@rubytech/create-maxy-code 0.1.75 → 0.1.79

package/dist/__tests__/plugin-install.test.js

@@ -7,7 +7,7 @@ import assert from "node:assert/strict";
 import { parsePluginList, computeInstallActions, computeConfigureActions, parseExternalPlugins, } from "../lib/plugin-install.js";
 test("parsePluginList extracts name@marketplace tuples", () => {
     const stdout = `
-  ❯ tasks@maxy-platform
+  ❯ work@maxy-platform
     Version: 0.1.0
     Scope: local
 
@@ -16,7 +16,7 @@ test("parsePluginList extracts name@marketplace tuples", () => {
 `;
     const out = parsePluginList(stdout);
     assert.deepEqual(out, [
-        { name: "tasks", marketplace: "maxy-platform" },
+        { name: "work", marketplace: "maxy-platform" },
         { name: "telegram", marketplace: "claude-plugins-official" },
     ]);
 });

package/dist/lib/plugin-install.js

@@ -4,7 +4,7 @@
 // branches unit-testable without stubbing every shell invocation.
 /**
  * `claude plugin list` prints rows like:
- *   ❯ tasks@maxy-platform
+ *   ❯ work@maxy-platform
  *     Version: 0.1.0
  *     Scope: local
  *

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@rubytech/create-maxy-code",
-  "version": "0.1.75",
+  "version": "0.1.79",
   "description": "Install Maxy — AI for Productive People",
   "bin": {
     "create-maxy-code": "./dist/index.js"

package/payload/platform/config/brand.json

@@ -47,7 +47,7 @@
   },
 
   "plugins": {
-    "core": ["admin", "memory", "docs", "cloudflare", "anthropic", "workflows", "tasks", "scheduling", "email", "contacts", "projects"],
+    "core": ["admin", "memory", "docs", "cloudflare", "anthropic", "workflows", "work", "scheduling", "email", "contacts", "projects"],
     "defaultEnabled": ["business-assistant", "sales"],
     "available": ["telegram", "waitlist", "deep-research", "whatsapp", "replicate", "linkedin-import"],
     "excluded": []

package/payload/platform/lib/graph-write/dist/index.js

@@ -222,7 +222,7 @@ async function writeNodeWithEdges(params) {
                 .filter((m) => m !== null);
             if (matched.length === 0) {
                 process.stderr.write(`[graph-write] reject reason=missing-provenance labels=${labelCsv} agent=${agentLabel}\n`);
-                throw new Error(`missing-provenance: write to ${labelCsv} requires an inbound :PRODUCED edge from a :Task, :Conversation, or :Message (createdBy.agent='${agentLabel}'). Either pass producedByTaskId on the write (autonomous workflows: call task-create at the start of the flow and thread the returned taskId), or rely on the MCP wrapper's CONVERSATION_NODE_ID env-stamp injection (direct admin asks).`);
+                throw new Error(`missing-provenance: write to ${labelCsv} requires an inbound :PRODUCED edge from a :Task, :Conversation, or :Message (createdBy.agent='${agentLabel}'). Either pass producedByTaskId on the write (autonomous workflows: call work-create at the start of the flow and thread the returned taskId), or rely on the MCP wrapper's CONVERSATION_NODE_ID env-stamp injection (direct admin asks).`);
             }
             provenanceSourceId = matched[0].rel.targetNodeId;
             provenanceSourceLabel = matched[0].sourceLabel;

package/payload/platform/lib/graph-write/src/index.ts

@@ -300,7 +300,7 @@ export async function writeNodeWithEdges(
           `[graph-write] reject reason=missing-provenance labels=${labelCsv} agent=${agentLabel}\n`
         );
         throw new Error(
-          `missing-provenance: write to ${labelCsv} requires an inbound :PRODUCED edge from a :Task, :Conversation, or :Message (createdBy.agent='${agentLabel}'). Either pass producedByTaskId on the write (autonomous workflows: call task-create at the start of the flow and thread the returned taskId), or rely on the MCP wrapper's CONVERSATION_NODE_ID env-stamp injection (direct admin asks).`
+          `missing-provenance: write to ${labelCsv} requires an inbound :PRODUCED edge from a :Task, :Conversation, or :Message (createdBy.agent='${agentLabel}'). Either pass producedByTaskId on the write (autonomous workflows: call work-create at the start of the flow and thread the returned taskId), or rely on the MCP wrapper's CONVERSATION_NODE_ID env-stamp injection (direct admin asks).`
         );
       }
       provenanceSourceId = matched[0].rel.targetNodeId;

package/payload/platform/package.json

@@ -13,7 +13,7 @@
     "build:telegram": "tsc -p plugins/telegram/mcp/tsconfig.json",
     "build:admin": "tsc -p plugins/admin/mcp/tsconfig.json",
     "build:cloudflare": "tsc -p plugins/cloudflare/mcp/tsconfig.json",
-    "build:tasks": "tsc -p plugins/tasks/mcp/tsconfig.json",
+    "build:work": "tsc -p plugins/work/mcp/tsconfig.json",
     "build:email": "tsc -p plugins/email/mcp/tsconfig.json",
     "build:outlook": "tsc -p plugins/outlook/mcp/tsconfig.json",
     "build:workflows": "tsc -p plugins/workflows/mcp/tsconfig.json",

package/payload/platform/plugins/.claude-plugin/marketplace.json

@@ -1,14 +1,114 @@
 {
-  "name": "maxy-premium",
+  "name": "maxy-platform",
   "owner": {
     "name": "Rubytech LLC"
   },
   "plugins": [
+    {
+      "name": "admin",
+      "source": "./admin",
+      "version": "0.1.0"
+    },
+    {
+      "name": "business-assistant",
+      "source": "./business-assistant",
+      "version": "0.1.0"
+    },
+    {
+      "name": "cloudflare",
+      "source": "./cloudflare",
+      "version": "0.1.0"
+    },
+    {
+      "name": "contacts",
+      "source": "./contacts",
+      "version": "0.1.0"
+    },
+    {
+      "name": "deep-research",
+      "source": "./deep-research",
+      "version": "0.1.0"
+    },
+    {
+      "name": "docs",
+      "source": "./docs",
+      "version": "0.1.0"
+    },
+    {
+      "name": "email",
+      "source": "./email",
+      "version": "0.1.0"
+    },
+    {
+      "name": "linkedin-import",
+      "source": "./linkedin-import",
+      "version": "0.1.0"
+    },
+    {
+      "name": "memory",
+      "source": "./memory",
+      "version": "0.1.0"
+    },
+    {
+      "name": "outlook",
+      "source": "./outlook",
+      "version": "0.1.0"
+    },
+    {
+      "name": "projects",
+      "source": "./projects",
+      "version": "0.1.0"
+    },
+    {
+      "name": "replicate",
+      "source": "./replicate",
+      "version": "0.1.0"
+    },
+    {
+      "name": "sales",
+      "source": "./sales",
+      "version": "0.1.0"
+    },
+    {
+      "name": "scheduling",
+      "source": "./scheduling",
+      "version": "0.1.0"
+    },
+    {
+      "name": "tasks",
+      "source": "./tasks",
+      "version": "0.1.0"
+    },
     {
       "name": "teaching",
       "source": "./teaching",
       "version": "0.1.0"
     },
+    {
+      "name": "telegram",
+      "source": "./telegram",
+      "version": "0.1.0"
+    },
+    {
+      "name": "waitlist",
+      "source": "./waitlist",
+      "version": "0.1.0"
+    },
+    {
+      "name": "whatsapp",
+      "source": "./whatsapp",
+      "version": "0.1.0"
+    },
+    {
+      "name": "work",
+      "source": "./work",
+      "version": "0.1.0"
+    },
+    {
+      "name": "workflows",
+      "source": "./workflows",
+      "version": "0.1.0"
+    },
     {
       "name": "writer-craft",
       "source": "./writer-craft",

