chore: opencode canonical

.opencode/skill/flow-next-export-context/SKILL.md

@@ -12,8 +12,8 @@ Build RepoPrompt context and export to a markdown file for use with external LLM
 **CRITICAL: flowctl is BUNDLED — NOT installed globally.** `which flowctl` will fail (expected). Always use:
 ```bash
 ROOT="$(git rev-parse --show-toplevel)"
-PLUGIN_ROOT="$ROOT/plugins/flow-next"
-FLOWCTL="$PLUGIN_ROOT/scripts/flowctl"
+OPENCODE_DIR="$ROOT/.opencode"
+FLOWCTL="$OPENCODE_DIR/bin/flowctl"
 $FLOWCTL <command>
 ```
 
@@ -34,8 +34,8 @@ Examples:
 
 ```bash
 ROOT="$(git rev-parse --show-toplevel)"
-PLUGIN_ROOT="$ROOT/plugins/flow-next"
-FLOWCTL="$PLUGIN_ROOT/scripts/flowctl"
+OPENCODE_DIR="$ROOT/.opencode"
+FLOWCTL="$OPENCODE_DIR/bin/flowctl"
 REPO_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
 ```
 

.opencode/skill/flow-next-impl-review/SKILL.md

@@ -15,8 +15,8 @@ Conduct a John Carmack-level review of implementation changes on the current bra
 **CRITICAL: flowctl is BUNDLED — NOT installed globally.** `which flowctl` will fail (expected). Always use:
 ```bash
 ROOT="$(git rev-parse --show-toplevel)"
-PLUGIN_ROOT="$ROOT/plugins/flow-next"
-FLOWCTL="$PLUGIN_ROOT/scripts/flowctl"
+OPENCODE_DIR="$ROOT/.opencode"
+FLOWCTL="$OPENCODE_DIR/bin/flowctl"
 ```
 
 ## Backend Selection
@@ -42,17 +42,17 @@ If found, use that backend and skip all other detection.
 
 ```bash
 # Check available backends
-HAVE_RP=0
+HAVE_RP=0;
 if command -v rp-cli >/dev/null 2>&1; then
-  HAVE_RP=1
+  HAVE_RP=1;
 elif [[ -x /opt/homebrew/bin/rp-cli || -x /usr/local/bin/rp-cli ]]; then
-  HAVE_RP=1
-fi
+  HAVE_RP=1;
+fi;
 
 # Get configured backend
-BACKEND="${FLOW_REVIEW_BACKEND:-}"
+BACKEND="${FLOW_REVIEW_BACKEND:-}";
 if [[ -z "$BACKEND" ]]; then
-  BACKEND="$($FLOWCTL config get review.backend 2>/dev/null | jq -r '.value // empty')"
+  BACKEND="$($FLOWCTL config get review.backend --json 2>/dev/null | jq -r '.value // empty')";
 fi
 ```
 
@@ -97,11 +97,10 @@ fi
 5. **Re-reviews MUST stay in SAME chat** - omit `--new-chat` after first review
 
 **For opencode backend:**
-1. Use the task tool with `subagent_type: opencode-reviewer`
-2. Provide full diff context (git log + changed files + diff) and focus areas
-3. Parse verdict from `<verdict>...` tag
-4. If `REVIEW_RECEIPT_PATH` set: write receipt JSON with `mode: "opencode"`
-5. **Re-reviews must reuse the same task session**: capture `session_id` from `<task_metadata>` and pass it back via `session_id` on subsequent task tool calls
+1. Use the **task tool** with subagent_type `opencode-reviewer`
+2. Reviewer gathers context via tools (git diff/log, read files)
+3. Parse verdict from reviewer output
+4. Extract `session_id` from `<task_metadata>` and reuse it for re-reviews
 
 **For all backends:**
 - If `REVIEW_RECEIPT_PATH` set: write receipt after review (any verdict)
@@ -125,8 +124,8 @@ Reviews all changes on **current branch** vs main/master.
 
 ```bash
 ROOT="$(git rev-parse --show-toplevel)"
-PLUGIN_ROOT="$ROOT/plugins/flow-next"
-FLOWCTL="$PLUGIN_ROOT/scripts/flowctl"
+OPENCODE_DIR="$ROOT/.opencode"
+FLOWCTL="$OPENCODE_DIR/bin/flowctl"
 REPO_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
 ```
 
@@ -136,32 +135,18 @@ Run backend detection from SKILL.md above. Then branch:
 
