monomind 2.5.1 → 2.5.2

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/new-agent.md → mastermind-new-agent/SKILL.md}

@@ -49,7 +49,7 @@ This skill is invoked by `mastermind:new-agent` or directly via `/mastermind:new
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -238,4 +238,4 @@ model: <model>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/ops.md → mastermind-ops/SKILL.md}

@@ -13,7 +13,7 @@ This skill is invoked by `mastermind:master` or directly via `/mastermind:ops`.
 
 ## Inputs
 
-- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via _protocol.md brain load)
+- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via mastermind-protocol/SKILL.md brain load)
 - `prompt`: the operations goal for this run
 - `project_name`: monotask space name
 - `board_id`: monotask board ID (set by master, or created standalone)
@@ -43,9 +43,9 @@ Assess the prompt to determine execution mode:
 
 If this skill is invoked directly (not by master):
 
-1. Load brain context following _protocol.md Brain Load Procedure (namespace: `ops`)
-2. Run intake from _intake.md if prompt is vague
-3. Follow _protocol.md Monotask Space+Board Setup Procedure:
+1. Load brain context following mastermind-protocol/SKILL.md Brain Load Procedure (namespace: `ops`)
+2. Run intake from mastermind-intake/SKILL.md if prompt is vague
+3. Follow mastermind-protocol/SKILL.md Monotask Space+Board Setup Procedure:
    ```bash
    project_name="${project_name:-$(basename "$PWD")}"
    space_id=$(monotask space list 2>/dev/null | awk -F' \| ' -v n="$project_name" '$2==n{print $1}' | head -1)
@@ -59,7 +59,7 @@ If this skill is invoked directly (not by master):
    done_col=$(monotask column create "$board_id" "Done"  --json | jq -r '.id')
    ```
 4. Proceed with complexity assessment below
-5. At end: follow _protocol.md Brain Write Procedure (namespace: `ops`)
+5. At end: follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `ops`)
 
 ---
 

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/org-chart.md → mastermind-org-chart/SKILL.md}

@@ -25,7 +25,7 @@ This skill is invoked by `mastermind:org-chart` or directly via `/mastermind:org
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -206,4 +206,4 @@ agent_count: <N>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/org-settings.md → mastermind-org-settings/SKILL.md}

@@ -31,7 +31,7 @@ There is no `topology`, `governance`, `alert_threshold`, or `ceo_adapter` in Org
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -271,4 +271,4 @@ field: <field if edit>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/orgs.md → mastermind-orgs/SKILL.md}

@@ -21,7 +21,7 @@ Lists all saved orgs from `.monomind/orgs/*.json`.
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/orgstatus.md → mastermind-orgstatus/SKILL.md}

@@ -20,7 +20,7 @@ This skill is invoked by `mastermind:orgstatus` or directly via `/mastermind:org
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -251,4 +251,4 @@ status: complete
 
 ## Step 7 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/plan.md → mastermind-plan/SKILL.md}

@@ -24,7 +24,7 @@ Assume they are a skilled developer, but know almost nothing about our toolset o
 
 ## Inputs
 
-- `brain_context`: BRAIN CONTEXT block (loaded via _protocol.md brain load)
+- `brain_context`: BRAIN CONTEXT block (loaded via mastermind-protocol/SKILL.md brain load)
 - `params`: spec text, feature description, or path to spec file
 - `mode`: auto | confirm
 
