session-orchestrator 3.21.0 → 3.23.0

package/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
   },
   "metadata": {
     "description": "Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi.",
-    "version": "3.21.0"
+    "version": "3.23.0"
   },
   "plugins": [
     {

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "session-orchestrator",
-  "version": "3.21.0",
+  "version": "3.23.0",
   "description": "Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi.",
   "author": {
     "name": "Bernhard Goetzendorfer",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "session-orchestrator",
-  "version": "3.21.0+codex.20260819195349",
+  "version": "3.23.0+codex.20260828183221",
   "description": "Loop engineering for AI coding agents — turn ad-hoc sessions into a repeatable research → plan → wave-execute → close loop with verification gates. Runs on Claude Code, Codex CLI, Cursor, and Pi.",
   "keywords": [
     "session",

package/.cursor/commands/autopilot-multi.md

@@ -0,0 +1,14 @@
+---
+description: Multi-story autopilot orchestrator — runs N parallel issue pipelines in isolated git worktrees (v3.6 Phase D thin-slice)
+argument-hint: [--dry-run|--apply] [--max-stories=N] [--max-hours=H] [--inactivity-timeout=S] [--stall-seconds=S] [--draft-mr=off|on-loop-start|on-green] [--json] [--verbose]
+---
+
+# /autopilot-multi
+
+Use the Session Orchestrator command definition at `commands/autopilot-multi.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/autopilot.md

@@ -0,0 +1,14 @@
+---
+description: Autonomous session-orchestration loop with kill-switches (Phase C-1.b — all 10 kill-switches shipped)
+argument-hint: [--headless] [--verbose] [--max-sessions=N] [--max-hours=H] [--confidence-threshold=0.X] [--dry-run]
+---
+
+# /autopilot
+
+Use the Session Orchestrator command definition at `commands/autopilot.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/bootstrap.md

@@ -0,0 +1,14 @@
+---
+description: Scaffold the minimum repo structure required by session-orchestrator
+argument-hint: [--upgrade <tier>]
+---
+
+# /bootstrap
+
+Use the Session Orchestrator command definition at `commands/bootstrap.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/brainstorm.md

@@ -0,0 +1,14 @@
+---
+description: Run a lightweight Socratic design dialogue (3-5 AUQ rounds) and write a spec markdown file before any implementation work. Use BEFORE /plan feature when scope/UX is ambiguous.
+argument-hint: [topic-or-feature-slug]
+---
+
+# /brainstorm
+
+Use the Session Orchestrator command definition at `commands/brainstorm.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/close.md

@@ -0,0 +1,13 @@
+---
+description: End session with verification, commits, and documentation
+---
+
+# /close
+
+Use the Session Orchestrator command definition at `commands/close.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/contract-version-bump.md

@@ -0,0 +1,14 @@
+---
+description: Classify and apply a version bump to a machine-readable contract (JSON Schema, API spec, config schema) — version literals, consumer compatibility, changelog entry, downstream drift
+argument-hint: [--contract <path>]
+---
+
+# /contract-version-bump
+
+Use the Session Orchestrator command definition at `commands/contract-version-bump.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/debug.md

@@ -0,0 +1,14 @@
+---
+description: "Run a 4-phase systematic debugging investigation before proposing any fix. Iron Law — NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST. Produces a `.orchestrator/debug/` artifact the fixer agent must reference."
+argument-hint: [bug-description-or-issue-ref]
+---
+
+# /debug
+
+Use the Session Orchestrator command definition at `commands/debug.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/discovery.md

@@ -0,0 +1,14 @@
+---
+description: Systematic quality discovery and issue detection
+argument-hint: [all|code|infra|ui|arch|session|audit|vault|feature] [--since <git-ref>] [--full]
+---
+
+# /discovery
+
+Use the Session Orchestrator command definition at `commands/discovery.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/dispatcher.md

@@ -0,0 +1,14 @@
+---
+description: Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command
+argument-hint: [--dry-run] [--repo <name>]
+---
+
+# /dispatcher
+
+Use the Session Orchestrator command definition at `commands/dispatcher.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/eli5.md

