@syntesseraai/opencode-feature-factory 0.11.7 → 0.11.9

package/AGENTS.md

@@ -37,9 +37,9 @@ When work changes behavior, workflows, configuration, operational guidance, or r
 ## Preferred Tooling Pattern
 
 - Use codebase-memory MCP graph tools first in stage agents (`codebase-memory-mcp_search_graph`, `codebase-memory-mcp_get_architecture`, `codebase-memory-mcp_trace_call_path`, `codebase-memory-mcp_get_code_snippet`) for discovery, architecture context, and call-path impact analysis.
-- Keep `morph-mcp_codebase_search` as fallback when codebase-memory MCP is unavailable or the repository has not been indexed.
+- Keep `read`/`glob`/`grep` as fallback when codebase-memory MCP is unavailable or the repository has not been indexed.
 - Use `read`, `glob`, and `grep` for targeted file inspection.
-- Writable agents should prefer `morph-mcp` `edit_file`, then fallback to native `edit` when needed.
+- Writable agents should prefer native `edit` for file updates.
 - Keep `edit` restricted on read-only agents (`planning`, `reviewing`).
 - Route Git operations through `bash` with explicit `git`/`gh` allowlists (and optional `oo git`/`oo gh` wrappers) per OpenCode granular `permission.bash` rules, with last-match-wins ordering.
 - Keep read-only agents deny-first for shell usage (`bash: {'*': deny}` with explicit `git`/`gh` and `oo git`/`oo gh` overrides).

package/README.md

@@ -74,11 +74,11 @@ Instead, the `feature-factory` primary agent orchestrates workflows natively by
 6. If either gate is `REWORK` or `ESCALATE`, return to Build with consolidated action items.
 7. Complete only when both gates are `APPROVED`.
 
-Each transition carries forward prior-stage context (summary, gate/verdict, action items, open issues, and raw output via `$RESULT[...]`) so downstream stages receive full handoff state.
+Each transition carries forward normalized prior-stage context (summary, gate/verdict, action items, open issues, and resolved prior output excerpts sourced from previous stage output or existing context) so downstream stages receive full handoff state without unresolved placeholder aliases.
 
-Writable stage agents (`building`, `documenting`) prefer Morph MCP `edit_file` and can fallback to native `edit` (and `write` for new files) when needed. Read-only agents keep `edit` disabled.
+Writable stage agents (`building`, `documenting`) prefer native `edit` (and `write` for new files) when needed. Read-only agents keep `edit` disabled.
 
-Stage-agent code discovery is graph-first: planning/building/reviewing/documenting prefer codebase-memory MCP tools (`codebase-memory-mcp_search_graph`, `codebase-memory-mcp_get_architecture`, `codebase-memory-mcp_trace_call_path`, `codebase-memory-mcp_get_code_snippet`) before semantic warp_grep/warpgrep-style fallbacks.
+Stage-agent code discovery is graph-first: planning/building/reviewing/documenting prefer codebase-memory MCP tools (`codebase-memory-mcp_search_graph`, `codebase-memory-mcp_get_architecture`, `codebase-memory-mcp_trace_call_path`, `codebase-memory-mcp_get_code_snippet`) for repository-local analysis, and use `gh_grep_searchGitHub` when investigating public GitHub source examples.
 
 ### Permission policy for shell and PTY tools
 
@@ -90,12 +90,12 @@ Feature Factory agent assets follow OpenCode granular permissions (`permission.b
 
 ### Plugin auto-handoff safety net
 
-The plugin includes an auto-handoff hook that continues deterministic next steps by reading explicit machine-readable fields from assistant output and dispatching a `subtask` prompt via `client.session.prompt(...)`.
+The plugin includes an auto-handoff hook that continues deterministic next steps by reading explicit machine-readable fields from assistant output and dispatching the extracted prompt as a normal text prompt via `client.session.prompt(...)` while setting the target agent.
 
