@mmerterden/multi-agent-pipeline 19.1.4 → 20.0.0

package/pipeline/scripts/gc-refs.sh

@@ -4,7 +4,7 @@
 # `offload-ref.sh` parks build logs, diffs and test output under
 # <root>/.multi-agent/refs/<node_id>.md so a phase prompt can carry a pointer
 # instead of the whole log. In worktree modes that directory dies with the
-# worktree. In the --local modes there is no worktree: the refs land in the
+# worktree. With a local workspace there is no worktree: the refs land in the
 # real checkout and nothing ever removes them. They are gitignored, so they are
 # invisible to `git status` and grow without bound.
 #

package/pipeline/scripts/gen-mode-dispatch.mjs

@@ -16,12 +16,9 @@ import { readFileSync } from "node:fs";
  *   node pipeline/scripts/gen-mode-dispatch.mjs --mode=autopilot    # 0..5
  *   node pipeline/scripts/gen-mode-dispatch.mjs --mode=analysis     # 0/1/3/4/5 (no Dev)
  *
- * v16.0.0 removed the four dev-* modes. Depth is no longer a command name: the
- * Phase 0 Step 7.5 picker asks Full or Short and sets `state.onlyDevelop`. That
- * answer arrives long after the tracker boots at Step -1, so v17.5.0 splits
- * registration for the two modes that ask it (`full`, `local`): Phase 0 at Step -1,
- * the rest once depth has named them. Everything else still registers its whole
- * set up front, and a generated phase set is per-COMMAND, never per-depth.
+ * There is one pipeline. A mode's phase set is a property of the COMMAND and is
+ * known before the tracker boots, so every mode registers its whole set at
+ * Step -1 and no registration is deferred.
  *
  * Companion smoke `smoke-mode-dispatch-drift.sh` regenerates the section for
  * each mode file, diffs against the on-disk content, and fails on drift.
@@ -63,9 +60,7 @@ const MODES = Object.fromEntries(
     name,
     {
       phases: modePhases(name),
-      local: m.local,
       autopilot: m.autopilot,
-      ...(m.depth ? { depth: true } : {}),
     },
   ]),
 );
@@ -86,9 +81,6 @@ const phaseSequence = activeIds.map((id) => `Phase ${id}`).join(" → ");
 const MODE_LABELS = {
   autopilot: "`autopilot`",
   full: "full-pipeline",
-  local: "`--local`",
-  "local-autopilot": "`--local autopilot`",
-  "full-local": "full-pipeline + `--local`",
 };
 const modeLabel = MODE_LABELS[MODE] ?? `\`${MODE}\``;
 
@@ -98,46 +90,24 @@ const skipNote =
     ? `${modeLabel} mode does NOT TaskCreate phases ${skippedIds.join("/")}  -  those are not part of the ${modeLabel} phase set (\`${spec.phases.join(" ")}\`). Only register tiles for the active set.`
     : `${modeLabel} mode TaskCreates all ${PHASES.length} phases (no phase is skipped).`;
 
-const orderingNote = `**All TaskCreate calls in a batch fire in strict phase-number order BEFORE any TaskUpdate is applied.** For ${modeLabel} that means: ${spec.depth ? `Phase 0 at Step -1, then the rest in ascending order at Step 7.5 (${phaseSequence} minus whatever the depth answer drops)` : phaseSequence}. The native widget renders by creation order, not by phase number  -  out-of-order calls produce visually scrambled tile stacks. Full ordering contract in \`$HOME/.claude/multi-agent-refs/tracker-contract.md\` section "TaskCreate ordering (strict)".`;
-
-const localCaveat = spec.local
-  ? `\n> **Local mode:** no worktree is created, work happens on the current branch. Phase 0 Init still calls \`init\`  -  the \`--local\` flag is stored in tracker-state.json, and \`:resume\` restores the correct CWD.\n`
-  : "";
+const orderingNote = `**All TaskCreate calls in a batch fire in strict phase-number order BEFORE any TaskUpdate is applied.** For ${modeLabel} that means: ${phaseSequence}. The native widget renders by creation order, not by phase number  -  out-of-order calls produce visually scrambled tile stacks. Full ordering contract in \`$HOME/.claude/multi-agent-refs/tracker-contract.md\` section "TaskCreate ordering (strict)".`;
 