 ### OpenCode Backend
 
-```bash
-TASK_ID="${1:-}"
-BASE_BRANCH="main"
-RECEIPT_PATH="${REVIEW_RECEIPT_PATH:-/tmp/impl-review-receipt.json}"
-
-# Identify changes
-git branch --show-current
-git log main..HEAD --oneline 2>/dev/null || git log master..HEAD --oneline
-git diff main..HEAD --name-only 2>/dev/null || git diff master..HEAD --name-only
-DIFF_OUTPUT="$(git diff main..HEAD 2>/dev/null || git diff master..HEAD)"
-```
-
-Build a review prompt with:
-- Branch + base branch
-- Commit list
-- Changed files
-- Full diff (or a focused diff if huge)
-- Focus areas from arguments
-- Review criteria (correctness, security, performance, tests, risks)
-- Required verdict tag
+Use the task tool with subagent_type `opencode-reviewer`.
 
-Run reviewer subagent using the task tool:
-- subagent_type: `opencode-reviewer`
-- prompt: `<review prompt>`
+Prompt must require:
+- `git log main..HEAD --oneline`
+- `git diff main..HEAD --stat`
+- `git diff main..HEAD`
+- Read any changed files needed for correctness
+- No questions, no code changes, no TodoWrite
+- End with `<verdict>SHIP</verdict>` or `<verdict>NEEDS_WORK</verdict>` or `<verdict>MAJOR_RETHINK</verdict>`
 
-Parse verdict from reviewer response (`<verdict>SHIP|NEEDS_WORK|MAJOR_RETHINK</verdict>`).
+Parse verdict from the subagent response.
+Extract `session_id` from `<task_metadata>` and reuse for re-review.
 
 On NEEDS_WORK: fix code, commit, re-run review (same backend).
 

.opencode/skill/flow-next-impl-review/workflow.md

@@ -15,8 +15,8 @@ The reviewer model only sees provided context. RepoPrompt's Builder discovers co
 ```bash
 set -e
 ROOT="$(git rev-parse --show-toplevel)"
-PLUGIN_ROOT="$ROOT/plugins/flow-next"
-FLOWCTL="$PLUGIN_ROOT/scripts/flowctl"
+OPENCODE_DIR="$ROOT/.opencode"
+FLOWCTL="$OPENCODE_DIR/bin/flowctl"
 REPO_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
 
 # Check available backends
@@ -25,7 +25,7 @@ HAVE_RP=$(which rp-cli >/dev/null 2>&1 && echo 1 || echo 0)
 # Get configured backend (priority: env > config)
 BACKEND="${FLOW_REVIEW_BACKEND:-}"
 if [[ -z "$BACKEND" ]]; then
-  BACKEND="$($FLOWCTL config get review.backend 2>/dev/null | jq -r '.value // empty' 2>/dev/null || echo "")"
+  BACKEND="$($FLOWCTL config get review.backend --json 2>/dev/null | jq -r '.value // empty' 2>/dev/null || echo "")"
 fi
 
 # Fallback to available (opencode preferred)
@@ -71,15 +71,24 @@ Include:
 - Review criteria (correctness, security, performance, tests, risks)
 - Required verdict tag
 
-### Step 3: Execute review
+### Step 3: Execute review (subagent)
 
-Use the task tool:
-- subagent_type: `opencode-reviewer`
-- prompt: `<review prompt>`
+Use the **task** tool with subagent_type `opencode-reviewer`. The reviewer must gather context itself via tools, including Flow task/epic specs.
 
-Capture `session_id` from the `<task_metadata>` block in the tool output and reuse it for any re-review by passing `session_id` back into the task tool. This keeps the same subagent chat.
+**Task tool call** (example):
+```json
+{
+  "description": "Impl review",
+  "prompt": "You are the OpenCode reviewer. Review current branch vs main. Rules: no questions, no code changes, no TodoWrite. REQUIRED: set FLOWCTL to `.opencode/bin/flowctl`, then run `$FLOWCTL show <TASK_ID> --json` and `$FLOWCTL cat <TASK_ID>`. Then get epic id from task JSON and run `$FLOWCTL show <EPIC_ID> --json` and `$FLOWCTL cat <EPIC_ID>`. REQUIRED: run `git log main..HEAD --oneline` (fallback master), `git diff main..HEAD --stat`, `git diff main..HEAD`. Read any changed files needed for correctness. Then output issues grouped by severity and end with exactly one verdict tag: <verdict>SHIP</verdict> or <verdict>NEEDS_WORK</verdict> or <verdict>MAJOR_RETHINK</verdict>.",
+  "subagent_type": "opencode-reviewer"
+}
+```
+
+**After the task completes**:
+- Parse `VERDICT` from the subagent output.
+- Extract `session_id` from the `<task_metadata>` block (used for re-reviews).
 
-**Output must include** `<verdict>SHIP</verdict>` or `<verdict>NEEDS_WORK</verdict>` or `<verdict>MAJOR_RETHINK</verdict>`.
+If `VERDICT` is empty, output `<promise>RETRY</promise>` and stop.
 
 ### Step 4: Receipt
 
@@ -98,7 +107,7 @@ EOF
 If `VERDICT=NEEDS_WORK`:
 1. Parse issues from output
 2. Fix code, commit, run tests
-3. Re-run Step 3 (same backend, same `session_id`)
+3. Re-run Step 3 **with the same task session_id** (pass `session_id` to the task tool)
 4. Repeat until SHIP
 
 ---

.opencode/skill/flow-next-interview/SKILL.md

@@ -12,8 +12,8 @@ Conduct an extremely thorough interview about a task/spec and write refined deta
 **CRITICAL: flowctl is BUNDLED — NOT installed globally.** `which flowctl` will fail (expected). Always use:
 ```bash
 ROOT="$(git rev-parse --show-toplevel)"
-PLUGIN_ROOT="$ROOT/plugins/flow-next"
-FLOWCTL="$PLUGIN_ROOT/scripts/flowctl"
+OPENCODE_DIR="$ROOT/.opencode"
+FLOWCTL="$OPENCODE_DIR/bin/flowctl"
 $FLOWCTL <command>
 ```
 
@@ -41,8 +41,8 @@ If empty, ask: "What should I interview you about? Give me a Flow ID (e.g., fn-1
 