package/payload/platform/plugins/admin/mcp/dist/index.js

@@ -1759,7 +1759,7 @@ eagerTool(server, "skill-load", "Load a plugin skill's SKILL.md body by skill na
         if (requiredInputs) {
             const slotLabels = requiredInputs.map(s => s.join(" | ")).join(", ");
             const marker = JSON.stringify(requiredInputs);
-            const notice = `<!-- skill-input-contract requiredInputs=${marker} -->\nREQUIRED INPUTS: ${slotLabels}\nIf the operator has not supplied each of these inputs, your next tool call MUST be AskUserQuestion. Do not use memory-search, conversation-search, graph-read, or task-get to guess the missing input.\n<!-- /skill-input-contract -->\n\n`;
+            const notice = `<!-- skill-input-contract requiredInputs=${marker} -->\nREQUIRED INPUTS: ${slotLabels}\nIf the operator has not supplied each of these inputs, your next tool call MUST be AskUserQuestion. Do not use memory-search, conversation-search, graph-read, or work-get to guess the missing input.\n<!-- /skill-input-contract -->\n\n`;
             bodyOut = notice + content;
         }
         const ms = Date.now() - start;

package/payload/platform/plugins/admin/skills/commitment-followthrough/SKILL.md

@@ -39,7 +39,7 @@ Rule 1 is yours; rule 2 is this skill's job.
 Use the most appropriate tool:
 
 - `schedule-event` for time-bound reminders (every Monday, on Tuesday, by Friday).
-- `task-create` for open-ended obligations (chase X, finish Y, prepare Z).
+- `work-create` for open-ended obligations (chase X, finish Y, prepare Z).
 - `workflow-create` for multi-step processes that recur (monthly close-out, new-instruction onboarding).
 
 ## Verify executor capabilities before promising a workflow

package/payload/platform/plugins/admin/skills/session-management/SKILL.md

@@ -20,7 +20,7 @@ This skill wraps the session tools and carries the discipline that keeps long-ru
 
 When the owner asks to start a new session, clear the conversation, or reset, call `session-reset`. Do not ask for confirmation. After the tool call, say nothing further; the UI clears and returns to idle.
 
-**Before suggesting a reset (e.g. after a plugin activation, when context has drifted), persist every actionable finding from the current conversation to its durable store first.** Compaction saves a session summary, but summaries are lossy: decisions, working state, and unfinished threads must be captured explicitly before the context window is cleared. Write open tasks via `task-create`, profile updates via `profile-update`, and any other graph state. Then tell the owner what will carry into the new session (the summary and the open tasks via `<previous-context>`) and suggest the reset.
+**Before suggesting a reset (e.g. after a plugin activation, when context has drifted), persist every actionable finding from the current conversation to its durable store first.** Compaction saves a session summary, but summaries are lossy: decisions, working state, and unfinished threads must be captured explicitly before the context window is cleared. Write open tasks via `work-create`, profile updates via `profile-update`, and any other graph state. Then tell the owner what will carry into the new session (the summary and the open tasks via `<previous-context>`) and suggest the reset.
 
 ## Continuing a previous session
 

package/payload/platform/plugins/business-assistant/PLUGIN.md

@@ -39,7 +39,7 @@ Every conversation is a session. At the start of each session:
 3. Call `session-name` with the current `sessionKey` and a short label once the session's purpose is clear
 4. Surface any open tasks to the owner before asking what's new
 
-When the owner asks about sessions, tasks, or what's in progress — use `session-list` and `task-list`.
+When the owner asks about sessions, tasks, or what's in progress — use `session-list` and `work-list`.
 
 ## Industry Overlays
 

package/payload/platform/plugins/business-assistant/references/task-management.md

@@ -37,10 +37,10 @@ Do not create tasks for simple one-turn exchanges (answering a question, looking
 
 ### Creating a task
 
-Use `task-create`. Always pass `sessionKey` (from your system prompt — "Current session key: ...") to link the task to the current conversation automatically:
+Use `work-create`. Always pass `sessionKey` (from your system prompt — "Current session key: ...") to link the task to the current conversation automatically:
 
 ```
-task-create {
+work-create {
   name: "Telegram setup",
   description: "Configure Telegram bot and webhook for the business",
   status: "active",
@@ -51,10 +51,10 @@ task-create {
 
 ### Updating a task
 
-Use `task-update` to change name, description, status, priority, due date, or append a progress note:
+Use `work-update` to change name, description, status, priority, due date, or append a progress note:
 
 ```
-task-update {
+work-update {
   taskId: "<id>",
   name: "Corrected task name",
   note: "Renamed to reflect actual scope"
@@ -62,7 +62,7 @@ task-update {
 ```
 
 ```
-task-update {
+work-update {
   taskId: "<id>",
   status: "completed",
   note: "Webhook configured and verified"
@@ -73,10 +73,10 @@ Notes are append-only — never overwritten. Name and description changes preser
 
 ### Completing a task
 
-Use `task-complete` as a shorthand — it sets status to `completed` and appends a closing note:
+Use `work-complete` as a shorthand — it sets status to `completed` and appends a closing note:
 
 ```
-task-complete {
+work-complete {
   taskId: "<id>",
   note: "Telegram bot live, webhook responding"
 }
@@ -131,14 +131,14 @@ Returns recent conversations with their names, session keys, and any linked task
 ### List open tasks
 
 ```
-task-list { status: "active" }
-task-list { status: "pending" }
+work-list { status: "active" }
+work-list { status: "pending" }
 ```
 
 ### Get a specific task
 