 const banner = spec.autopilot
   ? `\n> **Autopilot mode:** user confirmations are skipped. The tracker is still mandatory  -  autopilot agent calls cannot skip it; skipping breaks \`smoke-tracker-contract.sh\`.\n`
   : "";
 
-// Registration shape. A mode that asks the depth question does not know its phase
-// set at Step -1 (the answer needs taskType, which needs the fetched issue and the
-// branch), so it registers Phase 0 there and the rest at Step 7.5. Drawing eight
-// tiles beside the question that decides whether two of them run is the failure this
-// split exists to remove.
-const fullSet = spec.phases.filter((p) => p !== "0:Init");
-const shortSet = fullSet.filter((p) => Number(p.split(":")[0]) >= 2);
+// Registration shape. Every mode knows its whole phase set at Step -1, so every
+// tile is created there and nothing is appended later.
 const loopFor = (list) =>
   `for p in ${list.map((x) => `"${x}"`).join(" ")}; do\n  bash $HOME/.claude/scripts/phase-tracker.sh add "\${p%%:*}" "\${p#*:}"\ndone`;
 
-const initLoop = spec.depth
-  ? 'bash $HOME/.claude/scripts/phase-tracker.sh add 0 "Init"\nbash $HOME/.claude/scripts/phase-tracker.sh tiles'
-  : `${loopFor(spec.phases)}`;
-
-const deferredBlock = spec.depth
-  ? `
-# Phase 0 Step 7.5, immediately after the depth answer - the first moment this
-# mode knows its phase set. Full:
-${loopFor(fullSet)}
-# Short (Analysis and Planning are not run, so they get no tile at all):
-${loopFor(shortSet)}
-# Then the widget, narrowed to the phases that do not have a tile yet:
-bash $HOME/.claude/scripts/phase-tracker.sh tiles --new
-`
-  : "";
+const initLoop = loopFor(spec.phases);
+const deferredBlock = "";
 
 const out = `## Required: Phase Tracker Contract
 
 **The phase tracker is mandatory**  -  the agent cannot skip it. Full spec: [\`$HOME/.claude/multi-agent-refs/tracker-contract.md\`]($HOME/.claude/multi-agent-refs/tracker-contract.md).
-${banner}${localCaveat}
+${banner}
 Two channels run in parallel at every phase boundary:
 
 1. **State channel** (every CLI, identical): \`phase-tracker.sh\` writes to \`tracker-state.json\`. Drives \`:resume\`, \`:log\`, \`:status\`.
@@ -160,11 +130,11 @@ bash $HOME/.claude/scripts/phase-tracker.sh tokens <N> <in> <out> [cached]
 
 In Claude Code the agent MUST also drive the native TaskList widget so the user sees a sticky phase tile stack  -  this is the only progress signal Claude Code surfaces. Skipping these calls is the #1 source of "I don't see any phases" complaints.
 