@@ -73,7 +73,7 @@ A task is the smallest unit that carries its own test cycle and is worth a fresh
 ```markdown
 # [Feature Name] Implementation Plan
 
-> **For agentic workers:** REQUIRED SUB-SKILL: Use `Skill("mastermind-skills:taskdev")` (recommended) or `Skill("mastermind-skills:execute")` to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+> **For agentic workers:** REQUIRED SUB-SKILL: Use `Skill("mastermind-taskdev")` (recommended) or `Skill("mastermind-execute")` to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
 
 **Goal:** [One sentence describing what this builds]
 
@@ -200,18 +200,18 @@ After the plan is approved (or in auto mode, after self-review):
 
 **"Plan complete and saved to `docs/mastermind/plans/<filename>.md`. Two execution options:**
 
-**1. Subagent-Driven (recommended)** — Invoke `Skill("mastermind-skills:taskdev")`: dispatches a fresh subagent per task, reviews between tasks, fast iteration.
+**1. Subagent-Driven (recommended)** — Invoke `Skill("mastermind-taskdev")`: dispatches a fresh subagent per task, reviews between tasks, fast iteration.
 
-**2. Inline Execution** — Invoke `Skill("mastermind-skills:execute")`: batch execution with checkpoints.
+**2. Inline Execution** — Invoke `Skill("mastermind-execute")`: batch execution with checkpoints.
 
 **Which approach?"**
 
-**In auto mode:** Skip the question. Default to subagent-driven — invoke `Skill("mastermind-skills:taskdev")` immediately.
+**In auto mode:** Skip the question. Default to subagent-driven — invoke `Skill("mastermind-taskdev")` immediately.
 
 **If Subagent-Driven chosen (or auto mode):**
-- Invoke `Skill("mastermind-skills:taskdev")`
+- Invoke `Skill("mastermind-taskdev")`
 - Fresh subagent per task + two-stage review
 
 **If Inline Execution chosen:**
-- Invoke `Skill("mastermind-skills:execute")`
+- Invoke `Skill("mastermind-execute")`
 - Batch execution with checkpoints for review

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/plan-to-tasks.md → mastermind-plan-to-tasks/SKILL.md}

@@ -25,7 +25,7 @@ This skill is invoked by `mastermind:plan-to-tasks` or directly via `/mastermind
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -133,4 +133,4 @@ dry_run: <true|false>
 
 ## Step 6 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/plugin-manager.md → mastermind-plugin-manager/SKILL.md}

@@ -43,7 +43,7 @@ This skill is invoked by `mastermind:plugin-manager` or directly via `/mastermin
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -238,4 +238,4 @@ plugin_id: <plugin_id>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/plugin-settings.md → mastermind-plugin-settings/SKILL.md}

@@ -55,7 +55,7 @@ This skill is invoked by `mastermind:plugin-settings` or directly via `/mastermi
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -270,4 +270,4 @@ health_status: <health>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/plugins.md → mastermind-plugins/SKILL.md}

@@ -24,7 +24,7 @@ This skill is invoked by `mastermind:plugins` or directly via `/mastermind:plugi
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -187,4 +187,4 @@ plugins_total: <N>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/profile.md → mastermind-profile/SKILL.md}

@@ -26,7 +26,7 @@ This skill is invoked by `mastermind:profile` or directly via `/mastermind:profi
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -184,4 +184,4 @@ user_id: <user_id or local-operator>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/project-detail.md → mastermind-project-detail/SKILL.md}

@@ -40,7 +40,7 @@ This skill is invoked by `mastermind:project-detail` or directly via `/mastermin
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -246,4 +246,4 @@ project_status: <status>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/project-workspace.md → mastermind-project-workspace/SKILL.md}

@@ -55,7 +55,7 @@ This skill is invoked by `mastermind:project-workspace` or directly via `/master
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -241,4 +241,4 @@ workspace_id: <workspace_id>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/projects.md → mastermind-projects/SKILL.md}

@@ -26,7 +26,7 @@ This skill is invoked by `mastermind:projects` or directly via `/mastermind:proj
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -164,4 +164,4 @@ projects_file: .monomind/orgs/<org_name>-projects.json
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/_protocol.md → mastermind-protocol/SKILL.md}

@@ -12,7 +12,7 @@ This file is a reference loaded by mastermind domain skills and master. It is NE
 
 ## Agent Delegation Protocol
 
-**Every Task/Agent spawn in mastermind and monomind MUST include the AGENT DELEGATION CAPABILITY block from `_delegation.md`.**
+**Every Task/Agent spawn in mastermind and monomind MUST include the AGENT DELEGATION CAPABILITY block from `mastermind-delegation/SKILL.md`.**
 
 This makes delegation recursive: every spawned agent can itself spawn sub-agents, which can spawn their own sub-agents. The capability block tells each agent which agent categories exist and how to delegate.
 
@@ -20,7 +20,7 @@ This makes delegation recursive: every spawned agent can itself spawn sub-agents
 
 **Why this matters:** Agents read their prompts cold. Without the delegation block, a spawned Security Engineer won't know it can delegate codebase exploration to a Code Reviewer, or that it can spawn a backend-dev to fix the issues it finds. With the block, every agent in the chain can self-organize and pull in the right specialist.
 
-**Reference:** Full block text is in `_delegation.md`. Copy it verbatim — do not paraphrase.
+**Reference:** Full block text is in `mastermind-delegation/SKILL.md`. Copy it verbatim — do not paraphrase.
 
 ---
 
@@ -400,5 +400,5 @@ AGENT: [agent slug, e.g. backend-dev | frontend-dev]
 SWARM: [topology agent-count consensus, e.g. \"hierarchical 4 raft\"]
 
 DEPENDENCIES: [task IDs, or \"none\"]
-OUTPUT FORMAT: Unified output schema (see mastermind _protocol.md)"
+OUTPUT FORMAT: Unified output schema (see mastermind mastermind-protocol/SKILL.md)"
 ```