 ```
-task-get { taskId: "<id>" }
+work-get { taskId: "<id>" }
 ```
 
 ---
@@ -147,10 +147,10 @@ task-get { taskId: "<id>" }
 
 If a user returns to work on a previous task:
 1. Call `session-list` to find the original session and task
-2. Call `task-update` to set `status: "active"` and note the resumption
-3. Pass `sessionKey` in `task-create` for any new tasks in the new session — it links them to the current conversation automatically
+2. Call `work-update` to set `status: "active"` and note the resumption
+3. Pass `sessionKey` in `work-create` for any new tasks in the new session — it links them to the current conversation automatically
 
-A task can span multiple sessions. Use `task-create` with `sessionKey` each time work resumes in a new conversation.
+A task can span multiple sessions. Use `work-create` with `sessionKey` each time work resumes in a new conversation.
 
 ---
 

package/payload/platform/plugins/docs/references/admin-session.md

@@ -119,18 +119,19 @@ The hook emits two summary lines per fire immediately before `spawn-request`:
 - `[turn-recorder] envelope sessionId=<op> turnsCount=<n> userTurns=<n> assistantTurns=<n> toolCallTurns=<n>` — the walker's output. `turnsCount` is monotone across spawns in the same operator session; a flat or decreasing series is the regression signature for "windowing crept back in".
 - `[turn-recorder] substitution sessionId=<op> schemaBytes=<n> conversationBytes=<n> bodyBytes=<n>` — the per-spawn substitution. `schemaBytes` covers schema-base plus any vertical concatenated. `bodyBytes` equals the trailing `initialMessageBytes` field on the next `spawn-request` line — the two log lines read the same number.
 
-**Manager-side specialist branches.** The recorder is the first specialist subagent that exercises the full specialist flag matrix:
+**Manager-side specialist branches (post-Task-207).** The recorder is the first specialist subagent that exercises the full specialist flag matrix:
 - The bundled `platform/templates/specialists/agents/database-operator.md` template is symlinked into `$CLAUDE_CONFIG_DIR/agents/database-operator.md` by the installer; without that link `claude --agent database-operator` silently falls back to the admin agent.
 - `--append-system-prompt` is omitted entirely — the agent file IS the prompt; admin IDENTITY / SOUL / aboutOwner do NOT layer on top.
-- `--allowed-tools` is sourced from the agent's frontmatter `tools:` list (11 entries for the recorder), not the admin surface.
-- The per-spawn `mcp.json` is narrowed to only `memory`, `contacts`, `tasks` — the plugins whose tools the agent's frontmatter names.
+- `--allowed-tools` is **not** pushed to argv. `--agent <name>` resolves the agent file's `tools:` frontmatter natively against Claude Code's plugin-tool registry; the argv push (Task 165) was empirically redundant and namespace-broke after Task 203's `mcp__plugin_…` rename (Task 207).
+- The per-spawn `mcp.json` is **not** written and `--mcp-config` is **not** pushed. Plugin manifests register the MCPs at session start (Tasks 202+203). The per-account env that the JSON used to inject (`ACCOUNT_ID`, `USER_ID`, `NEO4J_URI`, `NEO4J_PASSWORD`, `PLATFORM_ROOT`, `CLAUDE_CONFIG_DIR`) now rides the PTY env block directly — see [`mcp-servers.md`](mcp-servers.md) §3 (Task 207).
+- `--permission-mode bypassPermissions` is auto-pushed when the caller has not set `permissionMode`. Headless specialists have no operator to consent to write tools; default mode blocks them (Task 207).
 - `--remote-control` is **not** attached and the URL-capture handler is not registered. Remote Control is channel-facing only; the recorder has no human in the loop, so no `claude.ai/code/session_<id>` URL is ever emitted and the per-byte URL regex consumes no PTY output. The spawn log line carries `remoteControl=false`. Channel-facing specialists (content-producer, librarian, personal-assistant, project-manager, research-assistant) keep `--remote-control`; only specialists named in `HEADLESS_ROLES` (`database-operator`, `memory-classify`, `commitment`, `classifier`) drop it.
 
 **End-of-turn auto-archive.** When any session whose specialist is `database-operator` gains an assistant message with `stop_reason: "end_turn"` in its JSONL, the manager posts `/<sid>/stop` against itself, claude exits, the fs-watcher observes the PID-file removal and drops the row from the index. The auto-archive log line is `auto-archive sessionId=<sid> specialist=database-operator reason=end-turn …`. Every operator-request stop (auto-archive included) now ends in `master-fd=closed` because `stopSession()` calls `pty.destroy()` explicitly before `store.remove` (Task 170 — see `platform.md` "stopSession fd contract" for the failure mode this closes).
 
 **Hook recursion gate.** `pty-spawner` stamps `MAXY_SPECIALIST=<specialist>` on every PTY env. The Stop hook short-circuits when `MAXY_SPECIALIST=database-operator` so the recorder's own end-of-turn does not re-fire the hook.
 
-**Observability.** The hook emits exactly two lines per operator turn via `/api/admin/log-ingest`: `[turn-recorder] trigger sessionId=<op> turnIndex=0 transcriptBytes=<n> conversationBytes=<n>` and `[turn-recorder] spawn-request sessionId=<op> specialist=database-operator initialMessageBytes=<n>`. The manager adds `pty-spawn-allowlist specialist=database-operator count=11 stripped=0 sourced-from=agent-frontmatter`, `pty-spawn-start … specialist=database-operator append-system-prompt-bytes=0` before the PTY launches, and one `[pty-spawn-tool-inventory] sessionId=<rec> specialist=database-operator argv-tools=<n> mcp-listed-tools=<n> exposed=<csv> not-exposed=<csv>` line per spawn once the shadow probe of each MCP server returns. The remainder of the recorder lifecycle is covered by the Sidebar's existing lines (`pty-spawned`, JSONL events, `auto-archive`). Failure-mode names: `trigger-skipped reason=…` enumerates `role-not-admin | is-recorder | empty-stdin | missing-transcript | conversation-empty`. Hook-side spawn errors emit `[turn-recorder] spawn-failed reason=loopback-http http=<code>`. Probe-side failure on the inventory line emits `[pty-spawn-tool-inventory-failed] sessionId=<rec> specialist=<name> err=<json>`.
+**Observability (post-Task-207).** The hook emits exactly two lines per operator turn via `/api/admin/log-ingest`: `[turn-recorder] trigger sessionId=<op> turnIndex=0 transcriptBytes=<n> conversationBytes=<n>` and `[turn-recorder] spawn-request sessionId=<op> specialist=database-operator initialMessageBytes=<n>`. The manager adds `pty-spawn-allowlist specialist=database-operator source=native-agent-flag count=skipped stripped=0`, `pty-spawn-mcp-config specialist=database-operator source=plugin-manifests`, `pty-spawn-start … specialist=database-operator append-system-prompt-bytes=0 env-keys=ACCOUNT_ID,USER_ID,PLATFORM_ROOT,CLAUDE_CONFIG_DIR,NEO4J_URI,NEO4J_PASSWORD` before the PTY launches, and one `[pty-spawn-tool-inventory] sessionId=<rec> specialist=database-operator argv-tools=0 mcp-listed-tools=<n> exposed=<csv> not-exposed=<csv>` line per spawn once the shadow probe of each MCP server returns. The remainder of the recorder lifecycle is covered by the Sidebar's existing lines (`pty-spawned`, JSONL events, `auto-archive`). Failure-mode names: `trigger-skipped reason=…` enumerates `role-not-admin | is-recorder | empty-stdin | missing-transcript | conversation-empty`. Hook-side spawn errors emit `[turn-recorder] spawn-failed reason=loopback-http http=<code>`. Probe-side failure on the inventory line emits `[pty-spawn-tool-inventory-failed] sessionId=<rec> specialist=<name> err=<json>`.
 