 - The orchestrator (`@feature-factory`) remains the source of truth for workflow progression.
 - Auto-handoff is a continuation safety net, not a replacement for orchestrator logic.
 - Multi-stage continuation should target `feature-factory`; one-stage follow-up can target a stage agent.
-- Dispatch is performed through direct API prompt calls (not slash-command execution), and handoffs are executed as sub-agent tasks.
+- Dispatch is performed through direct API prompt calls (not slash-command execution), and handoffs are injected as the next user turn for the targeted agent.
 
 ## Quick Commands
 
@@ -133,21 +133,8 @@ The plugin merges the following MCP servers into global OpenCode config when mis
 - `jina-ai`
 - `gh_grep`
 - `context7`
-- `morph-mcp`
 
-`codebase-memory-mcp` is currently treated as an optional prerequisite (not auto-provisioned by this plugin) because it commonly requires repository-specific indexing/setup. Stage agents still include morph semantic fallback guidance when codebase-memory MCP is unavailable.
-
-`morph-mcp` is configured as:
-
-```json
-"morph-mcp": {
-  "type": "local",
-  "command": ["npx", "-y", "@morphllm/morphmcp"],
-  "environment": {
-    "MORPH_API_KEY": "{env:MORPH_API_KEY}"
-  }
-}
-```
+`codebase-memory-mcp` is currently treated as an optional prerequisite (not auto-provisioned by this plugin) because it commonly requires repository-specific indexing/setup.
 
 The plugin also merges the following default plugins when they are missing:
 
@@ -158,12 +145,12 @@ The plugin also merges the following default plugins when they are missing:
 
 ### Merge Outcomes
 
-`DEFAULT_MCP_SERVERS` currently includes 4 servers (`jina-ai`, `gh_grep`, `context7`, `morph-mcp`).
+`DEFAULT_MCP_SERVERS` currently includes 3 servers (`jina-ai`, `gh_grep`, `context7`).
 
 The merge behavior is additive and non-destructive:
 
-- Empty or missing existing MCP config -> 4 servers after merge.
-- Existing config with 1 custom server and a customized `gh_grep` entry -> 5 servers after merge (custom + customized `gh_grep` + 3 missing defaults).
+- Empty or missing existing MCP config -> 3 servers after merge.
+- Existing config with 1 custom server and a customized `gh_grep` entry -> 4 servers after merge (custom + customized `gh_grep` + 2 missing defaults).
 - Existing server definitions are preserved and never overwritten by defaults.
 
 Plugin merge behavior is also additive and non-destructive:

package/agents/building.md

@@ -7,7 +7,6 @@ tools:
   read: true
   write: true
   edit: true
-  edit_file: true
   bash: true
   skill: true
   task: true
@@ -16,7 +15,6 @@ tools:
   'codebase-memory-mcp_trace_call_path': true
   'codebase-memory-mcp_get_code_snippet': true
   'codebase-memory-mcp_search_code': true
-  'morph-mcp_codebase_search': true
 permission:
   skill:
     '*': allow
@@ -49,13 +47,14 @@ You are the building specialist.
 
 ## Operating Mode
 
-- Use plan/build/review command handoff via `$RESULT[...]`.
+- Use normalized, resolved stage handoff context from prior-stage output or existing context.
+- Never rely on unresolved placeholder aliases in handoff prompts.
 - Do not rely on intermediate artifact files for pipeline progression.
 - Persist only when explicitly requested by the user.
 
 ## Editing Workflow (Required)
 
-Prefer the OpenCode `edit_file` tool (Fast Apply) for all implementation edits.
+Use the OpenCode `edit` tool for implementation edits.
 
 Fallback policy:
 
@@ -64,9 +63,9 @@ Fallback policy:
 - **New files (all models):** `write` or `patch` are acceptable.
 