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/release.md → mastermind-release/SKILL.md}

@@ -13,7 +13,7 @@ This skill is invoked by `mastermind:master` or directly via `/mastermind:releas
 
 ## Inputs
 
-- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via _protocol.md brain load)
+- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via mastermind-protocol/SKILL.md brain load)
 - `prompt`: the release goal (version target, scope, environment)
 - `project_name`: monotask space name
 - `board_id`: monotask board ID (set by master, or created standalone)
@@ -43,9 +43,9 @@ Assess the prompt to determine execution mode:
 
 If this skill is invoked directly (not by master):
 
-1. Load brain context following _protocol.md Brain Load Procedure (namespace: `release`)
-2. Run intake from _intake.md if prompt is vague
-3. Follow _protocol.md Monotask Space+Board Setup Procedure:
+1. Load brain context following mastermind-protocol/SKILL.md Brain Load Procedure (namespace: `release`)
+2. Run intake from mastermind-intake/SKILL.md if prompt is vague
+3. Follow mastermind-protocol/SKILL.md Monotask Space+Board Setup Procedure:
    ```bash
    project_name="${project_name:-$(basename "$PWD")}"
    space_id=$(monotask space list 2>/dev/null | awk -F' \| ' -v n="$project_name" '$2==n{print $1}' | head -1)
@@ -59,7 +59,7 @@ If this skill is invoked directly (not by master):
    done_col=$(monotask column create "$board_id" "Done"  --json | jq -r '.id')
    ```
 4. Proceed with complexity assessment below
-5. At end: follow _protocol.md Brain Write Procedure (namespace: `release`)
+5. At end: follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `release`)
 
 ---
 

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/_repeat.md → mastermind-repeat/SKILL.md}