 ### Recorder lifecycle diagnostic
 
@@ -139,8 +140,8 @@ When the operator reports "the recorder did nothing this turn", run these seven
 1. **Stop hook fired.** `grep '\[turn-recorder\] trigger sessionId=<op>' ~/.<brand>/logs/server.log` — expects one line of shape `[turn-recorder] trigger sessionId=<op> turnIndex=0 transcriptBytes=<n> conversationBytes=<n>`. Absent: the Stop hook didn't run; check that `MAXY_SESSION_ROLE=admin` was set on the operator PTY and that `MAXY_SPECIALIST!=database-operator` (recursion gate).
 2. **/spawn accepted.** `grep '\[turn-recorder\] spawn-request sessionId=<op>' ~/.<brand>/logs/server.log` — expects `[turn-recorder] spawn-request sessionId=<op> specialist=database-operator initialMessageBytes=<n>`. The response body of this POST carries `<rec>`. Absent: the hook fired but `/api/admin/claude-sessions` rejected; look for `[turn-recorder] spawn-failed reason=loopback-http http=<code>` on the next line.
 3. **PTY started.** `grep 'pty-spawn-start .* specialist=database-operator' ~/.<brand>/logs/server.log` — expects `pty-spawn-start claudeBin=<…> argv-count=<n> append-system-prompt-bytes=0 … specialist=database-operator prompt-positional=yes prompt-bytes=<n>`. Absent: the wrapper accepted but the manager rejected before exec; check the spawn-failure surfaces (`which-claude-not-found | pty-spawn-failed | pid-file-timeout | host-context-unresolved | identity-unresolved | mcp-config-write-failed`).
-4. **Agent file resolved.** `grep 'pty-spawn-allowlist specialist=database-operator count=11 stripped=0 sourced-from=agent-frontmatter' ~/.<brand>/logs/server.log` — expects exactly one line per recorder spawn. Absent (or `count` not equal to the frontmatter's tool count, or `stripped>0` meaning the brand excluded a plugin the recorder template references — Task 173): the agent file at `$CLAUDE_CONFIG_DIR/agents/database-operator.md` is missing the `tools:` line, the symlink the installer creates never landed, or the brand-aware drift filter dropped tools. Re-run the installer; cross-reference `brand.json#plugins.excluded` against the agent frontmatter.
-4b. **Tool inventory exposed to the model.** `grep '\[pty-spawn-tool-inventory\] sessionId=<rec>' ~/.<brand>/logs/server.log` — expects one line of shape `[pty-spawn-tool-inventory] sessionId=<rec> specialist=database-operator argv-tools=11 mcp-listed-tools=<n> exposed=<csv> not-exposed=<csv>`. The line lands once per spawn after the manager's shadow probe finishes a `tools/list` against each MCP server in the per-spawn `mcp.json`. The four fields decode the recorder's runtime tool surface directly: `argv-tools` is the allowlist on the `claude` argv (= phase 4's `count`); `mcp-listed-tools` is the sum across servers of names the probe captured; `exposed` is the intersection (in frontmatter order); `not-exposed` is the allowlist minus `exposed`. The regression query for "model says no tools" is `exposed=$|exposed= ` — when the line ends `exposed= not-exposed=<all 11>`, the allowlist landed on the argv but none of the names came back from any MCP server (cause space: frontmatter format, name canonicalisation, MCP handshake repair). Absent line: probe is fire-and-forget, so absence either means the spawn was not a specialist (operator chat) or the probe itself crashed — in which case `[pty-spawn-tool-inventory-failed] sessionId=<rec> specialist=… err=…` is the partner line to grep. Note: the probe captures what each MCP server offers, not what claude code's own tools/list saw — CLI-side filtering after handshake is a separate observability concern.
+4. **Agent file resolved.** `grep 'pty-spawn-allowlist specialist=database-operator source=native-agent-flag' ~/.<brand>/logs/server.log` — expects exactly one line per recorder spawn of shape `pty-spawn-allowlist specialist=database-operator source=native-agent-flag count=skipped stripped=<n>`. `count=skipped` is structural: post-Task-207 the agent file's `tools:` frontmatter is resolved natively by `--agent`, never re-stamped onto argv. `stripped>0` means the brand-aware drift filter (Task 173) dropped tools from the agent's declared set. Absent line: the agent file at `$CLAUDE_CONFIG_DIR/agents/database-operator.md` is missing the `tools:` line, or the symlink the installer creates never landed. Re-run the installer; cross-reference `brand.json#plugins.excluded` against the agent frontmatter.
+4b. **Tool inventory exposed to the model.** `grep '\[pty-spawn-tool-inventory\] sessionId=<rec>' ~/.<brand>/logs/server.log` — expects one line of shape `[pty-spawn-tool-inventory] sessionId=<rec> specialist=database-operator argv-tools=0 mcp-listed-tools=<n> exposed=<csv> not-exposed=<csv>`. The line lands once per spawn after the manager's shadow probe finishes a `tools/list` against each MCP server referenced by the agent's frontmatter (descriptors re-sourced from `deps.toolSurface.mcpServers` post-Task-207). The four fields decode the recorder's runtime tool surface directly: `argv-tools=0` is the literal truth — specialists no longer push `--allowed-tools` (Task 207); `mcp-listed-tools` is the sum across servers of names the probe captured; `exposed` is the intersection (in frontmatter order); `not-exposed` is the frontmatter list minus `exposed`. The regression query for "model says no tools" is `mcp-listed-tools=0` — that means registry #1 lost the platform plugins again (re-check the Task 203 marketplace-manifest gate). Absent line: probe is fire-and-forget, so absence either means the spawn was not a specialist (operator chat) or the probe itself crashed — in which case `[pty-spawn-tool-inventory-failed] sessionId=<rec> specialist=… err=…` is the partner line to grep.
 5. **Graph write outcome.** `grep '\[mcp:memory\] memory-write .* session=<rec>' ~/.<brand>/logs/server.log` — expects one line ending `result=ok elementId=<id>` or `result=error reason=<slug>` (slug enumerated by the memory MCP write-path observability work). Absent: the recorder loaded but produced no tool calls — model-side decision, not infra. Read the recorder JSONL at `<accountDir>/.claude/projects/<slug>/<rec>.jsonl` to see what the LLM did.