-**TaskCreate ordering (strict)**: All TaskCreate calls in a registration batch fire in strict phase-number order BEFORE any TaskUpdate in that batch, and a later batch only ever appends phases numbered above everything already registered.${spec.depth ? " This mode registers in two batches (Step -1, then Step 7.5), so `tiles --new` narrows the second one and the Phase 0 tile is never created twice." : ""} The native widget renders by creation order, not by phase number  -  out-of-order calls produce visually scrambled tile stacks (e.g. \`1 ✓ · 2 ✓ · 4 ✓ · 0 ▶ · 3 ☐\`) even when the underlying state is correct. Pre-marking phases as completed/skipped before Phase 0 starts is FORBIDDEN  -  register the tile in order, then flip status via TaskUpdate when the phase actually short-circuits. Full contract in \`$HOME/.claude/multi-agent-refs/tracker-contract.md\` section "TaskCreate ordering (strict)".
+**TaskCreate ordering (strict)**: All TaskCreate calls in a registration batch fire in strict phase-number order BEFORE any TaskUpdate in that batch, and a later batch only ever appends phases numbered above everything already registered. The native widget renders by creation order, not by phase number  -  out-of-order calls produce visually scrambled tile stacks (e.g. \`1 ✓ · 2 ✓ · 4 ✓ · 0 ▶ · 3 ☐\`) even when the underlying state is correct. Pre-marking phases as completed/skipped before Phase 0 starts is FORBIDDEN  -  register the tile in order, then flip status via TaskUpdate when the phase actually short-circuits. Full contract in \`$HOME/.claude/multi-agent-refs/tracker-contract.md\` section "TaskCreate ordering (strict)".
 
 \`\`\`text
 # Register one tile per phase, capture the taskId, persist it:
-for each phase in ${spec.depth ? `0:Init at Step -1, then ${fullSet.join(", ")} (Full) or ${shortSet.join(", ")} (Short) at Step 7.5` : spec.phases.join(", ")}:
+for each phase in ${spec.phases.join(", ")}:
   TaskCreate({ subject: "Phase <N>: <Name>", activeForm: "<doing-form>" })
     -> returns taskId
   bash $HOME/.claude/scripts/phase-tracker.sh meta <N> tasklist_id "<taskId>"

package/pipeline/scripts/migrate-prefs.mjs

@@ -357,31 +357,32 @@ function migrate(prefs) {
     out.global.skillConformance.blockOnCoverageGap = false;
     changes.push("added skillConformance.blockOnCoverageGap=false (report, do not halt)");
   }
-  // Rename chain for the pipeline-tail command: /multi-agent:finish (pre-v2.5.0)
-  // -> :ship (v2.5.0) -> :resume-local (current). The autoFix value survives every
-  // hop - carry whichever legacy block still holds one rather than reset it.
-  if (!out.global.resumeLocal || typeof out.global.resumeLocal !== "object") {
-    out.global.resumeLocal = {};
-    changes.push("added resumeLocal (/multi-agent:ship renamed to :resume-local)");
-  }
-  if (typeof out.global.resumeLocal.autoFix !== "boolean") {
-    const legacyAutoFix =
-      typeof out.global.ship?.autoFix === "boolean"
-        ? out.global.ship.autoFix
-        : out.global.finish?.autoFix;
-    out.global.resumeLocal.autoFix = typeof legacyAutoFix === "boolean" ? legacyAutoFix : false;
+  // Rename chain for the tail that runs over work already on the branch:
+  // global.finish -> global.ship -> global.resumeLocal -> global.resume, the
+  // last hop following the command itself into /multi-agent:resume. The
+  // autoFix value survives every hop - carry whichever legacy block still
+  // holds one rather than reset it.
+  if (!out.global.resume || typeof out.global.resume !== "object") {
+    out.global.resume = {};
+    changes.push("added resume (:resume-local folded into :resume)");
+  }
+  if (typeof out.global.resume.autoFix !== "boolean") {
+    const legacyAutoFix = ["resumeLocal", "ship", "finish"]
+      .map((k) => out.global[k]?.autoFix)
+      .find((v) => typeof v === "boolean");
+    out.global.resume.autoFix = typeof legacyAutoFix === "boolean" ? legacyAutoFix : false;
     changes.push(
       typeof legacyAutoFix === "boolean"
-        ? "moved ship/finish autoFix -> resumeLocal.autoFix (value preserved)"
-        : "added resumeLocal.autoFix=false",
+        ? "moved tail autoFix -> resume.autoFix (value preserved)"
+        : "added resume.autoFix=false",
     );
   }
-  for (const legacy of ["ship", "finish"]) {
+  for (const legacy of ["resumeLocal", "ship", "finish"]) {
     if (out.global[legacy] && typeof out.global[legacy] === "object") {
       delete out.global[legacy].autoFix;
       if (Object.keys(out.global[legacy]).length === 0) {
         delete out.global[legacy];
-        changes.push(`removed obsolete ${legacy} block (renamed to resumeLocal)`);
+        changes.push(`removed obsolete ${legacy} block (renamed to resume)`);
       }
     }
   }