@@ -1,5 +1,5 @@
 ---
-name: mastermind-repeat-postamble
+name: mastermind-repeat
 description: REPEAT POSTAMBLE — executes inter-session repeat/tillend loop continuation after any mastermind or monomind command completes. Calls ScheduleWakeup when work remains.
 type: protocol-skill
 ---
@@ -142,7 +142,7 @@ cat > ".monomind/loops/${LOOP_ID}.json" << EOF
   "lastRunAt": ${NOW_MS},
   "nextRunAt": ${NEXT_AT},
   "status": "running",
-  "source": "_repeat.md"
+  "source": "mastermind-repeat/SKILL.md"
 }
 EOF
 ```

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/research.md → mastermind-research/SKILL.md}

@@ -13,7 +13,7 @@ This skill is invoked by `mastermind:master` or directly via `/mastermind:resear
 
 ## Inputs
 
-- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via _protocol.md brain load)
+- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via mastermind-protocol/SKILL.md brain load)
 - `prompt`: the research question or intelligence goal
 - `project_name`: monotask space name
 - `board_id`: monotask board ID (set by master, or created standalone)
@@ -43,9 +43,9 @@ Assess the prompt to determine execution mode:
 
 If this skill is invoked directly (not by master):
 
-1. Load brain context following _protocol.md Brain Load Procedure (namespace: `research`)
-2. Run intake from _intake.md if prompt is vague
-3. Follow _protocol.md Monotask Space+Board Setup Procedure:
+1. Load brain context following mastermind-protocol/SKILL.md Brain Load Procedure (namespace: `research`)
+2. Run intake from mastermind-intake/SKILL.md if prompt is vague
+3. Follow mastermind-protocol/SKILL.md Monotask Space+Board Setup Procedure:
    ```bash
    project_name="${project_name:-$(basename "$PWD")}"
    space_id=$(monotask space list 2>/dev/null | awk -F' \| ' -v n="$project_name" '$2==n{print $1}' | head -1)
@@ -59,7 +59,7 @@ If this skill is invoked directly (not by master):
    done_col=$(monotask column create "$board_id" "Done"  --json | jq -r '.id')
    ```
 4. Proceed with complexity assessment below
-5. At end: follow _protocol.md Brain Write Procedure (namespace: `research`)
+5. At end: follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `research`)
 
 ---
 

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/review.md → mastermind-review/SKILL.md}

@@ -13,7 +13,7 @@ This skill is invoked by `mastermind:master` or directly via `/mastermind:review
 
 ## Inputs
 
-- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via _protocol.md brain load)
+- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via mastermind-protocol/SKILL.md brain load)
 - `prompt`: what to review and what to assess
 - `project_name`: monotask space name
 - `board_id`: monotask board ID (set by master, or created standalone)
@@ -54,9 +54,9 @@ Assess the prompt to determine execution mode:
 
 If this skill is invoked directly (not by master):
 
-1. Load brain context following _protocol.md Brain Load Procedure (namespace: `review`)
-2. Run intake from _intake.md if prompt is vague
-3. Follow _protocol.md Monotask Space+Board Setup Procedure:
+1. Load brain context following mastermind-protocol/SKILL.md Brain Load Procedure (namespace: `review`)
+2. Run intake from mastermind-intake/SKILL.md if prompt is vague
+3. Follow mastermind-protocol/SKILL.md Monotask Space+Board Setup Procedure:
    ```bash
    project_name="${project_name:-$(basename "$PWD")}"
    space_id=$(monotask space list 2>/dev/null | awk -F' \| ' -v n="$project_name" '$2==n{print $1}' | head -1)
@@ -70,7 +70,7 @@ If this skill is invoked directly (not by master):
    done_col=$(monotask column create "$board_id" "Done"  --json | jq -r '.id')
