monomind 2.7.12 → 2.7.13

package/packages/@monomind/cli/.claude/skills/mastermind-stoporg/SKILL.md

@@ -1,147 +0,0 @@
----
-name: mastermind-stoporg
-description: Mastermind stoporg — stop a running scheduled org loop by setting its status to "stopped". The next scheduled wakeup will read the status, skip all work, and not reschedule. Loop dies within one interval — no orphaned wakeups.
-type: domain-skill
-default_mode: auto
----
-
-# Mastermind Stop Org
-
-This skill is invoked by `mastermind:stoporg` or directly via `/mastermind:stoporg`.
-
----
-
-## Inputs
-
-- `org_name`: name of the org to stop (matches `.monomind/orgs/<org_name>.json`)
-- `session_id`: session ID generated by the command wrapper
-- `caller`: command | master
-
----
-
-## Step 0 — Brain Load (standalone only)
-
-If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
-
----
-
-## Step 1 — Validate Org
-
-```bash
-orgFile=".monomind/orgs/${org_name}.json"
-[ ! -f "$orgFile" ] && {
-  echo "ERROR: Org '${org_name}' not found."
-  echo "Available orgs: $(ls .monomind/orgs/*.json 2>/dev/null | grep -vE -- '-approvals|-state|-activity|-goals|-routines|-projects|-members|-issues|-workspaces|-worktrees|-environments|-plugins|-adapters|-bootstrap|-threads|-budgets|-project-workspaces|-approval-comments' | xargs -I{} basename {} .json | tr '\n' ' ')"
-  exit 1
-}
-```
-
-Read current status:
-```bash
-current_status=$(jq -r '.status // "no-schedule"' "$orgFile")
-has_schedule=$(jq -r 'if .loop.poll_interval_minutes then "yes" else "no" end' "$orgFile")
-```
-
-If `has_schedule == "no"` — this is a **v2 org** (Org Runtime v2 has `schedule`,
-never `.loop`). Its daemon polls `.monomind/orgs/<name>/stop` every 2s, which is
-exactly what `monomind org stop` writes — use the CLI, not the v1 `.stops/` path:
-
-```bash
-REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
-CTRL_URL=$(jq -r '.url // "http://localhost:4242"' "$REPO_ROOT/.monomind/control.json" 2>/dev/null || echo "http://localhost:4242")
-npx -y monomind@latest org stop "${org_name}" \
-  || { mkdir -p ".monomind/orgs/${org_name}"; date -u +%Y-%m-%dT%H:%M:%SZ > ".monomind/orgs/${org_name}/stop"; }
-# Also POST to the control server in case a dashboard-started instance is running
-curl -s -X POST -H "x-monomind-token: $(cat "${REPO_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}/.monomind/dashboard-token" 2>/dev/null || true)" "${CTRL_URL}/api/orgs/${org_name}/stop" >/dev/null 2>&1 || true
-echo "Stop requested for org '${org_name}' (v2 daemon exits within 2s)."
-```
-- Exit.
-
-<!-- LEGACY-ORG-V1: remove this branch when v1 orgs are gone -->
-Everything below this point only runs for v1 orgs — v2 orgs already exited above.
-
-If `current_status == "stopped"`:
-- Print: "Org '<org_name>' is already stopped."
-- Exit.