package/pipeline/scripts/phase-tracker.sh

@@ -1132,7 +1132,7 @@ case "$ACTION" in
     state=$(load_state)
     # Idempotent: a phase id that already exists is a no-op (name, status, and
     # token history are preserved). This is what lets continuation commands
-    # (/multi-agent:resume-local, resume) re-declare their phase set against a
+    # (/multi-agent:resume, /multi-agent:manual-test) re-declare their phase set against a
     # pre-existing tracker without duplicating or resetting tiles.
     new=$(echo "$state" | jq --arg id "$PID" --arg name "$PNAME" '
       if any(.phases[]?; .id == $id) then .
@@ -1167,7 +1167,7 @@ case "$ACTION" in
     # completion is recoverable (record, then re-run) and loses no work; a
     # phase that genuinely made no LLM call says so with --no-llm.
     if [ "$STATUS" = "completed" ] && [ "$NO_LLM" -eq 0 ]; then
-      case " ${TRACKER_LLM_PHASES:-1 2 3 4} " in
+      case " ${TRACKER_LLM_PHASES:-1 2 3 4 5} " in
         *" $PID "*)
           RECORDED=$(load_state | jq -r --arg id "$PID" \
             '(.phases[] | select(.id == $id) | (.tokens_in // 0) + (.tokens_out // 0)) // 0')

package/pipeline/scripts/phase0-exit-gate.mjs

@@ -270,7 +270,7 @@ export function evaluate(state, extraInput = "") {
     failures.push(
       `workspaceSource="autopilot" on an interactive run. Autopilot resolves the workspace ` +
         `to a worktree because an unattended commit in the user's own checkout is what ` +
-        `worktrees prevent; an interactive run asks (Step 5b) or is told by :local / --local.`,
+        `worktrees prevent; an interactive run asks at Step 5b, and the multi-repo bridge records "command".`,
     );
   }
 

package/pipeline/scripts/plan-coverage-gate.mjs

@@ -150,9 +150,9 @@ if (isMain) {
 
   // No plan at all is not a pass, and neither is an empty one: a Phase 2 that
   // produced no steps, or a state whose todos got cleared, would otherwise read
-  // as "0/0 accounted for" and let the commit through. A Short run has no Phase
-  // 2, and the caller is expected to skip this gate for those modes rather than
-  // let it report clean.
+  // as "0/0 accounted for" and let the commit through. A mode with no Phase 2
+  // (analysis) is expected to skip this gate explicitly rather than let it
+  // report clean.
   if (!Array.isArray(todos) || todos.length === 0) {
     const msg = Array.isArray(todos)
       ? "the plan has zero steps - that is an unusable plan, not a clean one; skip this gate explicitly for modes with no Phase 2"

package/pipeline/scripts/run-aggregator.mjs

@@ -159,7 +159,7 @@ function computeCost(modelKey, tokensIn, tokensOut, costTable) {
 
