monomind 2.5.1 → 2.5.3

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

@@ -47,7 +47,7 @@ This skill is invoked by `mastermind:access` or directly via `/mastermind:access
 
 ## 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`.
 
 ---
 
@@ -233,4 +233,4 @@ pending_requests: <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/activity.md → mastermind-activity/SKILL.md}

@@ -41,7 +41,7 @@ This skill is invoked by `mastermind:activity` or directly via `/mastermind:acti
 
 ## 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`.
 
 ---
 
@@ -188,4 +188,4 @@ events_shown: <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/adapter-manager.md → mastermind-adapter-manager/SKILL.md}

@@ -58,7 +58,7 @@ This skill is invoked by `mastermind:adapter-manager` 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`.
 
 ---
 
@@ -256,4 +256,4 @@ adapter_type: <type>
 
 ## 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/adapters.md → mastermind-adapters/SKILL.md}

@@ -24,7 +24,7 @@ This skill is invoked by `mastermind:adapters` or directly via `/mastermind:adap
 
 ## 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`.
 
 ---
 
@@ -201,4 +201,4 @@ adapter_type: <adapter_type if applicable>
 
 ## 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/agent-detail.md → mastermind-agent-detail/SKILL.md}

@@ -24,7 +24,7 @@ This skill is invoked by `mastermind:agent-detail` 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`.
 
 ---
 
@@ -239,4 +239,4 @@ agent_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/agents.md → mastermind-agents/SKILL.md}

@@ -23,7 +23,7 @@ This skill is invoked by `mastermind:agents` or directly via `/mastermind:agents
 
 ## 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`.
 
 ---
 
@@ -179,4 +179,4 @@ Print summary and any suggested next actions (e.g. "Run /mastermind:heartbeatv1
 
 ## 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/approval-detail.md → mastermind-approval-detail/SKILL.md}

@@ -48,7 +48,7 @@ This skill is invoked by `mastermind:approval-detail` 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`.
 
 ---
 
@@ -256,4 +256,4 @@ approval_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/approvev1.md → mastermind-approvev1/SKILL.md}

@@ -27,7 +27,7 @@ This skill is invoked by `mastermind:approvev1` or directly via `/mastermind:app
 
 ## 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`.
 
 ---
 
@@ -188,4 +188,4 @@ pending_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/architect.md → mastermind-architect/SKILL.md}

@@ -13,7 +13,7 @@ This skill is invoked by `mastermind:master` or directly via `/mastermind:archit
 
 ## 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 architect, review, or redesign
 - `project_name`: monotask space name
 - `board_id`: monotask board ID (set by master, or created standalone)
@@ -71,8 +71,8 @@ If this skill is invoked directly (not by master):
      -H "Content-Type: application/json" \
      -d '{"type":"session:start","session":"<sessionId>","domain":"architect","ts":'"$(date +%s)"'000}' || true
    ```
-2. Load brain context following _protocol.md Brain Load Procedure (namespace: `architect`)
-3. Run intake from _intake.md if prompt is vague
+2. Load brain context following mastermind-protocol/SKILL.md Brain Load Procedure (namespace: `architect`)
+3. Run intake from mastermind-intake/SKILL.md if prompt is vague
 4. Detect stack from current directory:
    ```bash
    # Detect tech stack
@@ -108,7 +108,7 @@ If this skill is invoked directly (not by master):
      -H "Content-Type: application/json" \
      -d '{"type":"session:complete","session":"<sessionId>","domain":"architect","ts":'"$(date +%s)"'000}' || true
    ```
-   Then: if `caller` is `standalone` (default), follow _protocol.md Brain Write Procedure (namespace: `architect`). If `caller` is `command` or `master`, skip — the caller handles the brain write.
+   Then: if `caller` is `standalone` (default), follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `architect`). If `caller` is `command` or `master`, skip — the caller handles the brain write.
 