@@ -0,0 +1,14 @@
+---
+description: Say the last answer again in plain words — same facts, in the order the operator needs them. Optional topic argument.
+argument-hint: [topic]
+---
+
+# /eli5
+
+Use the Session Orchestrator command definition at `commands/eli5.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/eval.md

@@ -0,0 +1,14 @@
+---
+description: Run an honest session-process evaluation (Standard v1, aiat-llm-eval/1.0) — score the last completed session against the pre-registered rubric-v1 dimensions
+argument-hint: [--session <id>] [--no-write] [--verify <run-id>]
+---
+
+# /eval
+
+Use the Session Orchestrator command definition at `commands/eval.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/evolve.md

@@ -0,0 +1,14 @@
+---
+description: Extract session patterns into reusable learnings
+argument-hint: [analyze|review|list|dialectic [--apply]]
+---
+
+# /evolve
+
+Use the Session Orchestrator command definition at `commands/evolve.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/go.md

@@ -0,0 +1,14 @@
+---
+description: Approve session plan and begin wave execution
+argument-hint: [optional instructions]
+---
+
+# /go
+
+Use the Session Orchestrator command definition at `commands/go.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/grill.md

@@ -0,0 +1,14 @@
+---
+description: Stress-test a plan, design, or PRD before any build — relentless one-question-at-a-time interrogation that hunts contradictions against the code and challenges assumptions. Composable; no HARD-GATE.
+argument-hint: [file-path-or-topic]
+---
+
+# /grill
+
+Use the Session Orchestrator command definition at `commands/grill.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/harness-audit.md

@@ -0,0 +1,13 @@
+---
+description: Run the harness audit and report the rubric score for this repository
+---
+
+# /harness-audit
+
+Use the Session Orchestrator command definition at `commands/harness-audit.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/journey-audit.md

@@ -0,0 +1,14 @@
+---
+description: Outside-in product audit as a deep session — 7 read-only roles check what the site promises against what the code does, what a user experiences, what arrives by mail, and what the data says is used. Writes a dossier; needs a per-repo journey-manifest.
+argument-hint: [manifest-path]
+---
+
+# /journey-audit
+
+Use the Session Orchestrator command definition at `commands/journey-audit.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/memory-cleanup.md

@@ -0,0 +1,14 @@
+---
+description: Manual memory consolidation — review, consolidate, and prune memory files (Dream-equivalent)
+argument-hint: [--dry-run | --apply-pending]
+---
+
+# /memory-cleanup
+
+Use the Session Orchestrator command definition at `commands/memory-cleanup.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/persona-panel.md

@@ -0,0 +1,14 @@
+---
+description: Run a parallel multi-persona domain-expert review panel against a file, directory, or output range
+argument-hint: <target> [--personas <names,...>] [--mode <voting|hard-gate|summary>] [--threshold <M-of-N|all|any>] [--grounding <off|re-derive>] [--dry-run]
+---
+
+# /persona-panel
+
+Use the Session Orchestrator command definition at `commands/persona-panel.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/plan.md

@@ -0,0 +1,14 @@
+---
+description: Plan a new project, feature, or retrospective with structured requirement gathering
+argument-hint: [new|feature|retro]
+---
+
+# /plan
+
+Use the Session Orchestrator command definition at `commands/plan.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/portfolio.md

@@ -0,0 +1,14 @@
+---
+description: Aggregate cross-repo issue/MR/CI health across vault-registered projects into a single Markdown dashboard
+argument-hint: [--dry-run] [--repo <name>]
+---
+
+# /portfolio
+
+Use the Session Orchestrator command definition at `commands/portfolio.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/reconcile.md

@@ -0,0 +1,14 @@
+---
+description: Reconcile learnings into .claude/rules/ proposals — on-demand version of session-end Phase 3.6.8
+argument-hint: [--dry-run]
+---
+
+# /reconcile
+
+Use the Session Orchestrator command definition at `commands/reconcile.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/release.md

@@ -0,0 +1,14 @@
+---
+description: Cut a release — the order the steps must run in, and the criteria that abort a release
+argument-hint: [X.Y.Z]
+---
+
+# /release
+
+Use the Session Orchestrator command definition at `commands/release.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/repo-audit.md