 /**
  * Heuristic: Plan (1) uses Opus per personas + dev-mode docs; Dev (2) uses
- * Sonnet by default unless the run is a Short pipeline (Opus); Review (3)
+ * Sonnet by default unless routing names another rung; Review (3)
  * triage is Opus and the reviewer breakdown comes from spans.
  *
  * This is a fallback when phase-tracker doesn't record the model used. Live

package/pipeline/scripts/usage-report.mjs

@@ -277,7 +277,6 @@ function commandOf(state) {
   const c = state.command;
   if (typeof c === "string" && c.trim()) return c.trim().slice(0, 60);
   if (state.mode) return state.mode;
-  if (state.onlyDevelop) return "dev";
   if (state.localMode) return "local";
   return "full";
 }
@@ -501,7 +500,6 @@ function buildEvent(state) {
     m: state.mode || null,
     ap: Boolean(state.autopilot),
     lo: Boolean(state.localMode),
-    dev: Boolean(state.onlyDevelop),
     in: inputType(state),
     rp: projectDigest(state.project),
     ph: typeof state.currentPhase === "number" ? state.currentPhase : null,

package/pipeline/scripts/worktree-finalize.sh

@@ -116,13 +116,13 @@ fi
 
 # --- preconditions ---------------------------------------------------------
 
-# `--local` mode has no worktree: worktreePath equals the project root. Removing
+# A local workspace has no worktree: worktreePath equals the project root. Removing
 # it would delete the user's checkout.
 rp_wt="$(cd "$WORKTREE" 2>/dev/null && pwd -P || echo "")"
 rp_pr="$(cd "$PROJECT_ROOT" 2>/dev/null && pwd -P || echo "")"
 [ -n "$rp_wt" ] || skip "worktree path does not exist: $WORKTREE"
 [ -n "$rp_pr" ] || skip "project root does not exist: $PROJECT_ROOT"
-[ "$rp_wt" != "$rp_pr" ] || skip "worktree equals project root (--local mode)  -  nothing to remove"
+[ "$rp_wt" != "$rp_pr" ] || skip "worktree equals project root (local workspace)  -  nothing to remove"
 
 # Refuse if the caller is standing inside the tree being removed. A shell left on
 # a deleted inode is worse than a leftover directory, and Phase 4 legitimately