    ```
 4. Proceed with complexity assessment below
-5. At end: follow _protocol.md Brain Write Procedure (namespace: `review`)
+5. At end: follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `review`)
 
 ---
 

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/routine-detail.md → mastermind-routine-detail/SKILL.md}

@@ -59,7 +59,7 @@ This skill is invoked by `mastermind:routine-detail` or directly via `/mastermin
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -250,4 +250,4 @@ trigger_kind: <schedule|webhook>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/routines.md → mastermind-routines/SKILL.md}

@@ -30,7 +30,7 @@ This skill is invoked by `mastermind:routines` or directly via `/mastermind:rout
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -200,4 +200,4 @@ routines_file: .monomind/orgs/<org_name>-routines.json
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/runorgv1.md → mastermind-runorgv1/SKILL.md}

@@ -26,7 +26,7 @@ This skill is invoked by `mastermind:runorgv1` or directly via `/mastermind:runo
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -702,7 +702,7 @@ run_id: "<runId>"
 
 ## Step 8 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.
 
 ---
 

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/sales.md → mastermind-sales/SKILL.md}

@@ -13,7 +13,7 @@ This skill is invoked by `mastermind:master` or directly via `/mastermind:sales`
 
 ## Inputs
 
-- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via _protocol.md brain load)
+- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via mastermind-protocol/SKILL.md brain load)
 - `prompt`: the sales goal for this run
 - `project_name`: monotask space name
 - `board_id`: monotask board ID (set by master, or created standalone)
@@ -43,9 +43,9 @@ Assess the prompt to determine execution mode:
 
 If this skill is invoked directly (not by master):
 
-1. Load brain context following _protocol.md Brain Load Procedure (namespace: `sales`)
-2. Run intake from _intake.md if prompt is vague
-3. Follow _protocol.md Monotask Space+Board Setup Procedure:
+1. Load brain context following mastermind-protocol/SKILL.md Brain Load Procedure (namespace: `sales`)
+2. Run intake from mastermind-intake/SKILL.md if prompt is vague
+3. Follow mastermind-protocol/SKILL.md Monotask Space+Board Setup Procedure:
    ```bash
    project_name="${project_name:-$(basename "$PWD")}"
    space_id=$(monotask space list 2>/dev/null | awk -F' \| ' -v n="$project_name" '$2==n{print $1}' | head -1)
@@ -59,7 +59,7 @@ If this skill is invoked directly (not by master):
    done_col=$(monotask column create "$board_id" "Done"  --json | jq -r '.id')
    ```
 4. Proceed with complexity assessment below
-5. At end: follow _protocol.md Brain Write Procedure (namespace: `sales`)
+5. At end: follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `sales`)
 
 ---
 

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/search.md → mastermind-search/SKILL.md}

@@ -24,7 +24,7 @@ This skill is invoked by `mastermind:search` or directly via `/mastermind:search
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -183,4 +183,4 @@ total_hits: <N>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/secrets.md → mastermind-secrets/SKILL.md}

@@ -25,7 +25,7 @@ This skill is invoked by `mastermind:secrets` or directly via `/mastermind:secre
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -196,4 +196,4 @@ secrets_count: <N>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/{mastermind-skills/skill-builder.md → mastermind-skill-builder/SKILL.md}

@@ -66,14 +66,16 @@ API docs, syntax guides, tool documentation
 ## Directory Structure
 