 ---
 
@@ -663,7 +663,7 @@ mcp__monomind__memory_store(namespace: "architect:<sessionId>", key: "humaninloo
 ```
 (Use the same `<YYYYMMDD-HHmmss>` value used when writing the file above.)
 
-Spawn `Skill("mastermind-skills:build")` with:
+Spawn `Skill("mastermind-build")` with:
 - `prompt`: "Implement the following architecture fixes:\n" followed by the CRITICAL and HIGH `recommendation` fields extracted from `last_findings`, one bullet per line (format: `- [severity] [dimension]: [recommendation]`)
 - `project_name`: same project_name
 - `board_id`: same board_id
@@ -685,7 +685,7 @@ mcp__monomind__memory_store(namespace: "architect:<sessionId>", key: "cycle_<i>_
 
 **If activity = review:**
 
-Re-invoke `Skill("mastermind-skills:architect")` with:
+Re-invoke `Skill("mastermind-architect")` with:
 - `prompt`: if `i == 1` (clean initial pass — second independent review): "Second independent review to confirm initial clean result. Perform a fresh pass with no prior context bias." Otherwise: "Re-review after fixes applied in cycle \<i-1>. Focus on dimensions that had CRITICAL or HIGH findings: \<list dimension names from last_findings>"
 - `project_name`, `board_id`, `brain_context`, `stack`: same as initial pass
 - `scope`: if initial scope was `all`, use `review+deduplicate` (running both review and deduplicate catches structural regressions introduced by fixes without the full cost of design and migrate phases); otherwise use the same scope as the initial pass
@@ -815,7 +815,7 @@ Suggested next: <what to do next, e.g. "run mastermind:release" or "all architec
 Human-in-the-loop files: <retrieve humaninloop_files from memory (namespace: "architect:<sessionId>"); list each filename, or "none" if key absent>
 ```
 
-Then, if `caller` is `standalone`, follow _protocol.md Brain Write Procedure (namespace: `architect`) — the iteration results count as additional decisions scored from this run. If `caller` is `command` or `master`, skip — the caller handles the brain write.
+Then, if `caller` is `standalone`, follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `architect`) — the iteration results count as additional decisions scored from this run. If `caller` is `command` or `master`, skip — the caller handles the brain write.
 
 ---
 

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

@@ -17,12 +17,12 @@ Two modes:
 
 ## Inputs
 
-- `brain_context`: BRAIN CONTEXT block (loaded via _protocol.md Brain Load Procedure)
+- `brain_context`: BRAIN CONTEXT block (loaded via mastermind-protocol/SKILL.md Brain Load Procedure)
 - `count`: number of improvements to build (default: 1; set by leading integer in arguments)
 - `newfeature_count`: set by `--newfeature N` — number of brand-new features to discover and fully deliver
 - `focus`: optional topic hint (e.g. "performance", "security", "dx") — narrows research
 - `mode`: auto | confirm (default: auto)
-- `current_rep` / `loop_id`: injected by _repeat.md on continuation runs
+- `current_rep` / `loop_id`: injected by mastermind-repeat/SKILL.md on continuation runs
 
 ---
 
@@ -35,7 +35,7 @@ When invoked via the `/mastermind:autodev` command these arrive pre-parsed; pars
 3. `--newfeature <N>` → feature mode. Missing or invalid N → default 3. N > 10 → emit `[autodev] Warning: --newfeature capped at 10 (requested: N)` and cap.
 4. `--focus <topic>` → focus.
 5. `--auto` / `--confirm` → mode.
-6. `--tillend`, `--repeat`, `--maxruns`, `--wait`, `--rep`, `--loop` → handled by the _repeat.md PREAMBLE before this skill runs. If `--tillend` and `--newfeature` are both present: emit `[autodev] Warning: --tillend is not supported with --newfeature and will be ignored.` and strip `--tillend` (the pipeline delivers a fixed shortlist, not an open-ended loop).
+6. `--tillend`, `--repeat`, `--maxruns`, `--wait`, `--rep`, `--loop` → handled by the mastermind-repeat/SKILL.md PREAMBLE before this skill runs. If `--tillend` and `--newfeature` are both present: emit `[autodev] Warning: --tillend is not supported with --newfeature and will be ignored.` and strip `--tillend` (the pipeline delivers a fixed shortlist, not an open-ended loop).
 7. Remaining text → `focus` hint if none was given.
 