 6. **Auto-archive.** `grep 'auto-archive .* sessionId=<rec> .* specialist=database-operator reason=end-turn' ~/.<brand>/logs/server.log` — expects one line. Absent: the recorder finished but the manager's end-turn watcher didn't fire; the fs-watcher row will get reaped on its TTL but the recorder hung longer than expected. Investigate `pty-spawn-stop` and `pid-file-removed` lines on the same `<rec>`.
 

package/payload/platform/plugins/docs/references/internals.md

@@ -541,9 +541,9 @@ Every durable action — cloudflare tunnel-login, brand publish, future determin
 
 The doctrine is enforced at the storage primitive: writes to `:Person`, `:UserProfile`, `:AdminUser`, `:Organization`, `:LocalBusiness`, `:CloudflareTunnel`, or `:CloudflareHostname` MUST include at least one inbound `:PRODUCED` edge whose source is one of `:Task`, `:Conversation`, or `:Message`. Subtype labels like `:AdminConversation`, `:UserMessage`, `:AssistantMessage`, `:AdminMessage` qualify because the gate checks the full `labels()` array. Bootstrap writes (PIN-setup, schema migrations, lazy first-session UserProfile creation) are exempt via `createdBy.agent === 'system'`.
 
-Two surfaces emit the lifecycle: agent-driven actions call `task-create`/`task-update`/`task-complete` over MCP (`task-create` accepts `kind`, the canonical `inputsProvided` call-shape record, `inputs` + `inputSchema` for the operator-meaningful form payload, and `raisedDuringConversationKey` to resolve the `RAISED_DURING` edge). Shell-driven actions wrap their script invocation in [platform/ui/app/lib/cloudflare-task-tracker.ts](../../../ui/app/lib/cloudflare-task-tracker.ts) (cloudflare is the first; installer / brand-publish / OAuth-login deferred). Both surfaces emit the same `[task] action-start|step|done` log lines so operators can grep one channel uniformly. Both also call the central `redactSecrets` primitive ([platform/lib/task-secrets/](../../../lib/task-secrets/)) to strip schema-tagged secret keys before persisting `inputs.<field>` props on the Task — see `.docs/neo4j.md § Audit Task input contract` for the contract that replaces per-kind allow-lists.
+Two surfaces emit the lifecycle: agent-driven actions call `work-create`/`work-update`/`work-complete` over MCP (`work-create` accepts `kind`, the canonical `inputsProvided` call-shape record, `inputs` + `inputSchema` for the operator-meaningful form payload, and `raisedDuringConversationKey` to resolve the `RAISED_DURING` edge). Shell-driven actions wrap their script invocation in [platform/ui/app/lib/cloudflare-task-tracker.ts](../../../ui/app/lib/cloudflare-task-tracker.ts) (cloudflare is the first; installer / brand-publish / OAuth-login deferred). Both surfaces emit the same `[task] action-start|step|done` log lines so operators can grep one channel uniformly. Both also call the central `redactSecrets` primitive ([platform/lib/task-secrets/](../../../lib/task-secrets/)) to strip schema-tagged secret keys before persisting `inputs.<field>` props on the Task — see `.docs/neo4j.md § Audit Task input contract` for the contract that replaces per-kind allow-lists.
 
-Two surfaces feed the gate. (1) **Workflow path:** `memory-write` accepts an optional `producedByTaskId` parameter. When set, an inbound `:PRODUCED` edge from that Task is composed into the write's relationships before the gate runs — the typical agent-side pattern is to call `task-create` at the start of an autonomous flow, capture `taskId`, and pass it as `producedByTaskId` on every subsequent `memory-write` for a gated label. The gate verifies Task and write share the same `accountId`; mismatch is rejected loud. (2) **Direct-ask path:** the admin server resolves the active `:AdminConversation` elementId at MCP spawn time and stamps it as `CONVERSATION_NODE_ID` in the env. The `contact-create` and `memory-write` wrappers call `injectConversationProvenance` (exported from [`@maxy/graph-write`](../../../lib/graph-write/src/conversation-provenance.ts)) which verifies `accountId` parity and prepends the synthetic `:PRODUCED` edge — no agent-visible schema field changes. `memory-write` uses the env-stamp only as a fallback when `producedByTaskId` is unset; `contact-create` has no `producedByTaskId` parameter today and relies on the env-stamp alone.
+Two surfaces feed the gate. (1) **Workflow path:** `memory-write` accepts an optional `producedByTaskId` parameter. When set, an inbound `:PRODUCED` edge from that Task is composed into the write's relationships before the gate runs — the typical agent-side pattern is to call `work-create` at the start of an autonomous flow, capture `taskId`, and pass it as `producedByTaskId` on every subsequent `memory-write` for a gated label. The gate verifies Task and write share the same `accountId`; mismatch is rejected loud. (2) **Direct-ask path:** the admin server resolves the active `:AdminConversation` elementId at MCP spawn time and stamps it as `CONVERSATION_NODE_ID` in the env. The `contact-create` and `memory-write` wrappers call `injectConversationProvenance` (exported from [`@maxy/graph-write`](../../../lib/graph-write/src/conversation-provenance.ts)) which verifies `accountId` parity and prepends the synthetic `:PRODUCED` edge — no agent-visible schema field changes. `memory-write` uses the env-stamp only as a fallback when `producedByTaskId` is unset; `contact-create` has no `producedByTaskId` parameter today and relies on the env-stamp alone.
 
 Operator audit cyphers:
 - "What entities did this conversation's actions produce?" — `MATCH (c:AdminConversation {conversationId:$id})<-[:RAISED_DURING]-(t:Task)-[:PRODUCED]->(e) RETURN labels(e), e.name, t.kind, t.status`

package/payload/platform/plugins/memory/PLUGIN.md

@@ -140,7 +140,7 @@ Every node in the graph sits under a parent in the canonical chain `LocalBusines
 
 Writes targeting `:Person`, `:UserProfile`, `:AdminUser`, `:Organization`, `:LocalBusiness`, `:CloudflareTunnel`, or `:CloudflareHostname` require an inbound `:PRODUCED` edge whose source is one of `:Task`, `:Conversation`, or `:Message` (deterministic bootstrap paths run as `createdBy.agent === 'system'` and are exempt). Two surfaces feed the gate:
 
-- **Workflow path — `producedByTaskId`.** `memory-write` accepts an optional `producedByTaskId` parameter. When set, the platform composes an inbound `:PRODUCED` edge from that `:Task` node into the write's `relationships` array before the write runs. The Task and the new node must share the same `accountId`; mismatch is rejected loud. The typical pattern: call `task-create` at the start of an autonomous flow (onboarding skill, cloudflare tunnel-login) with `kind` and `raisedDuringConversationKey`; capture the returned `taskId`; pass it as `producedByTaskId` on every subsequent `memory-write` for one of the gated labels.
+- **Workflow path — `producedByTaskId`.** `memory-write` accepts an optional `producedByTaskId` parameter. When set, the platform composes an inbound `:PRODUCED` edge from that `:Task` node into the write's `relationships` array before the write runs. The Task and the new node must share the same `accountId`; mismatch is rejected loud. The typical pattern: call `work-create` at the start of an autonomous flow (onboarding skill, cloudflare tunnel-login) with `kind` and `raisedDuringConversationKey`; capture the returned `taskId`; pass it as `producedByTaskId` on every subsequent `memory-write` for one of the gated labels.
 