-
----
-
-<!-- LEGACY-ORG-V1: remove this step when v1 orgs are gone -->
-## Step 2 — Set Status to Stopped and Clear next_run (v1 only)
-
-```bash
-orgFile=".monomind/orgs/${org_name}.json"
-tmp="${orgFile}.tmp"
-# Clear next_run to avoid showing a stale future timestamp in orgstatus
-jq '.status = "stopped" | if .loop then .loop.next_run = null else . end' "$orgFile" > "$tmp" && mv "$tmp" "$orgFile"
-```
-
----
-
-<!-- LEGACY-ORG-V1: remove this step when v1 orgs are gone -->
-## Step 3 — Write Stop File (for any running boss agents, v1 only)
-
-Any persistent boss agent checks for this file at the start of each loop iteration:
-
-```bash
-mkdir -p .monomind/orgs/.stops
-touch ".monomind/orgs/.stops/${org_name}.stop"
-```
-
----
-
-<!-- LEGACY-ORG-V1: remove this step when v1 orgs are gone -->
-## Step 4 — Emit Dashboard Events
-
-```bash
-REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
-CTRL_URL=$(jq -r '.url // "http://localhost:4242"' "$REPO_ROOT/.monomind/control.json" 2>/dev/null || echo "http://localhost:4242")
-
-# org:stop — signals dashboard to update status to stopped
-curl -s -X POST "${CTRL_URL}/api/mastermind/event" -H "x-monomind-token: $(cat "${REPO_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}/.monomind/dashboard-token" 2>/dev/null || true)" \
-  -H "Content-Type: application/json" \
-  -d "$(jq -cn \
-    --arg session "${session_id:-manual}" \
-    --arg org "$org_name" \
-    --arg proj "$REPO_ROOT" \
-    '{type:"org:stop",session:$session,org:$org,project:$proj,ts:(now*1000|floor)}')" || true
-```
-
----
-
-<!-- LEGACY-ORG-V1: remove this step when v1 orgs are gone -->
-## Step 5 — Report to User (v1 only)
-
-```
-✓ Org "<org_name>" stopped.
-
-  Current status: stopped
-  The loop will exit at its next scheduled wakeup without rescheduling.
-  Loop fully dead within: ≤$(jq -r '.loop.poll_interval_minutes // "?"' "$orgFile") minutes
-
-  To restart: /mastermind:runorg --org <org_name>
-  Status:     /mastermind:orgstatus --org <org_name>
-```
-
----
-
-## Step 6 — Return Output
-
-```yaml
-domain: ops
-status: complete
-decisions:
-  - what: "Org <org_name> stopped"
-    why: "status set to 'stopped'; next wakeup exits without rescheduling"
-    confidence: 1.0
-    outcome: shipped
-next_actions:
-  - "To restart: /mastermind:runorg --org <org_name>"
-  - "To check current state: /mastermind:orgstatus --org <org_name>"
-```
-
----
-
-## Step 7 — Brain Write (standalone only)
-
-If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.

package/packages/@monomind/cli/.claude/skills/mastermind-taskdev/SKILL.md

@@ -1,377 +0,0 @@
----
-name: mastermind-taskdev
-description: Execute implementation plans with independent tasks using fresh subagents per task, with two-stage review (spec compliance then code quality) after each.
-type: domain-skill
-default_mode: auto
----
-
-# Mastermind Taskdev
-
-Execute a plan by dispatching a fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
-
-**Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
-
-**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
-
-**Narration:** between tool calls, narrate at most one short line — the progress ledger and the tool results carry the record.