 1. **Read before editing** to confirm current behavior and scope.
-2. **Apply changes with `edit_file`** for targeted replacements/insertions whenever available.
+2. **Apply changes with `edit`** for targeted replacements/insertions.
 3. **Re-read after edits** to verify the applied diff and avoid stale assumptions.
-4. If `edit_file` is unavailable or cannot express the required change, choose fallback by model family: Codex → `patch`/`apply_patch`; non-Codex → `edit`.
+4. If `edit` cannot express the required change, choose fallback by model family: Codex → `patch`/`apply_patch`; non-Codex → `edit`.
 5. For brand-new files, use `write` or `patch`.
 
 ## Semantic Code Search
@@ -78,15 +77,14 @@ Use codebase-memory MCP tools first for semantic/structural code search when you
 - Trace caller/callee impact with `codebase-memory-mcp_trace_call_path`
 - Read exact source around graph hits with `codebase-memory-mcp_get_code_snippet`
 
-Prefer this over warp_grep/warpgrep-style search because graph context reduces false positives and improves dependency-aware edits.
+Prefer this over generic text-only search because graph context reduces false positives and improves dependency-aware edits. For public GitHub source examples, use `gh_grep_searchGitHub`.
 
 Search fallback order:
 
 1. `codebase-memory-mcp_search_graph` + `codebase-memory-mcp_get_architecture` for discovery.
 2. `codebase-memory-mcp_trace_call_path` / `codebase-memory-mcp_get_code_snippet` for impact and code verification.
-3. `morph-mcp_codebase_search` if codebase-memory MCP is unavailable or unindexed.
-4. `read` to inspect exact implementation details before editing.
-5. `grep` for exact symbol/literal checks when needed.
+3. `read` to inspect exact implementation details before editing.
+4. `grep` for exact symbol/literal checks when needed.
 
 ## Command Output Compression
 

package/agents/documenting.md

@@ -7,7 +7,6 @@ tools:
   read: true
   write: true
   edit: true
-  edit_file: true
   bash: true
   pty_spawn: false
   pty_write: false
@@ -21,7 +20,6 @@ tools:
   'codebase-memory-mcp_trace_call_path': true
   'codebase-memory-mcp_get_code_snippet': true
   'codebase-memory-mcp_search_code': true
-  'morph-mcp_codebase_search': true
 permission:
   skill:
     '*': allow
@@ -52,6 +50,11 @@ You are the documenting specialist.
 - Explain what changed, why it matters, when a reader should use the document, and where they should go next.
 - Return a structured summary for documentation review.
 
+## Operating Mode
+
+- Use normalized, resolved stage handoff context from prior-stage output or existing context.
+- Never rely on unresolved placeholder aliases in handoff prompts.
+
 ## Shared Documentation Rules (Required)
 
 Always load `ff-documentation-rules` before scoping or editing documentation. Treat it as the authoritative rule set for repository documentation placement, `INDEX.md` navigation, cross-references, and root `README.md` entry points.
@@ -65,7 +68,7 @@ Always load `ff-documentation-rules` before scoping or editing documentation. Tr
 
 ## Editing Workflow (Required)
 
-Prefer the OpenCode `edit_file` tool (Fast Apply) for documentation updates.
+Use the OpenCode `edit` tool for documentation updates.
 
 Fallback policy:
 
@@ -76,9 +79,9 @@ Fallback policy:
 1. **Read the current navigation chain first** — inspect the root `README.md`, `docs/INDEX.md`, relevant nested `docs/**/INDEX.md` files, and affected leaf docs before editing.
 2. **Verify behavior from code** — use semantic search and targeted reads so the documentation matches what actually ships.
 3. **Update canonical docs and navigation together** — change the affected leaf docs, every impacted `INDEX.md`, and the root `README.md` when primary documentation entry points or doc structure change.
-4. **Apply changes with `edit_file`** for precise doc updates whenever available.
+4. **Apply changes with `edit`** for precise doc updates.
 5. **Re-read after edits** to validate wording, relative links, and cross-doc consistency.
-6. If `edit_file` is unavailable or cannot express the required change, choose fallback by model family: Codex → `patch`/`apply_patch`; non-Codex → `edit`.
+6. If `edit` cannot express the required change, choose fallback by model family: Codex → `patch`/`apply_patch`; non-Codex → `edit`.
 7. For brand-new documentation files, use `write` or `patch`.
 