 Default `count = 1`.
@@ -82,7 +82,7 @@ LOOP:
   review_iter += 1
   If review_iter > 5: EXIT LOOP (capped — log a warning, continue to the next phase; don't block)
 
-  Invoke Skill("mastermind-skills:review") with:
+  Invoke Skill("mastermind-review") with:
     prompt: "Review the changes just made for: <title>. Verify: correctness, edge cases,
              tests present and passing, no regressions, security, API consistency."
     brain_context: brain_context
@@ -92,7 +92,7 @@ LOOP:
   Else: auto-fix findings; continue loop
 ```
 
-**Critical:** never pass `--tillend` to review and never invoke it as `/mastermind:review --tillend`. That schedules a ScheduleWakeup continuation and terminates the autodev session. Always invoke inline via `Skill("mastermind-skills:review")`. If the review skill is unavailable or throws: log a warning, treat as capped, continue.
+**Critical:** never pass `--tillend` to review and never invoke it as `/mastermind:review --tillend`. That schedules a ScheduleWakeup continuation and terminates the autodev session. Always invoke inline via `Skill("mastermind-review")`. If the review skill is unavailable or throws: log a warning, treat as capped, continue.
 
 ---
 
@@ -133,7 +133,7 @@ mcp__monomind__memory_store(
 
 ### Phase 3 — Build
 
-Invoke `Skill("mastermind-skills:build")` with:
+Invoke `Skill("mastermind-build")` with:
 - `prompt`: detailed implementation brief (MUST include: concrete spec, which files to touch, 2–4 testable acceptance criteria, what NOT to change)
 - `brain_context`, `mode: auto`, `project_name: $(basename "$PWD")`
 - `board_id`: only if non-empty; omit if monotask was unavailable
@@ -214,7 +214,7 @@ mcp__monomind__memory_store(
 )
 ```
 
-Invoke `Skill("mastermind-skills:build")` with a brief that includes:
+Invoke `Skill("mastermind-build")` with a brief that includes:
 - Feature title and user_value
 - Concrete spec: inputs, outputs, API surface, CLI flags, UI, etc.
 - Entry point file(s) to create or modify — list every path explicitly
@@ -230,7 +230,7 @@ Run R2 with the prompt scoped to the new feature `<title>`.
 