@@ -0,0 +1,13 @@
+---
+description: Run a 9-category baseline compliance audit on the current repository
+---
+
+# /repo-audit
+
+Use the Session Orchestrator command definition at `commands/repo-audit.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/session.md

@@ -0,0 +1,14 @@
+---
+description: Start a development session (housekeeping, feature, deep)
+argument-hint: [housekeeping|feature|deep]
+---
+
+# /session
+
+Use the Session Orchestrator command definition at `commands/session.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/spinout.md

@@ -0,0 +1,14 @@
+---
+description: Guided 5-step venture-spinout / sanitized-fork runbook (copy + fresh-init + SNAPSHOT-FREEZE) — interactive, not scripted
+argument-hint: [--type venture|snapshot] [--dry-run]
+---
+
+# /spinout
+
+Use the Session Orchestrator command definition at `commands/spinout.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/sunset-review.md

@@ -0,0 +1,14 @@
+---
+description: Identify unused / near-zero-use / stale skills, agents, and commands as Demote or Retire candidates (read-only; never deletes)
+argument-hint: [--kind skill|agent|command] [--window-days N]
+---
+
+# /sunset-review
+
+Use the Session Orchestrator command definition at `commands/sunset-review.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/templates-ack.md

@@ -0,0 +1,14 @@
+---
+description: Acknowledge templates-first policy for the current session — bypasses the pre-bash-templates-first hook for the remainder of the session
+argument-hint: [optional-reason]
+---
+
+# /templates-ack
+
+Use the Session Orchestrator command definition at `commands/templates-ack.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/commands/test.md

@@ -0,0 +1,14 @@
+---
+description: Agentic end-to-end test orchestrator — drive web/macOS flows, evaluate UX rubric, reconcile issues
+argument-hint: [scope|profile-name] [--since <git-ref>] [--full]
+---
+
+# /test
+
+Use the Session Orchestrator command definition at `commands/test.md`.
+
+Arguments: $ARGUMENTS
+
+Read that command file and follow it exactly. When it references `$ARGUMENTS`, substitute the arguments above. Keep all Session Orchestrator platform fallbacks intact.
+
+Cursor has no Skill tool. When the command says to invoke a skill, Read `skills/<skill-name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same `skills/<skill-name>/` directory.

package/.cursor/hooks.json

@@ -0,0 +1,60 @@
+{
+  "version": 1,
+  "hooks": {
+    "sessionStart": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event sessionStart"
+      }
+    ],
+    "sessionEnd": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event sessionEnd"
+      }
+    ],
+    "beforeShellExecution": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event beforeShellExecution"
+      }
+    ],
+    "afterShellExecution": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event afterShellExecution"
+      }
+    ],
+    "preToolUse": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event preToolUse"
+      }
+    ],
+    "postToolUse": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event postToolUse"
+      }
+    ],
+    "afterFileEdit": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event afterFileEdit"
+      }
+    ],
+    "postToolUseFailure": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event postToolUseFailure"
+      }
+    ],
+    "stop": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event stop"
+      }
+    ],
+    "subagentStart": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event subagentStart"
+      }
+    ],
+    "subagentStop": [
+      {
+        "command": "sh hooks/run-node.sh scripts/lib/cursor-hook-bridge.mjs --event subagentStop"
+      }
+    ]
+  }
+}

package/.cursor/rules/000-session-orchestrator.mdc

@@ -8,6 +8,14 @@ alwaysApply: true
 
 You have Session Orchestrator capabilities. This plugin provides structured session management for development work.
 
+Native Cursor surface (this repo and `scripts/cursor-install.mjs` targets):
+- Slash commands: `.cursor/commands/*.md` — type `/session`, `/go`, `/close`
+- Skills: `.cursor/skills/<name>/SKILL.md` wrappers that point at canonical `skills/<name>/SKILL.md`
+- Hooks: `.cursor/hooks.json` → `scripts/lib/cursor-hook-bridge.mjs`
+
+**There is no Skill tool on Cursor.** When a command says to invoke a skill, Read `skills/<name>/SKILL.md` and follow it. Supporting files (`soul.md`, phase docs) live in that same directory.
+
+
 ## Platform Context
 