 ## Semantic Code Search
@@ -94,9 +97,8 @@ Search fallback order:
 
 1. `codebase-memory-mcp_search_graph` + `codebase-memory-mcp_get_architecture` for graph-first discovery.
 2. `codebase-memory-mcp_trace_call_path` / `codebase-memory-mcp_get_code_snippet` for behavior confirmation.
-3. `morph-mcp_codebase_search` if codebase-memory MCP is unavailable or the repo is not indexed.
-4. `read` to verify exact behavior before writing docs.
-5. `grep` for exact symbol/literal checks when needed.
+3. `read` to verify exact behavior before writing docs.
+4. `grep` for exact symbol/literal checks when needed.
 
 ## Command Output Compression
 

package/agents/feature-factory.md

@@ -8,7 +8,6 @@ tools:
   glob: true
   write: false
   edit: false
-  edit_file: false
   bash: false
   pty_spawn: false
   pty_write: false
@@ -17,7 +16,6 @@ tools:
   pty_kill: false
   skill: true
   task: true
-  'morph-mcp_codebase_search': false
 permission:
   skill:
     '*': allow
@@ -38,7 +36,7 @@ Do not call `ff_pipeline`, `ff_mini_loop`, or `ff_list_models`. This workflow is
 This is an orchestration-only, read-only agent. Do not run direct implementation tools.
 
 - Allowed direct tools: `task`, `read`, `glob`, and `skill` (shared instruction loading only).
-- Do not run `write`, `edit`, `edit_file`, `bash`, PTY tools, or semantic search tools directly from this agent.
+- Do not run `write`, `edit`, `bash`, PTY tools, or semantic search tools directly from this agent.
 - Any investigation, edits, command execution, or validation must be delegated to the appropriate sub-agent.
 
 ## Delegation-first execution policy
@@ -130,7 +128,7 @@ When delegating each stage, include:
 3. **Previous stage summary**
 4. **Previous stage gate/verdict**
 5. **Key action items / issues**
-6. **Raw prior output via `$RESULT[...]`**
+6. **Resolved prior output context (never unresolved placeholders)**
 
 ### Handoff template (use for every transition)
 
@@ -148,12 +146,20 @@ PREVIOUS_STAGE_OPEN_ISSUES:
 - ...
 
 RAW_PREVIOUS_STAGE_OUTPUT:
-$RESULT[<previous_stage_alias>]
+<resolved prior-stage output excerpt or summary>
+
+RESOLUTION_SOURCE:
+<previous stage output | existing context>
+
+PLACEHOLDER_CHECK:
+PASS (no unresolved placeholder tokens such as unresolved result aliases)
 
