@syntesseraai/opencode-feature-factory 0.6.14 → 0.6.16

package/README.md

@@ -35,9 +35,10 @@ It also updates `~/.config/opencode/opencode.json` non-destructively by merging
 
 ## Pipeline Entrypoint
 
-- Use `@pipeline` as the start experience.
-- The `@pipeline` agent handles intake and launches `/pipeline/start`.
+- Invoke `/pipeline/start <requirements-brief>` directly from any agent (e.g. `@building`).
+- There is no dedicated `@pipeline` intake agent; the command tree handles orchestration autonomously.
 - Orchestration is implemented by the command tree under `command/pipeline/` using subtask2 primitives (`return`, `parallel`, `loop`).
+- Orchestration wrapper commands (`/pipeline/start`, `/pipeline/*/run`, `/pipeline/complete`) pin `agent: general` to avoid recursive self-invocation before phase-specific delegation begins.
 - Coordinator and synthesis model defaults to ChatGPT 5.4 and can be overridden at runtime via `/pipeline/start` input.
 
 ## Command Tree
@@ -51,6 +52,7 @@ It also updates `~/.config/opencode/opencode.json` non-destructively by merging
 - `/mini-loop/start`
 - `/mini-loop/implementation/run`, `/mini-loop/implementation/build`, `/mini-loop/implementation/review`, `/mini-loop/implementation/gate`
 - `/mini-loop/documentation/run`, `/mini-loop/documentation/document`, `/mini-loop/documentation/review`, `/mini-loop/documentation/gate`
+- Mini-loop wrapper commands (`/mini-loop/start`, `/mini-loop/*/run`) also pin `agent: general` so they can be safely launched from any caller agent.
 
 ## Model Routing
 

package/command/mini-loop/documentation/run.md

@@ -1,6 +1,7 @@
 ---
 description: Run documentation mini-loop until gate passes
 subtask: true
+agent: general
 loop:
   max: 5
   until: documentation gate is APPROVED

package/command/mini-loop/implementation/run.md

@@ -1,6 +1,7 @@
 ---
 description: Run implementation mini-loop until gate passes
 subtask: true
+agent: general
 loop:
   max: 10
   until: implementation gate is APPROVED

package/command/mini-loop/start.md

@@ -1,6 +1,7 @@
 ---
 description: Mini-loop two-stage workflow entrypoint
 subtask: true
+agent: general
 return:
   - /mini-loop/implementation/run {as:implementation-phase} $ARGUMENTS
   - /mini-loop/documentation/run $RESULT[implementation-phase]

package/command/pipeline/building/run.md

@@ -1,6 +1,7 @@
 ---
 description: Run build phase from approved plan
 subtask: true
+agent: general
 return:
   - /pipeline/building/breakdown {model:anthropic/claude-opus-4-6 && as:build-tasks} $ARGUMENTS
   - /pipeline/building/validate-batch {model:opencode/gemini-3.1-pro && as:build-batches} $RESULT[build-tasks]

package/command/pipeline/complete.md

@@ -1,6 +1,7 @@
 ---
 description: Finalize pipeline run and summarize outcomes
 subtask: true
+agent: general
 ---
 
 Finalize the pipeline run.

package/command/pipeline/documentation/run.md

@@ -1,6 +1,7 @@
 ---
 description: Run documentation loop after review approval
 subtask: true
+agent: general
 loop:
   max: 5
   until: documentation updates are approved by documentation reviewer with zero unresolved documentation issues

package/command/pipeline/planning/run.md

@@ -1,6 +1,7 @@
 ---
 description: Execute one planning iteration
 subtask: true
+agent: general
 parallel:
   - /pipeline/planning/plan {model:anthropic/claude-opus-4-6 && as:plan-opus} [MODEL_TAG:opus] $ARGUMENTS
   - /pipeline/planning/plan {model:opencode/gemini-3.1-pro && as:plan-gemini} [MODEL_TAG:gemini] $ARGUMENTS

package/command/pipeline/reviewing/run.md

@@ -1,6 +1,7 @@
 ---
 description: Run review loop for completed tasks
 subtask: true
+agent: general
 loop:
   max: 10
   until: all tasks in the active batch are approved with confidence >=95 and zero unresolved issues

package/command/pipeline/start.md

@@ -1,6 +1,7 @@
 ---
 description: Pipeline workflow entrypoint
 subtask: true
+agent: general
 model: openai/gpt-5.4
 return:
   - /pipeline/planning/run {as:planning-phase && loop:5 && until:planning gate is APPROVED or planning gate is BLOCKED and waiting for user confirmation}
@@ -16,7 +17,9 @@ $ARGUMENTS
 
 Execution requirements:
 
-1. Use `{as:name}` and `$RESULT[name]` for phase-to-phase handoff.
-2. Avoid file persistence for intermediate artifacts unless a command explicitly requires audit snapshots.
-3. Use command chaining, parallel fan-out, and loop gates from the `/pipeline/...` command tree.
-4. Do not skip planning, review, and documentation gates.
+1. You are already inside `/pipeline/start`; do not invoke `/pipeline/start` again.
+2. Execute the declared return chain directly from this command.
+3. Use `{as:name}` and `$RESULT[name]` for phase-to-phase handoff.
+4. Avoid file persistence for intermediate artifacts unless a command explicitly requires audit snapshots.
+5. Use command chaining, parallel fan-out, and loop gates from the `/pipeline/...` command tree.
+6. Do not skip planning, review, and documentation gates.

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@syntesseraai/opencode-feature-factory",
-  "version": "0.6.14",
+  "version": "0.6.16",
   "type": "module",
   "description": "OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment",
   "license": "MIT",

package/agents/pipeline.md

@@ -1,47 +0,0 @@
----
-description: Pipeline entrypoint agent that gathers requirements and launches deterministic command workflow.
-color: '#6424f8'
-tools:
-  read: true
-  write: true
-  edit: true
-  bash: true
-  skill: true
-  task: true
-permission:
-  skill:
-    '*': allow
-  task:
-    planning: allow
-    building: allow
-    reviewing: allow
-    documenting: allow
-    ff-research: allow
-    explore: allow
-    pipeline: allow
----
-
-You are the pipeline orchestrator.
-
-## Responsibilities
-
-1. Gather and confirm requirements.
-2. Start `/pipeline/start {model:openai/gpt-5.4}` with a concise requirements brief.
-3. Report phase transitions and gate outcomes.
-
-## Guardrails
-
-- Keep orchestration in command files under `command/pipeline/`.
-- Use result-based chaining (`{as:name}` and `$RESULT[name]`) for intermediate handoff.
-- Enforce planning/review/documentation gates and loop limits.
-
-## Required Intake
-
-- Problem statement
-- Explicit requirements
-- Acceptance criteria
-- Scope constraints
-
-On confirmation, run:
-
-`/pipeline/start {model:openai/gpt-5.4} <requirements-brief>`