 - **Direct-ask path — `CONVERSATION_NODE_ID` env-stamp.** When `producedByTaskId` is not provided (typical of direct admin asks like "add Anneke as person"), `memory-write` falls back to the `CONVERSATION_NODE_ID` env var that the admin server stamps at MCP spawn time. The value is the elementId of the active `:AdminConversation`. The wrapper verifies `accountId` parity before injecting the synthetic `:PRODUCED` edge — `accountId` mismatch is logged as `[mcp:memory] [provenance-missing] reason=account-mismatch` and the gate then fires `missing-provenance`. The env-stamp is invisible to the agent (no schema field changes); the LLM never decides whether to use it.
 

package/payload/platform/plugins/memory/mcp/dist/lib/__tests__/neo4j-password-path.test.d.ts

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=neo4j-password-path.test.d.ts.map

package/payload/platform/plugins/memory/mcp/dist/lib/__tests__/neo4j-password-path.test.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"neo4j-password-path.test.d.ts","sourceRoot":"","sources":["../../../src/lib/__tests__/neo4j-password-path.test.ts"],"names":[],"mappings":""}

package/payload/platform/plugins/memory/mcp/dist/lib/__tests__/neo4j-password-path.test.js

@@ -0,0 +1,57 @@
+import { afterEach, beforeEach, describe, expect, it } from "vitest";
+import { existsSync, mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
+import { join, resolve } from "node:path";
+import { tmpdir } from "node:os";
+// Task 207 — `readPassword()` (memory plugin) falls back to a
+// `<platformRoot>/config/.neo4j-password` lookup when neither
+// `NEO4J_PASSWORD` nor `PLATFORM_ROOT` is set in env. Before this task,
+// the fallback's `../../../..` math from `dist/lib/neo4j.js` landed at
+// `platform/plugins/` (one level too high), so the read failed silently
+// while the per-spawn `.mcp.json` masked the bug by always injecting
+// `PLATFORM_ROOT`. With Task 207 dropping the per-spawn JSON for
+// specialists, this fallback is the new load-bearing path; the path
+// math is `../../../../..` (five up).
+//
+// This test verifies the resolved path lands at `<platformRoot>/config/`,
+// not `<platformRoot>/plugins/config/`, by walking the same number of
+// segments up from a fixture directory shaped like the dist layout.
+describe("Task 207 — readPassword fallback path math", () => {
+    let tmpRoot = "";
+    const originalEnv = { ...process.env };
+    beforeEach(() => {
+        tmpRoot = mkdtempSync(join(tmpdir(), "task207-neo4j-path-"));
+        delete process.env.NEO4J_PASSWORD;
+        delete process.env.PLATFORM_ROOT;
+    });
+    afterEach(() => {
+        process.env = { ...originalEnv };
+        if (tmpRoot)
+            rmSync(tmpRoot, { recursive: true, force: true });
+    });
+    it("five-segment hop from dist/lib/neo4j.js lands at platform/config/.neo4j-password", () => {
+        // Layout mirrors the compiled tree:
+        //   <tmpRoot>/platform/config/.neo4j-password
+        //   <tmpRoot>/platform/plugins/memory/mcp/dist/lib/neo4j.js
+        const platformRoot = join(tmpRoot, "platform");
+        mkdirSync(join(platformRoot, "config"), { recursive: true });
+        writeFileSync(join(platformRoot, "config", ".neo4j-password"), "secret-from-file\n", "utf-8");
+        // Simulate the source-of-truth math: import.meta.dirname is the
+        // directory of the compiled neo4j.js. Five segments up is platform/.
+        const distLibDir = join(platformRoot, "plugins", "memory", "mcp", "dist", "lib");
+        mkdirSync(distLibDir, { recursive: true });
+        const resolved = resolve(distLibDir, "../../../../..", "config/.neo4j-password");
+        expect(resolved).toBe(join(platformRoot, "config/.neo4j-password"));
+        expect(readFileSync(resolved, "utf-8").trim()).toBe("secret-from-file");
+    });
+    it("four-segment hop lands at platform/plugins/ which has no .neo4j-password — proves the regression case", () => {
+        const platformRoot = join(tmpRoot, "platform");
+        mkdirSync(join(platformRoot, "config"), { recursive: true });
+        writeFileSync(join(platformRoot, "config", ".neo4j-password"), "secret\n", "utf-8");
+        const distLibDir = join(platformRoot, "plugins", "memory", "mcp", "dist", "lib");
+        mkdirSync(distLibDir, { recursive: true });
+        const wrong = resolve(distLibDir, "../../../..", "config/.neo4j-password");
+        expect(wrong).toBe(join(platformRoot, "plugins", "config", ".neo4j-password"));
+        expect(existsSync(wrong)).toBe(false);
+    });
+});
+//# sourceMappingURL=neo4j-password-path.test.js.map

package/payload/platform/plugins/memory/mcp/dist/lib/__tests__/neo4j-password-path.test.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"neo4j-password-path.test.js","sourceRoot":"","sources":["../../../src/lib/__tests__/neo4j-password-path.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,UAAU,EAAE,QAAQ,EAAE,MAAM,EAAE,EAAE,EAAE,MAAM,QAAQ,CAAC;AACrE,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,WAAW,EAAE,YAAY,EAAE,MAAM,EAAE,aAAa,EAAE,MAAM,SAAS,CAAC;AAClG,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAC1C,OAAO,EAAE,MAAM,EAAE,MAAM,SAAS,CAAC;AAEjC,8DAA8D;AAC9D,8DAA8D;AAC9D,wEAAwE;AACxE,uEAAuE;AACvE,wEAAwE;AACxE,qEAAqE;AACrE,iEAAiE;AACjE,oEAAoE;AACpE,sCAAsC;AACtC,EAAE;AACF,0EAA0E;AAC1E,sEAAsE;AACtE,oEAAoE;AAEpE,QAAQ,CAAC,4CAA4C,EAAE,GAAG,EAAE;IAC1D,IAAI,OAAO,GAAG,EAAE,CAAC;IACjB,MAAM,WAAW,GAAG,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE,CAAC;IAEvC,UAAU,CAAC,GAAG,EAAE;QACd,OAAO,GAAG,WAAW,CAAC,IAAI,CAAC,MAAM,EAAE,EAAE,qBAAqB,CAAC,CAAC,CAAC;QAC7D,OAAO,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC;QAClC,OAAO,OAAO,CAAC,GAAG,CAAC,aAAa,CAAC;IACnC,CAAC,CAAC,CAAC;IAEH,SAAS,CAAC,GAAG,EAAE;QACb,OAAO,CAAC,GAAG,GAAG,EAAE,GAAG,WAAW,EAAE,CAAC;QACjC,IAAI,OAAO;YAAE,MAAM,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAC;IACjE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,kFAAkF,EAAE,GAAG,EAAE;QAC1F,oCAAoC;QACpC,8CAA8C;QAC9C,4DAA4D;QAC5D,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,UAAU,CAAC,CAAC;QAC/C,SAAS,CAAC,IAAI,CAAC,YAAY,EAAE,QAAQ,CAAC,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;QAC7D,aAAa,CACX,IAAI,CAAC,YAAY,EAAE,QAAQ,EAAE,iBAAiB,CAAC,EAC/C,oBAAoB,EACpB,OAAO,CACR,CAAC;QAEF,gEAAgE;QAChE,qEAAqE;QACrE,MAAM,UAAU,GAAG,IAAI,CACrB,YAAY,EACZ,SAAS,EACT,QAAQ,EACR,KAAK,EACL,MAAM,EACN,KAAK,CACN,CAAC;QACF,SAAS,CAAC,UAAU,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;QAC3C,MAAM,QAAQ,GAAG,OAAO,CAAC,UAAU,EAAE,gBAAgB,EAAE,wBAAwB,CAAC,CAAC;QACjF,MAAM,CAAC,QAAQ,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,YAAY,EAAE,wBAAwB,CAAC,CAAC,CAAC;QACpE,MAAM,CAAC,YAAY,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,CAAC,kBAAkB,CAAC,CAAC;IAC1E,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,uGAAuG,EAAE,GAAG,EAAE;QAC/G,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,UAAU,CAAC,CAAC;QAC/C,SAAS,CAAC,IAAI,CAAC,YAAY,EAAE,QAAQ,CAAC,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;QAC7D,aAAa,CACX,IAAI,CAAC,YAAY,EAAE,QAAQ,EAAE,iBAAiB,CAAC,EAC/C,UAAU,EACV,OAAO,CACR,CAAC;QACF,MAAM,UAAU,GAAG,IAAI,CACrB,YAAY,EACZ,SAAS,EACT,QAAQ,EACR,KAAK,EACL,MAAM,EACN,KAAK,CACN,CAAC;QACF,SAAS,CAAC,UAAU,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;QAC3C,MAAM,KAAK,GAAG,OAAO,CAAC,UAAU,EAAE,aAAa,EAAE,wBAAwB,CAAC,CAAC;QAC3E,MAAM,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,YAAY,EAAE,SAAS,EAAE,QAAQ,EAAE,iBAAiB,CAAC,CAAC,CAAC;QAC/E,MAAM,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IACxC,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC"}