-
-**Continuous execution:** Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
-
----
-
-## When to Use
-
-```dot
-digraph when_to_use {
-    "Have implementation plan?" [shape=diamond];
-    "Tasks mostly independent?" [shape=diamond];
-    "Stay in this session?" [shape=diamond];
-    "mastermind:taskdev" [shape=box];
-    "mastermind:execute" [shape=box];
-    "Manual execution or brainstorm first" [shape=box];
-
-    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
-    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
-    "Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
-    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
-    "Stay in this session?" -> "mastermind:taskdev" [label="yes"];
-    "Stay in this session?" -> "mastermind:execute" [label="no - parallel session"];
-}
-```
-
-**vs. mastermind:execute (parallel session):**
-- Same session (no context switch)
-- Fresh subagent per task (no context pollution)
-- Two-stage review after each task: spec compliance first, then code quality
-- Faster iteration (no human-in-loop between tasks)
-
----
-
-## Inputs
-
-- `brain_context`: BRAIN CONTEXT block (loaded via mastermind-protocol/SKILL.md brain load)
-- `plan_file`: absolute path to the plan `.md` file to execute
-- `params`: any additional flags or context
-- `mode`: auto | confirm
-
----
-
-## The Process
-
-```dot
-digraph process {
-    rankdir=TB;
-
-    subgraph cluster_per_task {
-        label="Per Task";
-        "Dispatch implementer subagent (./implementer-prompt.md)" [shape=box];
-        "Implementer subagent asks questions?" [shape=diamond];
-        "Answer questions, provide context" [shape=box];
-        "Implementer subagent implements, tests, commits, self-reviews" [shape=box];
-        "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [shape=box];
-        "Spec reviewer subagent confirms code matches spec?" [shape=diamond];
-        "Implementer subagent fixes spec gaps" [shape=box];
-        "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [shape=box];
-        "Code quality reviewer subagent approves?" [shape=diamond];
-        "Implementer subagent fixes quality issues" [shape=box];
-        "Mark task complete in TodoWrite" [shape=box];
-    }
-
-    "Read plan, note context and global constraints, create TodoWrite" [shape=box];
-    "More tasks remain?" [shape=diamond];
-    "Dispatch final code reviewer subagent for entire implementation" [shape=box];
-    "Use mastermind:finish" [shape=box style=filled fillcolor=lightgreen];
-
-    "Read plan, note context and global constraints, create TodoWrite" -> "Dispatch implementer subagent (./implementer-prompt.md)";
-    "Dispatch implementer subagent (./implementer-prompt.md)" -> "Implementer subagent asks questions?";
-    "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
-    "Answer questions, provide context" -> "Dispatch implementer subagent (./implementer-prompt.md)";
-    "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"];
-    "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)";
-    "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" -> "Spec reviewer subagent confirms code matches spec?";
-    "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"];
-    "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)" [label="re-review"];
-    "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="yes"];
-    "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" -> "Code quality reviewer subagent approves?";
-    "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"];
-    "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)" [label="re-review"];
-    "Code quality reviewer subagent approves?" -> "Mark task complete in TodoWrite" [label="yes"];
-    "Mark task complete in TodoWrite" -> "More tasks remain?";
-    "More tasks remain?" -> "Dispatch implementer subagent (./implementer-prompt.md)" [label="yes"];
-    "More tasks remain?" -> "Dispatch final code reviewer subagent for entire implementation" [label="no"];
-    "Dispatch final code reviewer subagent for entire implementation" -> "Use mastermind:finish";
-}
-```
-
----
-
-## Pre-Flight Plan Review
-
-Before dispatching Task 1, scan the plan once for conflicts:
-
-- tasks that contradict each other or the plan's Global Constraints
-- anything the plan explicitly mandates that the review rubric treats as a defect (a test that asserts nothing, verbatim duplication of a logic block)
-
-Present everything you find to your human partner as one batched question — each finding beside the plan text that mandates it, asking which governs — before execution begins, not one interrupt per discovery mid-plan. If the scan is clean, proceed without comment. The review loop remains the net for conflicts that only emerge from implementation. (In auto mode: resolve each conflict yourself, state the resolution explicitly, and log it as a decision with confidence.)
-
----
-
-## Model Selection
-
-Use the least powerful model that can handle each role to conserve cost and increase speed.
-
-**Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.
-
-**Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
-
-**Architecture and design tasks**: use the most capable available model. The final whole-branch review is one of these — dispatch it on the most capable available model, not the session default.
-
-**Review tasks**: choose the model with the same judgment, scaled to the diff's size, complexity, and risk. A small mechanical diff does not need the most capable model; a subtle concurrency change does.
-
-**Always specify the model explicitly when dispatching a subagent.** An omitted model inherits your session's model — often the most capable and most expensive — which silently defeats this section.