 CURRENT_STAGE_OBJECTIVE:
 <what this stage must do now>
 ```
 
+Never pass unresolved placeholder aliases (for example unresolved result-alias syntax) in stage handoff prompts.
+
 ### "Clear and obvious" transition rule
 
 Move to the next stage only when output is clear and obvious, meaning:

package/agents/planning.md

@@ -20,7 +20,6 @@ tools:
   'codebase-memory-mcp_trace_call_path': true
   'codebase-memory-mcp_get_code_snippet': true
   'codebase-memory-mcp_search_code': true
-  'morph-mcp_codebase_search': true
 permission:
   skill:
     '*': allow
@@ -53,7 +52,7 @@ You are the planning specialist.
 
 ## Editing Guidance
 
-Implementation agents should prefer Morph MCP `edit_file` (with `edit` fallback) for code changes. In planning outputs, reference concrete files and intended edits, not line-hash references.
+Implementation agents should use `edit` for code changes, with model-specific patch fallbacks when needed. In planning outputs, reference concrete files and intended edits, not line-hash references.
 
 You are a read-only agent — you do not write or edit files.
 
@@ -66,15 +65,14 @@ Use codebase-memory MCP tools first when planning:
 - `codebase-memory-mcp_trace_call_path` for dependency and impact analysis
 - `codebase-memory-mcp_get_code_snippet` to inspect exact implementation context
 
-This is preferred over warp_grep/warpgrep-style semantic discovery because graph-aware results surface structural context directly.
+This is preferred over generic text-only discovery because graph-aware results surface structural context directly. For public GitHub source research, use `gh_grep_searchGitHub`.
 
 Search fallback order:
 
 1. `codebase-memory-mcp_search_graph` + `codebase-memory-mcp_get_architecture` for graph-first discovery.
 2. `codebase-memory-mcp_trace_call_path` / `codebase-memory-mcp_get_code_snippet` for call-flow and source verification.
-3. `morph-mcp_codebase_search` if codebase-memory MCP is unavailable or the repository is not indexed yet.
-4. `read` to verify relevant source context.
-5. `grep` for exact symbol/literal checks when needed.
+3. `read` to verify relevant source context.
+4. `grep` for exact symbol/literal checks when needed.
 
 ## Command Output Compression
 
@@ -110,7 +108,8 @@ For external/library uncertainty, use the shared `ff-research-methods` skill dir
 ## Operating Mode
 
 - Prefer deterministic, structured output sections.
-- Use result-based orchestration (`{as:name}` and `$RESULT[name]`) for handoff.
+- Use normalized, resolved handoff context in stage transitions (summary, status, action items, open issues, and resolved prior output excerpts).
+- Never rely on unresolved placeholder aliases in handoff prompts.
 - Avoid writing intermediate plan files unless a user explicitly requests durable artifacts.
 
 ## Required Output Sections

package/agents/reviewing.md

@@ -20,7 +20,6 @@ tools:
   'codebase-memory-mcp_trace_call_path': true
   'codebase-memory-mcp_get_code_snippet': true
   'codebase-memory-mcp_search_code': true
-  'morph-mcp_codebase_search': true
 permission:
   skill:
     '*': allow
@@ -66,15 +65,14 @@ Use codebase-memory MCP tools first when reviewing:
 - `codebase-memory-mcp_trace_call_path` to verify security/validation coverage across call paths
 - `codebase-memory-mcp_get_code_snippet` to inspect concrete evidence for findings
 
-Prefer this over warp_grep/warpgrep-style search so findings are anchored to graph-aware dependencies, not isolated text matches.
+Prefer this over generic text-only search so findings are anchored to graph-aware dependencies, not isolated text matches. For public GitHub source checks, use `gh_grep_searchGitHub`.
 
 Search fallback order:
 