package/payload/platform/plugins/memory/mcp/dist/lib/neo4j.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"neo4j.d.ts","sourceRoot":"","sources":["../../src/lib/neo4j.ts"],"names":[],"mappings":"AAAA,OAAc,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,cAAc,CAAC;AAuBtD,wBAAgB,SAAS,IAAI,MAAM,CAgBlC;AAED,wBAAgB,UAAU,IAAI,OAAO,CAEpC;AAED,wBAAsB,WAAW,IAAI,OAAO,CAAC,IAAI,CAAC,CAKjD"}
+{"version":3,"file":"neo4j.d.ts","sourceRoot":"","sources":["../../src/lib/neo4j.ts"],"names":[],"mappings":"AAAA,OAAc,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,cAAc,CAAC;AA+BtD,wBAAgB,SAAS,IAAI,MAAM,CAgBlC;AAED,wBAAgB,UAAU,IAAI,OAAO,CAEpC;AAED,wBAAsB,WAAW,IAAI,OAAO,CAAC,IAAI,CAAC,CAKjD"}

package/payload/platform/plugins/memory/mcp/dist/lib/neo4j.js

@@ -5,7 +5,15 @@ let driver = null;
 function readPassword() {
     if (process.env.NEO4J_PASSWORD)
         return process.env.NEO4J_PASSWORD;
-    const passwordFile = resolve(process.env.PLATFORM_ROOT ?? resolve(import.meta.dirname, "../../../.."), "config/.neo4j-password");
+    // Task 207 — five segments up from the compiled file
+    // (`platform/plugins/memory/mcp/dist/lib/neo4j.js`) reaches `platform/`,
+    // where the installer writes `config/.neo4j-password`. The previous
+    // four-segment hop landed at `platform/plugins/`, where no password
+    // file exists; that miscalculation was masked while the per-spawn
+    // `.mcp.json` injected `PLATFORM_ROOT` on every MCP child. Task 207
+    // drops that JSON for specialists, so this fallback is the new
+    // load-bearing path when `process.env.PLATFORM_ROOT` is unset.
+    const passwordFile = resolve(process.env.PLATFORM_ROOT ?? resolve(import.meta.dirname, "../../../../.."), "config/.neo4j-password");
     try {
         return readFileSync(passwordFile, "utf-8").trim();
     }

package/payload/platform/plugins/memory/mcp/dist/lib/neo4j.js.map

@@ -1 +1 @@
-{"version":3,"file":"neo4j.js","sourceRoot":"","sources":["../../src/lib/neo4j.ts"],"names":[],"mappings":"AAAA,OAAO,KAA0B,MAAM,cAAc,CAAC;AACtD,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAC;AACvC,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAEpC,IAAI,MAAM,GAAkB,IAAI,CAAC;AAEjC,SAAS,YAAY;IACnB,IAAI,OAAO,CAAC,GAAG,CAAC,cAAc;QAAE,OAAO,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC;IAElE,MAAM,YAAY,GAAG,OAAO,CAC1B,OAAO,CAAC,GAAG,CAAC,aAAa,IAAI,OAAO,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,EAAE,aAAa,CAAC,EACxE,wBAAwB,CACzB,CAAC;IAEF,IAAI,CAAC;QACH,OAAO,YAAY,CAAC,YAAY,EAAE,OAAO,CAAC,CAAC,IAAI,EAAE,CAAC;IACpD,CAAC;IAAC,MAAM,CAAC;QACP,MAAM,IAAI,KAAK,CACb,yCAAyC,YAAY,gCAAgC,CACtF,CAAC;IACJ,CAAC;AACH,CAAC;AAED,MAAM,UAAU,SAAS;IACvB,IAAI,CAAC,MAAM,EAAE,CAAC;QACZ,6DAA6D;QAC7D,oEAAoE;QACpE,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,SAAS,CAAC;QAClC,IAAI,CAAC,GAAG,EAAE,CAAC;YACT,MAAM,IAAI,KAAK,CACb,yEAAyE,CAC1E,CAAC;QACJ,CAAC;QACD,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,UAAU,IAAI,OAAO,CAAC;QAC/C,MAAM,QAAQ,GAAG,YAAY,EAAE,CAAC;QAChC,OAAO,CAAC,KAAK,CAAC,+BAA+B,GAAG,EAAE,CAAC,CAAC;QACpD,MAAM,GAAG,KAAK,CAAC,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC,CAAC;IAC/D,CAAC;IACD,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,MAAM,UAAU,UAAU;IACxB,OAAO,SAAS,EAAE,CAAC,OAAO,EAAE,CAAC;AAC/B,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,WAAW;IAC/B,IAAI,MAAM,EAAE,CAAC;QACX,MAAM,MAAM,CAAC,KAAK,EAAE,CAAC;QACrB,MAAM,GAAG,IAAI,CAAC;IAChB,CAAC;AACH,CAAC"}
+{"version":3,"file":"neo4j.js","sourceRoot":"","sources":["../../src/lib/neo4j.ts"],"names":[],"mappings":"AAAA,OAAO,KAA0B,MAAM,cAAc,CAAC;AACtD,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAC;AACvC,OAAO,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAEpC,IAAI,MAAM,GAAkB,IAAI,CAAC;AAEjC,SAAS,YAAY;IACnB,IAAI,OAAO,CAAC,GAAG,CAAC,cAAc;QAAE,OAAO,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC;IAElE,qDAAqD;IACrD,yEAAyE;IACzE,oEAAoE;IACpE,oEAAoE;IACpE,kEAAkE;IAClE,oEAAoE;IACpE,+DAA+D;IAC/D,+DAA+D;IAC/D,MAAM,YAAY,GAAG,OAAO,CAC1B,OAAO,CAAC,GAAG,CAAC,aAAa,IAAI,OAAO,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,EAAE,gBAAgB,CAAC,EAC3E,wBAAwB,CACzB,CAAC;IAEF,IAAI,CAAC;QACH,OAAO,YAAY,CAAC,YAAY,EAAE,OAAO,CAAC,CAAC,IAAI,EAAE,CAAC;IACpD,CAAC;IAAC,MAAM,CAAC;QACP,MAAM,IAAI,KAAK,CACb,yCAAyC,YAAY,gCAAgC,CACtF,CAAC;IACJ,CAAC;AACH,CAAC;AAED,MAAM,UAAU,SAAS;IACvB,IAAI,CAAC,MAAM,EAAE,CAAC;QACZ,6DAA6D;QAC7D,oEAAoE;QACpE,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,SAAS,CAAC;QAClC,IAAI,CAAC,GAAG,EAAE,CAAC;YACT,MAAM,IAAI,KAAK,CACb,yEAAyE,CAC1E,CAAC;QACJ,CAAC;QACD,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,UAAU,IAAI,OAAO,CAAC;QAC/C,MAAM,QAAQ,GAAG,YAAY,EAAE,CAAC;QAChC,OAAO,CAAC,KAAK,CAAC,+BAA+B,GAAG,EAAE,CAAC,CAAC;QACpD,MAAM,GAAG,KAAK,CAAC,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC,CAAC;IAC/D,CAAC;IACD,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,MAAM,UAAU,UAAU;IACxB,OAAO,SAAS,EAAE,CAAC,OAAO,EAAE,CAAC;AAC/B,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,WAAW;IAC/B,IAAI,MAAM,EAAE,CAAC;QACX,MAAM,MAAM,CAAC,KAAK,EAAE,CAAC;QACrB,MAAM,GAAG,IAAI,CAAC;IAChB,CAAC;AACH,CAAC"}

package/payload/platform/plugins/memory/mcp/vitest.config.ts

@@ -16,6 +16,8 @@ export default defineConfig({
     include: [
       "src/tools/__tests__/**/*.test.ts",
       "src/lib/__tests__/live-schema-source.test.ts",
+      // Task 207 — Vitest-style test for `readPassword()` fallback path math.
+      "src/lib/__tests__/neo4j-password-path.test.ts",
     ],
     testTimeout: 10_000,
   },

package/payload/platform/plugins/memory/skills/conversation-archive-enrich/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: conversation-archive-enrich