 #### Phase C — Documentation
 
-Invoke `Skill("mastermind-skills:content")` with:
+Invoke `Skill("mastermind-content")` with:
 ```
 prompt: "Document the new feature '<title>' that was just built.
          Generate:
@@ -328,7 +328,7 @@ Staged: <staged_count>/<newfeature_count> features. Run `git commit` to finalize
 ## Standalone Execution
 
 1. Extract flags (see Flag Parsing)
-2. Load brain context via _protocol.md Brain Load Procedure (namespace: `autodev`)
+2. Load brain context via mastermind-protocol/SKILL.md Brain Load Procedure (namespace: `autodev`)
 3. Create monotask board (optional — skip gracefully if monotask is not installed):
    ```bash
    project_name="${project_name:-$(basename "$PWD")}"
@@ -336,7 +336,7 @@ Staged: <staged_count>/<newfeature_count> features. Run `git commit` to finalize
    [ -z "$board_id" ] && echo "[autodev] monotask board unavailable — board tracking skipped."
    ```
 4. `--newfeature` parsed → run the Feature Pipeline; otherwise run the Improvement Loop
-5. At end: follow _protocol.md Brain Write Procedure (namespace: `autodev`)
+5. At end: follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `autodev`)
 
 ---
 

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

@@ -25,7 +25,7 @@ This skill is invoked by `mastermind:backup` or directly via `/mastermind:backup
 
 ## 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`.
 
 ---
 
@@ -194,4 +194,4 @@ backup_file: <path if created>
 
 ## 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/bootstrap.md → mastermind-bootstrap/SKILL.md}

@@ -23,7 +23,7 @@ This skill is invoked by `mastermind:bootstrap` or directly via `/mastermind:boo
 
 ## 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 @@ state: initialized | token | reset
 
 ## 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/budgets.md → mastermind-budgets/SKILL.md}

@@ -25,7 +25,7 @@ This skill is invoked by `mastermind:budgets` or directly via `/mastermind:budge
 
 ## 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`.
 
 ---
 
@@ -234,4 +234,4 @@ org_name: <org_name>
 
 ## 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/build.md → mastermind-build/SKILL.md}

@@ -13,7 +13,7 @@ This skill is invoked by `mastermind:master` or directly via `/mastermind:build`
 
 ## 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 goal for this build run
 - `project_name`: monotask space name
 - `board_id`: monotask board ID (set by master, or created standalone)
@@ -44,9 +44,9 @@ 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: `build`)
-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: `build`)
+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 $1}' | head -1)
@@ -60,7 +60,7 @@ If this skill is invoked directly (not by master):
    done_col=$(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: `build`)
+5. At end: follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `build`)
 
 ---
 

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

@@ -24,7 +24,7 @@ This skill is invoked by `mastermind:companies` or directly via `/mastermind:com
 
 ## 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`.
 
 ---
 
@@ -253,4 +253,4 @@ active_org: <active_org>
 
 ## 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/content.md → mastermind-content/SKILL.md}

@@ -13,7 +13,7 @@ This skill is invoked by `mastermind:master` or directly via `/mastermind:conten
 
 ## 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 content goal for this run
 - `project_name`: monotask space name
 - `board_id`: monotask board ID (set by master, or created standalone)
@@ -65,9 +65,9 @@ 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: `content`)
-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: `content`)
+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 $1}' | head -1)
@@ -81,7 +81,7 @@ If this skill is invoked directly (not by master):
    done_col=$(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: `content`)
+5. At end: follow mastermind-protocol/SKILL.md Brain Write Procedure (namespace: `content`)
 
 ---
 

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

@@ -24,7 +24,7 @@ This skill is invoked by `mastermind:costs` or directly via `/mastermind:costs`.
 
 ## 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`.
 
 ---
 
@@ -148,4 +148,4 @@ usage_pct: <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/createorg.md → mastermind-createorg/SKILL.md}

@@ -29,11 +29,11 @@ Org Runtime v2 (`packages/@monomind/cli/src/orgrt/`) is a Node daemon, not a Tas
 
 ## Step 0 — Brain Load (standalone only)
 
-If `caller` is not "command" (i.e. invoked directly, not by the command wrapper), load brain context following _protocol.md Brain Load Procedure with namespace: `ops`.
+If `caller` is not "command" (i.e. invoked directly, not by the command wrapper), load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
 
 If `caller` is "command", use the `brain_context` already provided.
 
-Run intake from `_intake.md` if `prompt` is vague (stop at Q3, domain is `ops`). Skip intake if `prompt` is a rich prompt per _intake.md criteria.
+Run intake from `mastermind-intake/SKILL.md` if `prompt` is vague (stop at Q3, domain is `ops`). Skip intake if `prompt` is a rich prompt per mastermind-intake/SKILL.md criteria.
 
 ---
 
@@ -244,4 +244,4 @@ If `schedule` was set, also print:
 
 ## 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/debug.md → mastermind-debug/SKILL.md}

@@ -157,7 +157,7 @@ Once you understand WHERE the break is, find existing working examples:
 
 1. **Write a failing test first** (before touching production code)
    - Automated test where possible; a one-off test script if no framework
-   - Use `Skill("mastermind-skills:tdd")` for writing proper failing tests
+   - Use `Skill("mastermind-tdd")` for writing proper failing tests
    - The test MUST fail before the fix proves it
 
 2. **Implement a single fix**
@@ -170,7 +170,7 @@ Once you understand WHERE the break is, find existing working examples:
    - Test passes now?
    - No other tests broken?
    - Issue actually resolved?
-   - Use `Skill("mastermind-skills:review")` to verify before declaring done
+   - Use `Skill("mastermind-review")` to verify before declaring done
 
 4. **If the fix doesn't work:**
    - STOP
@@ -266,8 +266,8 @@ If systematic investigation reveals the issue is truly environmental, timing-dep
 - **Condition-based waiting:** replace arbitrary sleeps/timeouts in flaky tests and scripts with polling for the actual condition ("wait until the file exists / the port answers"), with a hard cap. Timing guesses are bugs waiting for a slower machine.
 
 **Related skills:**
-- `Skill("mastermind-skills:tdd")` — for creating the failing test case (Phase 4, Step 1)
-- `Skill("mastermind-skills:verify")` — verify the fix worked before claiming success
+- `Skill("mastermind-tdd")` — for creating the failing test case (Phase 4, Step 1)
+- `Skill("mastermind-verify")` — verify the fix worked before claiming success
 
 ## Impact
 

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

@@ -1,6 +1,6 @@
 ---
 name: mastermind-delegation
-description: Agent Delegation Capability — injected into every spawned agent prompt so subagents can further delegate specialized work. Never invoked directly; referenced by _protocol.md and domain skills.
+description: Agent Delegation Capability — injected into every spawned agent prompt so subagents can further delegate specialized work. Never invoked directly; referenced by mastermind-protocol/SKILL.md and domain skills.
 type: shared
 ---
 

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

@@ -25,7 +25,7 @@ Every feature goes through this process. A todo list, a single-function utility,
 
 ## 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 idea or request to design
 - `project_name`: project context
 - `mode`: auto | confirm
@@ -44,7 +44,7 @@ Complete these items in order:
 6. **Write design doc** — save to `docs/mastermind/specs/YYYY-MM-DD-<topic>-design.md`
 7. **Spec self-review** — inline check for placeholders, contradictions, ambiguity, scope (see below)
 8. **User reviews written spec** — ask user to review before proceeding
-9. **Transition to planning** — invoke `Skill("mastermind-skills:plan")` to create the implementation plan
+9. **Transition to planning** — invoke `Skill("mastermind-plan")` to create the implementation plan
 
 ---
 
@@ -67,10 +67,10 @@ Spec self-review (fix inline)
         ↓
 User reviews spec? → changes requested → Write design doc
         ↓ approved
-Invoke Skill("mastermind-skills:plan")  ← TERMINAL STATE
+Invoke Skill("mastermind-plan")  ← TERMINAL STATE
 ```
 