-
-**Turn count beats token price.** Wall-clock and context cost scale with how many turns a subagent takes, and the cheapest models routinely take 2-3× the turns on multi-step work — costing more overall. Use a mid-tier model as the floor for reviewers and for implementers working from prose descriptions. When the task's plan text contains the complete code to write, the implementation is transcription plus testing: use the cheapest tier for that implementer. Single-file mechanical fixes also take the cheapest tier.
-
-**Task complexity signals:**
-- Touches 1-2 files with a complete spec → cheap model
-- Touches multiple files with integration concerns → standard model
-- Requires design judgment or broad codebase understanding → most capable model
-
----
-
-## Handling Implementer Status
-
-Implementer subagents report one of four statuses. Handle each appropriately:
-
-**DONE:** Generate the task's diff file from the BASE you recorded before dispatching the implementer (never `HEAD~1` — it silently drops all but the last commit of a multi-commit task), then proceed to spec compliance review with the brief, report, and diff file paths.
-
-**DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.
-
-**NEEDS_CONTEXT:** The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.
-
-**BLOCKED:** The implementer cannot complete the task. Assess the blocker:
-1. If it's a context problem, provide more context and re-dispatch with the same model
-2. If the task requires more reasoning, re-dispatch with a more capable model
-3. If the task is too large, break it into smaller pieces
-4. If the plan itself is wrong, escalate to the human
-
-**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.
-
-**Async dispatches:** reviewer and implementer subagents may complete asynchronously even when dispatched synchronously. Wait for each result before acting on it — never proceed to the next gate, and never touch the files a dispatched subagent is working on, while its result is pending.
-
----
-
-## Handling Reviewer ⚠️ Items
-
-A reviewer may report "⚠️ Cannot verify from diff" items — requirements that live in unchanged code or span tasks. These do not block the rest of the review, but you must resolve each one yourself before marking the task complete: you hold the plan and cross-task context the reviewer lacks. If you confirm an item is a real gap, treat it as a failed spec review — send it back to the implementer and re-review.
-
----
-
-## Constructing Reviewer Prompts
-
-Per-task reviews are task-scoped gates. The broad review happens once, at the final whole-branch review. When you fill a reviewer template:
-
-- Do not add open-ended directives like "check all uses" or "run race tests if useful" without a concrete, task-specific reason
-- Do not ask a reviewer to re-run tests the implementer already ran on the same code — the implementer's report carries the test evidence
-- Do not pre-judge findings for the reviewer — never instruct a reviewer to ignore or not flag a specific issue. If you believe a finding would be a false positive, let the reviewer raise it and adjudicate it in the review loop. If the prompt you are writing contains "do not flag," "don't treat X as a defect," "at most Minor," or "the plan chose" — stop: you are pre-judging, usually to spare yourself a review loop.
-- The global-constraints block you hand the reviewer is its attention lens. Copy the binding requirements verbatim from the plan's Global Constraints section or the spec: exact values, exact formats, and the stated relationships between components ("same layout as X", "matches Y"). The reviewer's template already carries the process rules — the constraints block is for what THIS project's spec demands.
-- Hand the reviewer its diff as a file: run `git log --oneline BASE..HEAD`, `git diff --stat BASE..HEAD`, and `git diff -U10 BASE..HEAD`, redirected to one uniquely named file (e.g. `.monomind/taskdev/task-N-review.diff`), and pass the reviewer that path. The output never enters your own context, and the reviewer sees the commit list, stat summary, and full diff with context in one Read call. Use the BASE you recorded before dispatching the implementer — never `HEAD~1`, which silently truncates multi-commit tasks.
-- A dispatch prompt describes one task, not the session's history. Do not paste accumulated prior-task summaries ("state after Tasks 1-3") into later dispatches. A fresh subagent needs its task, the interfaces it touches, and the global constraints. Nothing else.
-- Dispatch fix subagents for Critical and Important findings. Record Minor findings in the progress ledger as you go, and point the final whole-branch review at that list so it can triage which must be fixed before merge. A roll-up nobody reads is a silent discard.