-description: Source-agnostic Phase 2 for any `:ConversationArchive` — walks the `:Section:Conversation` chunks of one named archive and asks the operator to confirm derived claims row-by-row. Fires only when the operator names a specific archive and asks for insights/enrichment; never auto-fires on Phase 1 completion. Per-row gate (wire / skip / reject) over four kinds — `mention`, `task`, `preference`, `observed-relationship`. Re-runs are idempotent on `(elementId(chunk), kind, contentHash)`, so collapsing duplicates is structural. Invokes the read-only MCP tool `mcp__memory__conversation-archive-derive-insights` to obtain proposals; never writes from the tool's return path. Each `wire` decision runs the proposal's returned `mergeCypher` via `mcp__graph__maxy-graph-write_neo4j_cypher`, or, for `task`, mints the `:Task` via `mcp__tasks__task-create` first and then runs the REFERENCES merge.
+description: Source-agnostic Phase 2 for any `:ConversationArchive` — walks the `:Section:Conversation` chunks of one named archive and asks the operator to confirm derived claims row-by-row. Fires only when the operator names a specific archive and asks for insights/enrichment; never auto-fires on Phase 1 completion. Per-row gate (wire / skip / reject) over four kinds — `mention`, `task`, `preference`, `observed-relationship`. Re-runs are idempotent on `(elementId(chunk), kind, contentHash)`, so collapsing duplicates is structural. Invokes the read-only MCP tool `mcp__memory__conversation-archive-derive-insights` to obtain proposals; never writes from the tool's return path. Each `wire` decision runs the proposal's returned `mergeCypher` via `mcp__graph__maxy-graph-write_neo4j_cypher`, or, for `task`, mints the `:Task` via `mcp__work__work-create` first and then runs the REFERENCES merge.
 ---
 
 # Conversation Archive — chunk-anchored insight derivation
@@ -78,7 +78,7 @@ A re-run against the same `(chunkElementId, target, contentHash)` collapses on t
 
 ### `task`
 
-1. Mint the `:Task` via `mcp__tasks__task-create` with `title=mergeParams.taskTitle`, optional due hint from `mergeParams.taskDueHint`, `affects=archiveElementId`, `raisedDuringConversationKey=chunkElementId`.
+1. Mint the `:Task` via `mcp__work__work-create` with `title=mergeParams.taskTitle`, optional due hint from `mergeParams.taskDueHint`, `affects=archiveElementId`, `raisedDuringConversationKey=chunkElementId`.
 2. Run the proposal's `mergeCypher` via `mcp__graph__maxy-graph-write_neo4j_cypher` with `mergeParams` plus `taskElementId=<minted Task elementId>`.
 
 The `:Task` itself is the durable artefact; the `REFERENCES` edge to the chunk records the evidence that produced it.

package/payload/platform/plugins/projects/PLUGIN.md

@@ -2,7 +2,7 @@
 name: projects
 description: "Structured project execution. Phased sprints, operational investigations, deliverable reviews, and retrospectives — backed by :Project:Task graph nodes with HAS_TASK relationships, health signals, and lifecycle tracking."
 requires:
-  - tasks
+  - work
 metadata: {"platform":{"always":false,"embed":["admin"],"pluginKey":"projects","optional":true,"recommended":true}}
 ---
 
@@ -41,7 +41,7 @@ Choose a tier based on scope:
 - **standard** — moderate complexity, multiple phases (e.g., kitchen refit)
 - **full** — significant scope, many dependencies (e.g., new build project)
 
-Include work items with their dependencies when the scope is known. If the user describes work incrementally, create the project first and add tasks later via `task-create` + `task-relate`.
+Include work items with their dependencies when the scope is known. If the user describes work incrementally, create the project first and add tasks later via `work-create` + `work-relate`.
 
 ## Checking Project Status
 
@@ -87,4 +87,4 @@ For scope changes and issues, use `project-update` with a `note` parameter follo
 
 ## Dependencies
 
-This plugin requires the `tasks` plugin to be enabled. Project tools are co-located in the tasks MCP server — same data domain, same Neo4j connection. If task tools are unavailable (tasks plugin not enabled), tell the user: "I need the tasks plugin to run structured projects. Would you like to enable it?" Do not attempt structured execution without task tools — fall back to a regular conversational approach until the dependency is resolved.
+This plugin requires the `work` plugin to be enabled. Project tools are co-located in the work MCP server — same data domain, same Neo4j connection. If work tools are unavailable (work plugin not enabled), tell the user: "I need the work plugin to run structured projects. Would you like to enable it?" Do not attempt structured execution without work tools — fall back to a regular conversational approach until the dependency is resolved.

package/payload/platform/plugins/projects/references/sprint.md

@@ -24,7 +24,7 @@ Understand what needs doing. Confirm the deliverable, the deadline (if any), and
 
 ### Execute
 
-Do the work. Track progress via task notes. Check `task-ready` if there are any dependencies. Mark the child task complete when done.
+Do the work. Track progress via task notes. Check `work-ready` if there are any dependencies. Mark the child task complete when done.
 
 ### Done
 
@@ -42,7 +42,7 @@ Check for prior learnings: call `memory-search` with a description of the projec
 
 ### Execute
 
-Work through the child tasks in dependency order. Before starting each task, check `task-ready` to confirm no blockers or AFFECTS conflicts. Append progress notes as work progresses. If a blocker is discovered mid-execution, create a new child task for it and link via `BLOCKS`.
+Work through the child tasks in dependency order. Before starting each task, check `work-ready` to confirm no blockers or AFFECTS conflicts. Append progress notes as work progresses. If a blocker is discovered mid-execution, create a new child task for it and link via `BLOCKS`.
 
 Record phase transitions: `[PROJECT:PHASE] Execute — starting {task name}`.
 

package/payload/platform/plugins/scheduling/skills/briefing/SKILL.md

@@ -21,7 +21,7 @@ The briefing has four sections, in this fixed order. Sections with no content co
 
 ### 1. Outstanding commitments
 
-Call `task-list` filtered to `status: open` AND (`dueDate <= today` OR `priority: high`). Order by due date ascending, then by priority. List the top five with one line each: title, due date, related entity. If more than five qualify, end the list with "+ N more open" and the total count.
+Call `work-list` filtered to `status: open` AND (`dueDate <= today` OR `priority: high`). Order by due date ascending, then by priority. List the top five with one line each: title, due date, related entity. If more than five qualify, end the list with "+ N more open" and the total count.
 
 ### 2. Today's calendar
 
@@ -63,7 +63,7 @@ The whole briefing must fit in one screen. If any section would overflow, collap
 
 ## Failure modes
 
-- **`task-list` empty.** Section 1 collapses to "nothing outstanding".
+- **`work-list` empty.** Section 1 collapses to "nothing outstanding".
 - **`schedule-list` empty.** Section 2 collapses to "nothing in the diary today".
 - **`memory-rank` returns fewer than five.** List what it returned; do not pad.
 - **`profile-read` shows the owner has no `lastActiveSession`.** Section 4 collapses to "no prior session recorded" rather than reporting from training data.