-**The terminal state is invoking `Skill("mastermind-skills:plan")`.** Do NOT invoke mastermind:build or any other implementation skill directly. The ONLY next step after design is plan.
+**The terminal state is invoking `Skill("mastermind-plan")`.** Do NOT invoke mastermind:build or any other implementation skill directly. The ONLY next step after design is plan.
 
 ---
 
@@ -142,11 +142,11 @@ Fix any issues inline. No need to re-review — just fix and move on.
 
 Wait for the user's response. If they request changes, make them and re-run the spec self-review. Only proceed once the user approves.
 
-**In auto mode:** Skip the wait. Proceed directly to `Skill("mastermind-skills:plan")`.
+**In auto mode:** Skip the wait. Proceed directly to `Skill("mastermind-plan")`.
 
 ### Transition to Planning
 
-- Invoke `Skill("mastermind-skills:plan")` to create a detailed implementation plan
+- Invoke `Skill("mastermind-plan")` to create a detailed implementation plan
 - Do NOT invoke any other skill. `mastermind:plan` is the only next step.
 
 ---
@@ -179,12 +179,12 @@ A browser-based companion for showing mockups, diagrams, and visual options duri
 
 A question about a UI topic is not automatically a visual question. "What does personality mean in this context?" is a conceptual question — use the terminal. "Which wizard layout works better?" is a visual question — use the browser.
 