-- A finding labeled plan-mandated — or any finding that conflicts with what the plan's text requires — is the human's decision, like any plan contradiction: present the finding and the plan text, ask which governs. Do not dismiss the finding because the plan mandates it, and do not dispatch a fix that contradicts the plan without asking. (In auto mode: resolve it explicitly, log the decision, and prefer the spec over the plan's example code.)
-- The final whole-branch review gets a diff file too: generate it from the merge base (`git merge-base main HEAD`) to HEAD and include the path in the final review dispatch, so the final reviewer reads one file instead of re-deriving the branch diff with git commands.
-- Every fix dispatch carries the implementer contract: the fix subagent re-runs the tests covering its change and reports the results. Name the covering test files in the dispatch — a one-line fix does not need the whole suite. Before re-dispatching the reviewer, confirm the fix report contains the covering tests, the command run, and the output.
-- If the final whole-branch review returns findings, dispatch ONE fix subagent with the complete findings list — not one fixer per finding. Per-finding fixers each rebuild context and re-run suites; a real session's final-review fix wave cost more than all its tasks combined.
-
----
-
-## File Handoffs
-
-Everything you paste into a dispatch prompt — and everything a subagent prints back — stays resident in your context for the rest of the session and is re-read on every later turn. Hand artifacts over as files:
-
-- **Task brief:** before dispatching an implementer, extract the task's full text from the plan into a uniquely named file (e.g. `.monomind/taskdev/task-N-brief.md`). Compose the dispatch so the brief stays the single source of requirements. Your dispatch should contain: (1) one line on where this task fits in the project; (2) the brief path, introduced as "read this first — it is your requirements, with the exact values to use verbatim"; (3) interfaces and decisions from earlier tasks that the brief cannot know; (4) your resolution of any ambiguity you noticed in the brief; (5) the report-file path and report contract. Exact values (numbers, magic strings, signatures, test cases) appear only in the brief.
-- **Report file:** name the implementer's report file after the brief (brief `…/task-N-brief.md` → report `…/task-N-report.md`) and put it in the dispatch prompt. The implementer writes the full report there and returns only status, commits, a one-line test summary, and concerns.
-- **Reviewer inputs:** each reviewer gets three paths — the same brief file, the report file, and the diff file — plus the global constraints that bind the task.
-- Fix dispatches append their fix report (with test results) to the same report file and return a short summary; re-reviews read the updated file.
-
----
-
-## Durable Progress
-
-Conversation memory does not survive compaction. Controllers that lost their place have re-dispatched entire completed task sequences — the single most expensive failure observed. Track progress in a ledger file, not only in todos.
-
-- At skill start, check for a ledger: `cat "$(git rev-parse --show-toplevel)/.monomind/taskdev/progress.md"`. Tasks listed there as complete are DONE — do not re-dispatch them; resume at the first task not marked complete.
-- When a task's reviews come back clean, append one line to the ledger in the same message as your other bookkeeping: `Task N: complete (commits <base7>..<head7>, spec ✅ quality ✅)`.
-- The ledger is your recovery map: the commits it names exist in git even when your context no longer remembers creating them. After compaction, trust the ledger and `git log` over your own recollection.
-- The ledger is git-ignored scratch; if it's destroyed, recover from `git log`.
-
----
-
-## Prompt Templates
-
-- `./implementer-prompt.md` - Dispatch implementer subagent
-- `./spec-reviewer-prompt.md` - Dispatch spec compliance reviewer subagent
-- `./code-quality-reviewer-prompt.md` - Dispatch code quality reviewer subagent
-- `./final-reviewer-prompt.md` - Dispatch the final whole-branch reviewer (most capable model, diff as a file)
-
----
-
-## Example Workflow
-
-```
-You: I'm using mastermind:taskdev to execute this plan.