 ```bash
 ROOT="$(git rev-parse --show-toplevel)"
-PLUGIN_ROOT="$ROOT/plugins/flow-next"
-FLOWCTL="$PLUGIN_ROOT/scripts/flowctl"
+OPENCODE_DIR="$ROOT/.opencode"
+FLOWCTL="$OPENCODE_DIR/bin/flowctl"
 ```
 
 ## Detect Input Type
@@ -98,42 +98,51 @@ After interview complete, write everything back.
 
 ### For Flow Epic ID
 
-1. Create a temp file with the refined epic spec including:
-   - Clear problem statement
-   - Technical approach with specifics
-   - Key decisions made during interview
-   - Edge cases to handle
-   - Quick commands section (required)
-   - Acceptance criteria
-
-2. Update epic spec:
-   ```bash
-   $FLOWCTL epic set-plan <id> --file <temp-md> --json
-   ```
-
-3. Create/update tasks if interview revealed breakdown:
-   ```bash
-   $FLOWCTL task create --epic <id> --title "..." --json
-   $FLOWCTL task set-description <task-id> --file <temp-md> --json
-   $FLOWCTL task set-acceptance <task-id> --file <temp-md> --json
-   ```
+Update epic spec using stdin heredoc (preferred):
+```bash
+$FLOWCTL epic set-plan <id> --file - --json <<'EOF'
+# Epic Title
 
-### For Flow Task ID
+## Problem
+Clear problem statement
+
+## Approach
+Technical approach with specifics, key decisions from interview
+
+## Edge Cases
+- Edge case 1
+- Edge case 2
 
-1. Write description to temp file with:
-   - Clear task description
-   - Technical details from interview
-   - Edge cases
+## Quick commands
+```bash
+# smoke test command
+```
 
-2. Write acceptance to temp file with:
-   - Checkboxes for acceptance criteria
-   - Specific, testable conditions
+## Acceptance
+- [ ] Criterion 1
+- [ ] Criterion 2
+EOF
+```
 
-3. Update task:
-   ```bash
-   $FLOWCTL task set-description <id> --file <desc-temp.md> --json
-   $FLOWCTL task set-acceptance <id> --file <acc-temp.md> --json
-   ```
+Create/update tasks if interview revealed breakdown:
+```bash
+$FLOWCTL task create --epic <id> --title "..." --json
+# Use set-spec for combined description + acceptance (fewer writes)
+$FLOWCTL task set-spec <task-id> --description /tmp/desc.md --acceptance /tmp/acc.md --json
+```
+
+### For Flow Task ID
+
+Update task using combined set-spec (preferred) or separate calls:
+```bash
+# Preferred: combined set-spec (2 writes instead of 4)
+$FLOWCTL task set-spec <id> --description /tmp/desc.md --acceptance /tmp/acc.md --json
+
+# Or use stdin for description only:
+$FLOWCTL task set-description <id> --file - --json <<'EOF'
+Clear task description with technical details and edge cases from interview
+EOF
+```
 
 ### For File Path