-If they agree to the companion, use `Skill("mastermind-skills:worktree")` to set up an isolated workspace, then invoke `Skill("agent-browser-testing")` to open the browser.
+If they agree to the companion, use `Skill("mastermind-worktree")` to set up an isolated workspace, then invoke `Skill("agent-browser-testing")` to open the browser.
 
 ---
 
 ## Integration
 
 **Skills used by this skill:**
-- `Skill("mastermind-skills:plan")` — creates the implementation plan after design is approved (terminal state)
-- `Skill("mastermind-skills:worktree")` — isolated workspace for visual companion work
+- `Skill("mastermind-plan")` — creates the implementation plan after design is approved (terminal state)
+- `Skill("mastermind-worktree")` — isolated workspace for visual companion work

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

@@ -36,7 +36,7 @@ If a proposed fix violates any invariant, drop it or rework it. State explicitly
 
 ## 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 @@ invariants:
 
 ## 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/env.md → mastermind-env/SKILL.md}

@@ -25,7 +25,7 @@ This skill is invoked by `mastermind:env` or directly via `/mastermind:env`.
 
 ## 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 @@ validation_errors: <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/environments.md → mastermind-environments/SKILL.md}

@@ -39,7 +39,7 @@ This skill is invoked by `mastermind:environments` 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`.
 
 ---
 
@@ -247,4 +247,4 @@ default_env: <id or null>
 
 ## 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/execute.md → mastermind-execute/SKILL.md}

@@ -11,13 +11,13 @@ Load plan, review critically, execute all tasks, report when complete.
 
 **Announce at start:** "I'm using the mastermind:execute skill to implement this plan."
 
-**Note:** This skill works best with subagent support (Claude Code). When subagents are available, prefer `Skill("mastermind-skills:taskdev")` for parallel task execution.
+**Note:** This skill works best with subagent support (Claude Code). When subagents are available, prefer `Skill("mastermind-taskdev")` for parallel task execution.
 
 ---
 
 ## 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)
 - `plan_path`: path to the plan file to execute
 - `project_name`: monotask space name
 - `board_id`: monotask board ID
@@ -48,16 +48,16 @@ For each task in the plan:
 4. Mark as `completed`
 
 When the plan references skills:
-- `mastermind:taskdev` → invoke `Skill("mastermind-skills:taskdev")`
-- `mastermind:verify` → invoke `Skill("mastermind-skills:verify")`
-- Any other `mastermind:*` skill → invoke `Skill("mastermind-skills:<name>")`
+- `mastermind:taskdev` → invoke `Skill("mastermind-taskdev")`
+- `mastermind:verify` → invoke `Skill("mastermind-verify")`
+- Any other `mastermind:*` skill → invoke `Skill("mastermind-<name>")`
 
 ### Step 3: Complete Development
 
 After all tasks complete and are verified:
 
 - Announce: "All tasks complete. Handing off to mastermind:finish."
-- **REQUIRED SUB-SKILL:** invoke `Skill("mastermind-skills:finish")`
+- **REQUIRED SUB-SKILL:** invoke `Skill("mastermind-finish")`
 - Follow that skill to verify tests, present options, and execute the chosen finish action
 
 ---
@@ -98,7 +98,7 @@ After all tasks complete and are verified:
 ## Integration
 
 **Skills used by this skill:**
-- `Skill("mastermind-skills:plan")` — creates the plan this skill executes
-- `Skill("mastermind-skills:taskdev")` — subagent-driven parallel task execution (preferred for complex plans)
-- `Skill("mastermind-skills:finish")` — complete the development branch after all tasks
-- `Skill("mastermind-skills:verify")` — verification gate before finishing
+- `Skill("mastermind-plan")` — creates the plan this skill executes
+- `Skill("mastermind-taskdev")` — subagent-driven parallel task execution (preferred for complex plans)
+- `Skill("mastermind-finish")` — complete the development branch after all tasks
+- `Skill("mastermind-verify")` — verification gate before finishing