-
-[Read plan file once: docs/mastermind/plans/feature-plan.md]
-[Check ledger .monomind/taskdev/progress.md — empty, starting fresh]
-[Create TodoWrite with all tasks]
-
-Task 1: Hook installation script
-
-[Extract Task 1 brief to .monomind/taskdev/task-1-brief.md; record BASE]
-[Dispatch implementer with brief + report paths + scene-setting context]
-
-Implementer: "Before I begin - should the hook be installed at user or system level?"
-
-You: "User level (~/.config/monomind/hooks/)"
-
-Implementer: "Got it. Implementing now..."
-[Later] Implementer:
-  - Implemented install-hook command
-  - Added tests, 5/5 passing
-  - Self-review: Found I missed --force flag, added it
-  - Committed
-
-[Generate diff file from recorded BASE, dispatch spec compliance reviewer]
-Spec reviewer: ✅ Spec compliant - all requirements met, nothing extra
-
-[Dispatch code quality reviewer with the same diff file]
-Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.
-
-[Mark Task 1 complete]
-
-Task 2: Recovery modes
-
-[Extract Task 2 brief to .monomind/taskdev/task-2-brief.md; record BASE]
-[Dispatch implementer with brief + report paths + Task 1 interfaces]
-
-Implementer: [No questions, proceeds]
-Implementer:
-  - Added verify/repair modes
-  - 8/8 tests passing
-  - Self-review: All good
-  - Committed
-
-[Dispatch spec compliance reviewer]
-Spec reviewer: ❌ Issues:
-  - Missing: Progress reporting (spec says "report every 100 items")
-  - Extra: Added --json flag (not requested)
-
-[Implementer fixes issues]
-Implementer: Removed --json flag, added progress reporting
-
-[Spec reviewer reviews again]
-Spec reviewer: ✅ Spec compliant now
-
-[Dispatch code quality reviewer]
-Code reviewer: Strengths: Solid. Issues (Important): Magic number (100)
-
-[Implementer fixes]
-Implementer: Extracted PROGRESS_INTERVAL constant
-
-[Code reviewer reviews again]
-Code reviewer: ✅ Approved
-
-[Mark Task 2 complete]
-
-...
-
-[After all tasks]
-[Dispatch final code-reviewer]
-Final reviewer: All requirements met, ready to merge
-
-Done!
-```
-
----
-
-## Advantages
-
-**vs. Manual execution:**
-- Subagents follow TDD naturally
-- Fresh context per task (no confusion)
-- Parallel-safe (subagents don't interfere)
-- Subagent can ask questions (before AND during work)
-
-**vs. mastermind:execute:**
-- Same session (no handoff)
-- Continuous progress (no waiting)
-- Review checkpoints automatic
-
-**Efficiency gains:**
-- Controller curates exactly what context is needed; bulk artifacts move as files (briefs, reports, diffs), not pasted text
-- Subagent gets complete information upfront
-- Questions surfaced before work begins (not after)
-
-**Quality gates:**
-- Self-review catches issues before handoff
-- Two-stage review: spec compliance, then code quality
-- Review loops ensure fixes actually work
-- Spec compliance prevents over/under-building
-- Code quality ensures implementation is well-built
-
-**Cost:**
-- More subagent invocations (implementer + 2 reviewers per task)
-- Controller does more prep work (extracting all tasks upfront)
-- Review loops add iterations
-- But catches issues early (cheaper than debugging later)
-
----
-
-## Red Flags
-
-**Never:**
-- Start implementation on main/master branch without explicit user consent
-- Skip reviews (spec compliance OR code quality)
-- Proceed with unfixed issues
-- Dispatch multiple implementation subagents in parallel (conflicts)
-- Make a subagent read the whole plan file (hand it its task-brief file instead)
-- Skip scene-setting context (subagent needs to understand where task fits)
-- Ignore subagent questions (answer before letting them proceed)
-- Accept "close enough" on spec compliance (spec reviewer found issues = not done)
-- Skip review loops (reviewer found issues = implementer fixes = review again)
-- Let implementer self-review replace actual review (both are needed)
