@syntesseraai/opencode-feature-factory 0.6.11 → 0.6.12

package/README.md

@@ -48,6 +48,9 @@ It also updates `~/.config/opencode/opencode.json` non-destructively by merging
 - `/pipeline/reviewing/run`, `/pipeline/reviewing/triage`, `/pipeline/reviewing/review`, `/pipeline/reviewing/synthesize`, `/pipeline/reviewing/gate`
 - `/pipeline/documentation/run`, `/pipeline/documentation/document`, `/pipeline/documentation/review`, `/pipeline/documentation/gate`
 - `/pipeline/complete`
+- `/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`
 
 ## Model Routing
 

package/agents/planning.md

@@ -12,10 +12,8 @@ permission:
   skill:
     '*': allow
   task:
-    reviewing: allow
     ff-research: allow
-    explore: allow
-    general: deny
+    '*': deny
 ---
 
 You are the planning specialist.
@@ -45,9 +43,9 @@ When producing plans, include:
 
 ## Delegation Guidance
 
-- Use `@ff-research` for external/library uncertainty.
-- Use `@reviewing` for focused acceptance/risk validation when requirements are unclear.
-- Use `@explore` for local codebase discovery.
+- Use `@ff-research` only for external/library uncertainty.
+- Do not delegate to `@building`, `@reviewing`, `@documenting`, `@planning`, or `@explore`.
+- Never perform implementation or file-modifying work in planning mode.
 
 ## Gate Contract
 

package/agents/reviewing.md

@@ -12,9 +12,8 @@ permission:
   skill:
     '*': allow
   task:
-    reviewing: allow
-    explore: allow
-    general: deny
+    ff-research: allow
+    '*': deny
 ---
 
 You are the unified reviewing specialist.
@@ -53,4 +52,6 @@ When acting as gate reviewer, output status line exactly:
 ## Operating Mode
 
 - Use result-based handoff (`$RESULT[...]`) rather than file-based artifacts.
-- Keep reports concise, evidence-based, and directly actionable for `@building` or `@documenting`.
+- Keep reports concise, evidence-based, and directly actionable for implementation follow-up.
+- Do not delegate except `@ff-research` for external/library uncertainty.
+- Never perform implementation or file-modifying work in reviewing mode.

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

@@ -0,0 +1,14 @@
+---
+description: Write documentation pass for mini-loop
+subtask: true
+agent: documenting
+---
+
+Update repository documentation for the approved mini-loop implementation from `$ARGUMENTS`.
+
+Requirements:
+
+1. Reflect shipped behavior and operational steps exactly.
+2. Apply prior documentation rework feedback when present.
+3. Keep updates concise and cross-link impacted docs when needed.
+4. Return a concise documentation update report with changed docs and rationale.

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

@@ -0,0 +1,15 @@
+---
+description: Apply documentation mini-loop gate
+subtask: true
+agent: reviewing
+---
+
+Read the latest documentation review input from `$ARGUMENTS` and apply this gate exactly:
+
+- APPROVED only when `CONFIDENCE` is strictly `>95`, `CHANGE_REQUESTED=NO`, and `UNRESOLVED_DOCUMENTATION_ISSUES=0`
+- REWORK when not approved and iteration < 5
+- ESCALATE when iteration == 5 and still not approved
+
+Output exactly one line:
+
+`MINI_LOOP_DOCUMENTATION_GATE=APPROVED|REWORK|ESCALATE`

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

@@ -0,0 +1,16 @@
+---
+description: Review documentation pass for mini-loop
+subtask: true
+agent: reviewing
+---
+
+Review the latest mini-loop documentation pass from `$ARGUMENTS`.
+
+Required output fields:
+
+1. `CHANGE_REQUESTED=YES|NO`
+2. `UNRESOLVED_DOCUMENTATION_ISSUES=<integer>`
+3. `CONFIDENCE=<0-100>`
+4. concise documentation rework instructions when change is requested
+
+Return a deterministic structured documentation review result with no file persistence.