 1. `codebase-memory-mcp_search_graph` + `codebase-memory-mcp_get_architecture` for discovery and context.
 2. `codebase-memory-mcp_trace_call_path` / `codebase-memory-mcp_get_code_snippet` for evidence collection.
-3. `morph-mcp_codebase_search` if codebase-memory MCP is unavailable or not indexed.
-4. `read` to verify concrete evidence and line references.
-5. `grep` for exact symbol/literal checks when needed.
+3. `read` to verify concrete evidence and line references.
+4. `grep` for exact symbol/literal checks when needed.
 
 ## Command Output Compression
 
@@ -154,7 +152,8 @@ AUTO_HANDOFF=NO
 
 ## Operating Mode
 
-- Use result-based handoff (`$RESULT[...]`) rather than file-based artifacts.
+- Use normalized, resolved handoff context (summary/status/action items/issues plus resolved prior output excerpts) rather than file-based artifacts.
+- Never rely on unresolved placeholder aliases in handoff prompts.
 - Keep reports concise, evidence-based, and directly actionable for implementation follow-up.
 - Do not delegate to implementation stages from reviewing mode.
 - Never perform implementation or file-modifying work in reviewing mode.

package/bin/ff-deploy.js

@@ -52,13 +52,6 @@ const DEFAULT_MCP_SERVERS = {
       CONTEXT7_API_KEY: '{env:CONTEXT7_API_KEY}',
     },
   },
-  'morph-mcp': {
-    type: 'local',
-    command: ['npx', '-y', '@morphllm/morphmcp'],
-    environment: {
-      MORPH_API_KEY: '{env:MORPH_API_KEY}',
-    },
-  },
 };
 
 const DEFAULT_PLUGINS = [

package/dist/auto-handoff.js

@@ -1,22 +1,9 @@
 const SERVICE_NAME = 'feature-factory';
 const MAX_AUTO_HANDOFFS_PER_SESSION = 5;
-const AUTO_HANDOFF_FLAG_RE = /^AUTO_HANDOFF=(YES|NO)$/m;
-const AUTO_HANDOFF_TARGET_RE = /^AUTO_HANDOFF_TARGET=(feature-factory|building|documenting|reviewing)$/m;
-const AUTO_HANDOFF_REASON_RE = /^AUTO_HANDOFF_REASON=(CONTINUE_WORKFLOW|REWORK|DOCUMENT|REVIEW)$/m;
-const AUTO_HANDOFF_PROMPT_RE = /AUTO_HANDOFF_PROMPT<<FF_PROMPT\r?\n([\s\S]*?)\r?\nFF_PROMPT/m;
-function buildSubtaskDescription(reason) {
-    switch (reason) {
-        case 'REWORK':
-            return 'Apply review rework recommendations';
-        case 'DOCUMENT':
-            return 'Continue workflow documentation stage';
-        case 'REVIEW':
-            return 'Continue workflow review stage';
-        case 'CONTINUE_WORKFLOW':
-        default:
-            return 'Continue Feature Factory workflow';
-    }
-}
+const AUTO_HANDOFF_FLAG_RE = /^\s*AUTO_HANDOFF\s*=\s*(YES|NO)\s*$/im;
+const AUTO_HANDOFF_TARGET_RE = /^\s*AUTO_HANDOFF_TARGET\s*=\s*(feature-factory|building|documenting|reviewing)\s*$/im;
+const AUTO_HANDOFF_REASON_RE = /^\s*AUTO_HANDOFF_REASON\s*=\s*(CONTINUE_WORKFLOW|REWORK|DOCUMENT|REVIEW)\s*$/im;
+const AUTO_HANDOFF_PROMPT_RE = /^\s*(?:AUTO_HANDOFF_PROMPT|FF_PROMPT)\s*<<\s*FF_PROMPT\s*\r?\n([\s\S]*?)\r?\n\s*FF_PROMPT\s*$/im;
 async function log(client, level, message, extra) {
     try {
         await client.app.log({
@@ -51,27 +38,28 @@ function extractMessageText(info) {
         .join('');
 }
 export function parseAutoHandoff(text) {
-    const enabledMatch = text.match(AUTO_HANDOFF_FLAG_RE);
+    const normalizedText = text.replace(/\r\n/g, '\n');
+    const enabledMatch = normalizedText.match(AUTO_HANDOFF_FLAG_RE);
     if (!enabledMatch) {
         return null;
     }
-    const enabled = enabledMatch[1];
+    const enabled = enabledMatch[1]?.toUpperCase();
     if (enabled === 'NO') {
         return { enabled: false };
     }
-    const targetMatch = text.match(AUTO_HANDOFF_TARGET_RE);
-    const reasonMatch = text.match(AUTO_HANDOFF_REASON_RE);
-    const promptMatch = text.match(AUTO_HANDOFF_PROMPT_RE);