 ```
-.claude/skills/mastermind/
-  skill-name.md              # Main skill (required)
+.claude/skills/
+  mastermind-<name>/
+    SKILL.md               # Main skill (required — a bare <name>.md does NOT register)
+    *-prompt.md            # Optional supporting files (prompt templates, references)
 
 .claude/commands/mastermind/
-  skill-name.md              # Command entry point (required)
+  <name>.md                # Command entry point (required)
 ```
 
-**Flat namespace** — all mastermind skills in one searchable namespace.
+**One top-level directory per skill** — Claude Code only registers `.claude/skills/<dir>/SKILL.md`, under the directory's own name. Grouping folders inside `.claude/skills/` do NOT register their children, so never nest. The `mastermind-` prefix on every skill directory is what prevents collisions with other skills, so never omit it — `monomind init` ships every `mastermind-*` directory automatically. Command wrappers invoke `Skill("mastermind-<name>")`.
 
 ## Skill File Structure
 
@@ -120,21 +122,21 @@ name: mastermind-[name]
 description: [one-line description of when to use]
 ---
 
-**First — extract repeat flags:** Follow REPEAT PREAMBLE from `_repeat.md`.
+**First — extract repeat flags:** Follow REPEAT PREAMBLE from `mastermind-repeat/SKILL.md`.
 
 Parse `$ARGUMENTS` for `--auto`, `--confirm`, `--project <name>`, and remaining text.
 
-Load brain context (follow `_protocol.md` Brain Load Procedure).
+Load brain context (follow `mastermind-protocol/SKILL.md` Brain Load Procedure).
 
 Default mode: **confirm** (or **auto** for low-risk/fast skills).
 
 ---
 
-Invoke `Skill("mastermind-skills:[name]")` passing: brain_context, params, mode.
+Invoke `Skill("mastermind-[name]")` passing: brain_context, params, mode.
 
-After skill returns: follow `_protocol.md` Brain Write Procedure.
+After skill returns: follow `mastermind-protocol/SKILL.md` Brain Write Procedure.
 
-Invoke `Skill("mastermind-skills:_repeat")` now. Required — do not skip.
+Invoke `Skill("mastermind-repeat")` now. Required — do not skip.
 ```
 
 ## Claude Search Optimization (CSO)
@@ -182,15 +184,15 @@ Use words Claude would search for:
 
 **Techniques:**
 - Reference other skills instead of repeating content
-- Use cross-references: `**REQUIRED BACKGROUND:** Use Skill("mastermind-skills:X")`
+- Use cross-references: `**REQUIRED BACKGROUND:** Use Skill("mastermind-X")`
 - One excellent example beats many mediocre ones
 
 ### Cross-Referencing Other Skills
 
 ```markdown
 # GOOD: Explicit requirement marker
-**REQUIRED SUB-SKILL:** Use Skill("mastermind-skills:worktree")
-**REQUIRED BACKGROUND:** You MUST understand Skill("mastermind-skills:finish")
+**REQUIRED SUB-SKILL:** Use Skill("mastermind-worktree")
+**REQUIRED BACKGROUND:** You MUST understand Skill("mastermind-finish")
 
 # BAD: Unclear if required
 See mastermind/worktree.md
@@ -221,7 +223,7 @@ See mastermind/worktree.md
 
 ## File Organization
 
-Mastermind skills are single files in a flat namespace. Keep everything inline. If a skill genuinely needs heavy reference material (500+ lines of API docs), condense it to what agents actually retrieve — a skill nobody can afford to load teaches nothing. Reusable prompt templates (like taskdev's implementer/reviewer prompts) live as sibling `*-prompt.md` files in the skills directory.
+Each mastermind skill is one directory holding a single `SKILL.md`. Keep everything inline in that file. If a skill genuinely needs heavy reference material (500+ lines of API docs), condense it to what agents actually retrieve — a skill nobody can afford to load teaches nothing. Reusable prompt templates (like taskdev's implementer/reviewer prompts) live as supporting `*-prompt.md` files inside the owning skill's directory, referenced as `./<name>-prompt.md`.
 
 ## The Iron Law (Same as TDD)
 
@@ -418,7 +420,7 @@ helper1, helper2, step3, pattern4
 - [ ] Re-test until bulletproof
 
 **Deployment:**
-- [ ] Skill file at `.claude/skills/mastermind/<name>.md`
+- [ ] Skill file at `.claude/skills/mastermind-<name>/SKILL.md`
 - [ ] Command file at `.claude/commands/mastermind/<name>.md`
 - [ ] Commit both files to git
 - [ ] Mirror both files into `packages/@monomind/cli/.claude/` (the npm-shipped copy)

package/packages/@monomind/cli/.claude/skills/mastermind-skills/{skills.md → SKILL.md}

@@ -24,7 +24,7 @@ This skill is invoked by `mastermind:skills` or directly via `/mastermind:skills
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command", load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 ---
 
@@ -153,4 +153,4 @@ skills_found: <N>
 
 ## Step 4 — Brain Write (standalone only)
 
-If `caller` is not "command", follow _protocol.md Brain Write Procedure for domain `ops`.
+If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.