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

@@ -0,0 +1,20 @@
+---
+description: Run documentation mini-loop until gate passes
+subtask: true
+loop:
+  max: 5
+  until: documentation gate is APPROVED
+return:
+  - /mini-loop/documentation/document {model:openai/gpt-5.3-codex && as:mini-doc-pass} $ARGUMENTS
+  - /mini-loop/documentation/review {model:openai/gpt-5.4 && as:mini-doc-review} $RESULT[mini-doc-pass]
+  - /mini-loop/documentation/gate {model:openai/gpt-5.4} $RESULT[mini-doc-review]
+  - If `MINI_LOOP_DOCUMENTATION_GATE=REWORK`, continue loop with prior documentation review feedback included in the next documentation pass.
+---
+
+Execute the documentation mini-loop for the approved implementation context.
+
+Stop criteria:
+
+- approve when `MINI_LOOP_DOCUMENTATION_GATE=APPROVED`
+- continue while `MINI_LOOP_DOCUMENTATION_GATE=REWORK` and iteration < 5
+- escalate to user when iteration reaches 5 without approval

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

@@ -0,0 +1,14 @@
+---
+description: Build implementation pass for mini-loop
+subtask: true
+agent: building
+---
+
+Implement the current mini-loop requirements from `$ARGUMENTS`.
+
+Requirements:
+
+1. Apply requested code rework when present.
+2. Add or update tests for behavioral changes.
+3. Run lint/typecheck/tests only for impacted scope.
+4. Return a concise implementation report with changed files, tests run, and known open issues.

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

@@ -0,0 +1,15 @@
+---
+description: Apply implementation mini-loop gate
+subtask: true
+agent: reviewing
+---
+
+Read the latest implementation review input from `$ARGUMENTS` and apply this gate exactly:
+
+- APPROVED only when `CONFIDENCE` is strictly `>95`, `CHANGE_REQUESTED=NO`, and `UNRESOLVED_BLOCKING_ISSUES=0`
+- REWORK when not approved and iteration < 10
+- ESCALATE when iteration == 10 and still not approved
+
+Output exactly one line:
+
+`MINI_LOOP_IMPLEMENTATION_GATE=APPROVED|REWORK|ESCALATE`

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

@@ -0,0 +1,16 @@
+---
+description: Review implementation pass for mini-loop
+subtask: true
+agent: reviewing
+---
+
+Review the latest mini-loop implementation output from `$ARGUMENTS`.
+
+Required output fields:
+
+1. `CHANGE_REQUESTED=YES|NO`
+2. `UNRESOLVED_BLOCKING_ISSUES=<integer>`
+3. `CONFIDENCE=<0-100>`
+4. concise rework instructions when change is requested
+
+Return a deterministic structured review result with no file persistence.

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

@@ -0,0 +1,20 @@
+---
+description: Run implementation mini-loop until gate passes
+subtask: true
+loop:
+  max: 10
+  until: implementation gate is APPROVED
+return:
+  - /mini-loop/implementation/build {model:openai/gpt-5.3-codex && as:mini-impl-build} $ARGUMENTS
+  - /mini-loop/implementation/review {model:openai/gpt-5.4 && as:mini-impl-review} $RESULT[mini-impl-build]
+  - /mini-loop/implementation/gate {model:openai/gpt-5.4} $RESULT[mini-impl-review]
+  - If `MINI_LOOP_IMPLEMENTATION_GATE=REWORK`, continue loop with prior review feedback included in the next build input.
+---
+
+Execute the implementation mini-loop for the active requirements/rework context.
+
+Stop criteria:
+
+- approve when `MINI_LOOP_IMPLEMENTATION_GATE=APPROVED`
+- continue while `MINI_LOOP_IMPLEMENTATION_GATE=REWORK` and iteration < 10
+- escalate to user when iteration reaches 10 without approval

package/command/mini-loop/start.md

@@ -0,0 +1,18 @@
+---
+description: Mini-loop two-stage workflow entrypoint
+subtask: true
+model: openai/gpt-5.4
+return:
+  - /mini-loop/implementation/run {as:implementation-phase} $ARGUMENTS
+  - /mini-loop/documentation/run $RESULT[implementation-phase]
+---
+
+Run the two-stage mini-loop workflow from this requirements brief:
+
+$ARGUMENTS
+
+Execution requirements:
+
+1. Always complete implementation approval before starting documentation.
+2. Use `{as:name}` and `$RESULT[name]` for all handoffs.
+3. Keep loop decisions deterministic and gate-driven.

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@syntesseraai/opencode-feature-factory",
-  "version": "0.6.11",
+  "version": "0.6.12",
   "type": "module",
   "description": "OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment",
   "license": "MIT",