --json` to confirm.
 
 9. **Show status, then cleanup**
 
@@ -169,10 +186,10 @@ Implement tasks from an OpenSpec change using the ensemble agent team.
 - ALWAYS pass the task IDs returned by team_tasks_add to each agent's spawn prompt
 - NEVER edit files between team_spawn and team_merge, team_merge blocks on overlapping local changes
 - ALWAYS add every task to the board with team_tasks_add before spawning
-- ALWAYS spawn agents sequentially (wait for each team_spawn result before the next), then send start messages to all of them together
+- ALWAYS spawn workers based on dependencies: parallel when safe, sequential when required
 - ALWAYS instruct agents to call team_claim before each task and team_tasks_complete after
 - If teammates are stuck, use team_message to resend tasks, then wait, never implement directly
-- Mark tasks complete in openspec AFTER specialists finish, not before
+- Mark tasks complete in openspec AFTER worker implementation and verification finish, not before
 - Pause on errors, blockers, or unclear requirements. Do not guess
 - Use contextFiles from CLI output, do not assume specific file paths
-- Use `rtk` wrapper for ALL CLI commands. Never run openspec, git, gh, or az directly
+- Follow CLI rules from `@ob-global` when present

package/content/.opencode/plugins/session-log.js

@@ -343,7 +343,7 @@ export const SessionLogPlugin = async ({ client, directory }) => {
               correlationMethod: spawnMatch.spawnedSessionId === sessionId ? "direct" : "time-window",
             })
           } else {
-            // No spawn match — schedule an unmatched-session warning
+            // No spawn match, schedule an unmatched-session warning
             const capturedSessionId = sessionId
             setTimeout(() => {
               const s = sessionState.get(capturedSessionId)