-- **Start code quality review before spec compliance is ✅** (wrong order)
-- Move to next task while either review has open Critical/Important issues
-- Tell a reviewer what not to flag, or pre-rate a finding's severity in the dispatch prompt ("treat it as Minor at most") — the plan's example code is a starting point, not evidence that its weaknesses were chosen
-- Dispatch a reviewer without a diff file — generate it first from the recorded BASE and name the path in the prompt
-- Re-dispatch a task the progress ledger already marks complete — check the ledger (and `git log`) after any compaction or resume
-
-**If subagent asks questions:**
-- Answer clearly and completely
-- Provide additional context if needed
-- Don't rush them into implementation
-
-**If reviewer finds issues:**
-- Implementer (same subagent) fixes them
-- Reviewer reviews again
-- Repeat until approved
-- Don't skip the re-review
-
-**If subagent fails task:**
-- Dispatch fix subagent with specific instructions
-- Don't try to fix manually (context pollution)
-
----
-
-## Integration
-
-**Required workflow skills:**
-- `Skill("mastermind-plan")` - Creates the plan this skill executes
-- `Skill("mastermind-review")` - Code review template for reviewer subagents
-- `Skill("mastermind-finish")` - Complete development after all tasks done
-
-**Subagents should use:**
-- `Skill("mastermind-tdd")` - Subagents follow TDD for each task
-
-**Alternative workflow:**
-- `Skill("mastermind-execute")` - Use for parallel session instead of same-session execution

package/packages/@monomind/cli/.claude/skills/mastermind-taskdev/code-quality-reviewer-prompt.md

@@ -1,60 +0,0 @@
-# Code Quality Reviewer Prompt Template
-
-Use this template when dispatching a code quality reviewer subagent from `mastermind:taskdev`.
-
-**Purpose:** Verify implementation is well-built — clean, tested, maintainable.
-
-**Only dispatch AFTER spec compliance review passes (✅).** Never run this first.
-
-```
-Task tool (general-purpose):
-  description: "Code quality review for Task N: [task name]"
-  prompt: |
-    You are reviewing the code quality of a recently implemented task.
-
-    ## Task Summary
-
-    [From implementer's report — what was built]
-
-    ## Diff to Review
-
-    Read this file — it contains the commit list, stat summary, and full
-    diff from [BASE_SHA] to [HEAD_SHA]:
-
-    [DIFF_FILE_PATH — e.g. .monomind/taskdev/task-N-review.diff]
-
-    ## What to Check
-
-    **Code quality:**
-    - Is the code clean and maintainable?
-    - Are names clear and accurate (match what things do, not how they work)?
-    - Is there duplication that could be DRY'd up?
-    - Are there magic numbers or hardcoded strings that should be constants?
-
-    **File structure:**
-    - Does each file have one clear responsibility with a well-defined interface?
-    - Are units decomposed so they can be understood and tested independently?
-    - Is the implementation following the file structure from the plan?
-    - Did this task create new files that are already large, or significantly grow
-      existing files? (Focus on what this change contributed, not pre-existing sizes.)
-
-    **Tests:**
-    - Do tests actually verify behavior (not just mock behavior)?
-    - Is test coverage adequate for the functionality added?
-    - Are tests readable and well-named?
-
-    **YAGNI / over-engineering:**
-    - Was anything built that wasn't needed?
-    - Is any abstraction premature?
-
-    ## Report Format
-
-    Return:
-    - **Strengths:** What was done well
-    - **Issues (Critical):** Must fix before proceeding
-    - **Issues (Important):** Should fix — notable quality problems
-    - **Issues (Minor):** Nice to have — low priority
-    - **Assessment:** ✅ Approved | ❌ Needs fixes
-
-    If issues are found, the implementer will fix them and you will re-review.
-```