 - Platform: Cursor IDE (SO_PLATFORM=cursor)
@@ -33,10 +41,11 @@ You have Session Orchestrator capabilities. This plugin provides structured sess
 **No AskUserQuestion tool**: Present choices as numbered Markdown lists:
 ```
 Choose one:
-1. Option A — description
-2. Option B — description
+1. Option A (Recommended) — what it does, and why it is the safe default here.
+2. Option B — when B applies instead, and what it costs.
 Reply with the number of your choice.
 ```
+Two rules the example above follows. `(Recommended)` goes on option 1, in the label — an operator skims labels, so a recommendation hidden in the description is a recommendation he never sees. And every option names a reason, a cost, or a consequence: a recommendation without one is a claim he can only believe or ignore.
 
 **No TaskCreate/Update**: Use plain-text checklists to track progress:
 ```

package/.cursor/rules/010-session-workflow.mdc

@@ -6,6 +6,14 @@ alwaysApply: false
 
 # Session Workflow
 
+This rule is an index, not the procedure. Canonical skills:
+
+- `/session` → Read `commands/session.md`, then `skills/session-start/SKILL.md`
+- `/go` → Read `commands/go.md`, then `skills/wave-executor/SKILL.md`
+- `/close` → Read `commands/close.md`, then `skills/session-end/SKILL.md`
+
+Cursor has no Skill tool. Follow those files exactly. The summary below is not a substitute.
+
 Three-phase workflow: Start -> Execute -> Close.
 
 ## Phase 1: Session Start (`/session [type]`)
@@ -155,7 +163,7 @@ For each planned item:
 grep -rn 'console\.log\|debugger\|TODO: remove' --include='*.ts' --include='*.tsx' src/
 ```
 
-Do NOT commit if any check fails. Fix quick issues (<2 min) inline. For longer fixes, create a `priority:high` issue.
+Do NOT commit if any check fails. Fix quick issues (<2 min) inline. For longer fixes, create a `priority::high` issue.
 
 ### Step 3: Commit and Push
 

package/.cursor/rules/020-quality-gates.mdc

@@ -69,7 +69,7 @@ grep -rn 'console\.log\|debugger\|TODO: remove' \
 **Rules**:
 - Do NOT commit if any check fails
 - Fix quick issues (<2 min) inline
-- For longer fixes: create a `priority:high` issue and exclude affected files from commit
+- For longer fixes: create a `priority::high` issue and exclude affected files from commit
 
 ## Variant 4: Per-File
 

package/.cursor/rules/030-wave-execution.mdc

@@ -56,7 +56,7 @@ For each wave in the session plan:
 
 ### Step 1: Write Scope Manifest
 
-Write `.cursor/wave-scope.json` before each wave. Set `enforcement: warn` — Cursor's afterFileEdit hook is post-hoc (warns only, cannot block):
+Write `.cursor/wave-scope.json` before each wave. Set `enforcement: warn` unless `.cursor/hooks.json` is installed — then `preToolUse` can block via `cursor-hook-bridge.mjs`. `afterFileEdit` remains post-hoc (cannot unwrite):
 
 ```json
 {

package/.cursor/rules/040-discovery.mdc

@@ -186,9 +186,9 @@ Options:
 1. [title] — [file_path]:[line] ([severity])
 
 Options:
-1. Accept all (Recommended) — create issues for all
-2. Review individually
-3. Dismiss all
+1. Accept all (Recommended) — one issue per finding. Fastest, and you can still close any of them later.
+2. Review individually — decide finding by finding. Costs about a minute per item.
+3. Dismiss all — no issues created, and the findings are gone when this session ends.
 ```
 
 ### Step 4: Batch Confirmation
@@ -196,9 +196,9 @@ Options:
 ```
 Ready to create [N] issues? ([X] critical, [Y] high, [Z] medium, [W] low)
 
-1. Create all [N] issues (Recommended)
-2. Review list first
-3. Cancel
+1. Create all [N] issues (Recommended) — the list is already filtered, so nothing here is noise. You can close any of them later.
+2. Review list first — read the titles before anything is written. Costs one extra step.
+3. Cancel — nothing is written, and this run's findings are not kept.
 ```
 
 ## Phase 5: Issue Creation