-    const target = targetMatch?.[1];
-    const reason = reasonMatch?.[1];
+    const targetMatch = normalizedText.match(AUTO_HANDOFF_TARGET_RE);
+    const reasonMatch = normalizedText.match(AUTO_HANDOFF_REASON_RE);
+    const promptMatch = normalizedText.match(AUTO_HANDOFF_PROMPT_RE);
+    const target = targetMatch?.[1]?.toLowerCase();
+    const reason = reasonMatch?.[1]?.toUpperCase();
     const prompt = promptMatch?.[1]?.trim();
     if (!target || !reason || !prompt) {
         return null;
     }
     return {
         enabled: true,
-        target: target,
-        reason: reason,
+        target,
+        reason,
         prompt,
     };
 }
@@ -180,12 +168,11 @@ export const AutoHandoffHooksPlugin = async ({ client }) => {
                 await client.session.prompt({
                     path: { id: dispatchSessionId },
                     body: {
+                        agent: parsed.target,
                         parts: [
                             {
-                                type: 'subtask',
-                                agent: parsed.target,
-                                description: buildSubtaskDescription(parsed.reason),
-                                prompt: parsed.prompt,
+                                type: 'text',
+                                text: parsed.prompt,
                             },
                         ],
                     },

package/dist/mcp-config.d.ts

@@ -26,13 +26,6 @@ export declare const DEFAULT_MCP_SERVERS: {
             readonly CONTEXT7_API_KEY: "{env:CONTEXT7_API_KEY}";
         };
     };
-    readonly 'morph-mcp': {
-        readonly type: "local";
-        readonly command: readonly ["npx", "-y", "@morphllm/morphmcp"];
-        readonly environment: {
-            readonly MORPH_API_KEY: "{env:MORPH_API_KEY}";
-        };
-    };
 };
 export interface MCPServerConfig {
     type: 'local' | 'remote';

package/dist/mcp-config.js

@@ -26,13 +26,6 @@ export const DEFAULT_MCP_SERVERS = {
             CONTEXT7_API_KEY: '{env:CONTEXT7_API_KEY}',
         },
     },
-    'morph-mcp': {
-        type: 'local',
-        command: ['npx', '-y', '@morphllm/morphmcp'],
-        environment: {
-            MORPH_API_KEY: '{env:MORPH_API_KEY}',
-        },
-    },
 };
 /**
  * Merge MCP servers, preserving existing servers and adding new ones.

package/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "@syntesseraai/opencode-feature-factory",
-  "version": "0.11.7",
+  "version": "0.11.9",
   "type": "module",
   "description": "OpenCode plugin for Feature Factory agents - provides sub-agents and skills for validation, review, security, and architecture assessment",
   "license": "MIT",

package/skills/ff-research-methods/SKILL.md

@@ -20,14 +20,13 @@ Use these tools directly when available in the active agent:
 - `jina-ai_parallel_search_web` / `jina-ai_parallel_read_url`
 - `context7_resolve-library-id` / `context7_query-docs`
 - `gh_grep_searchGitHub`
-- `morph-mcp_github_codebase_search`
 - `jina-ai_search_arxiv` / `jina-ai_search_ssrn`
 
 For local code context while researching implementation fit:
 
 - `codebase-memory-mcp_search_graph` + `codebase-memory-mcp_get_architecture`
 - `codebase-memory-mcp_trace_call_path` + `codebase-memory-mcp_get_code_snippet`
-- `morph-mcp_codebase_search` as local semantic fallback
+- `read` + `grep` as local fallback
 
 ## When to Use
 
@@ -96,7 +95,7 @@ Use `jina-ai_read_url` for:
 
 ### 4. Code Search (PROGRAMMING-SPECIFIC)
 
-Use `context7_query-docs` and `morph-mcp_github_codebase_search` for:
+Use `context7_query-docs` and `gh_grep_searchGitHub` for:
 
 - Finding library/SDK/API examples
 - Understanding implementation patterns