package/pipeline/skills/.skill-manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": "1.0.0",
-  "generatedAt": "2026-09-21T08:28:08Z",
-  "skillCount": 216,
+  "generatedAt": "2026-09-21T11:25:15Z",
+  "skillCount": 213,
   "entries": [
     {
       "path": "shared/core/apple-archive-compliance/SKILL.md",
@@ -33,7 +33,7 @@
     },
     {
       "path": "shared/core/multi-agent-autopilot-status/SKILL.md",
-      "sha256": "065958fb3ff608d7d0ea36b3eef4614da442742dc69b00799cf1658848cee786"
+      "sha256": "f706d3fe4a0db86691d525f4bc008c095fddffbf69026fc553b780b2389eac6e"
     },
     {
       "path": "shared/core/multi-agent-autopilot/SKILL.md",
@@ -85,11 +85,11 @@
     },
     {
       "path": "shared/core/multi-agent-help/SKILL.md",
-      "sha256": "6ebe7d4de1a1ff815f572abb5d5db5d5af9ea507b3047ec60597a54455176da5"
+      "sha256": "4d6181bd8d612f758db5b60df1b18668cf39a5fa3b5174c19b063491d240c054"
     },
     {
       "path": "shared/core/multi-agent-ios-coding-standard/SKILL.md",
-      "sha256": "15a8d583cb7c772d5223c66c158062f25fdff4c41c6d353b7b70590a441dea38"
+      "sha256": "a424507424e883be63886da79b294314e03c73129c658b4ad3d080315f60e325"
     },
     {
       "path": "shared/core/multi-agent-issue/SKILL.md",
@@ -107,14 +107,6 @@
       "path": "shared/core/multi-agent-language/SKILL.md",
       "sha256": "63e746bc63ec9963c54e852e6ca5cdb30afd9309a02ee3fdb35965eb931d0300"
     },
-    {
-      "path": "shared/core/multi-agent-local-autopilot/SKILL.md",
-      "sha256": "5e367258e57fa710d16a1ad6363d5974b89aa99fb0ac791d1ce0070c81191f6b"
-    },
-    {
-      "path": "shared/core/multi-agent-local/SKILL.md",
-      "sha256": "0a5f20782de81ac3376088579ff6fbc3a6f3781cb285860aae796408aa57e6aa"
-    },
     {
       "path": "shared/core/multi-agent-log/SKILL.md",
       "sha256": "34bb9841af478abfd4a052d13b821ab4ccd9b5ba29154e9a06029312955b45a4"
@@ -143,13 +135,9 @@
       "path": "shared/core/multi-agent-refactor/SKILL.md",
       "sha256": "56eb2be076a6840ddfbf57b8e82c8b4bcf76209553d41a06cc71e56dc894364e"
     },
-    {
-      "path": "shared/core/multi-agent-resume-local/SKILL.md",
-      "sha256": "9f5089c748a8f0ae5983a3f392879a86017a33c883a87607169e32705c68c5e9"
-    },
     {
       "path": "shared/core/multi-agent-resume/SKILL.md",
-      "sha256": "6701424edde0a19b55a7de62bb5ba5f9dbaef7d9fb9ea2bce632374863145774"
+      "sha256": "57b97c497d34d10afdd030f44b74628a0d9f054431fec424dab7114cba775cf7"
     },
     {
       "path": "shared/core/multi-agent-review-analysis/SKILL.md",
@@ -217,7 +205,7 @@
     },
     {
       "path": "shared/core/multi-agent-sync/SKILL.md",
-      "sha256": "3d3331d34f9610ea02b96ee27c8029734f3a3447d2857fc0dca92d5b43d0f8e2"
+      "sha256": "34aea52bbbe86018011edc1c96a986d1ee2aba8bdb82b19212714bac80bea076"
     },
     {
       "path": "shared/core/multi-agent-test-accessibility/SKILL.md",
@@ -253,7 +241,7 @@
     },
     {
       "path": "shared/core/multi-agent/SKILL.md",
-      "sha256": "7ea676d07cd0104cc929b825463c521aff66047c6dcdfc28e9e37ca3752107da"
+      "sha256": "ca1286f3f17d76b75547320ec9b39af575a88828da14b4ed4ffe79932c7406a3"
     },
     {
       "path": "shared/external/accessibility-compliance-accessibility-audit/SKILL.md",

package/pipeline/skills/.skills-index.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": "1.0.0",
-  "skillCount": 216,
+  "skillCount": 213,
   "entries": [
     {
       "name": "accessibility-compliance-accessibility-audit",
@@ -180,7 +180,7 @@
     },
     {
       "name": "apple-archive-compliance",
-      "description": "Apple App Store Review compliance  -  wraps the multi-agent-toolkit-mcp `ios_app_store_audit` tool (18-rule deep scan) with ITMS error code mapping + EN/TR humanizer templates. Consumed by: /multi-agent:test 'store-ready' (primary dispatch), Phase 4 Security Auditor (catalog cross-ref on Info.plist ",
+      "description": "Apple App Store Review compliance  -  wraps the multi-agent-toolkit-mcp `ios_app_store_audit` tool (18-rule deep scan) with ITMS error code mapping + EN/TR humanizer templates. Consumed by: /multi-agent:test 'store-ready' (primary dispatch), Phase 3 Security Auditor (catalog cross-ref on Info.plist ",
       "platform": null,
       "group": "core",
       "plugin": null,
@@ -587,7 +587,7 @@
     },
     {
       "name": "google-play-compliance",
-      "description": "Google Play Store publication compliance  -  bundletool + aapt2 + apksigner orchestration + 21-rule policy catalog with Play Console error codes + humanizer templates. Consumed by: /multi-agent:test 'store-ready' (primary dispatch), Phase 4 Security Auditor (catalog cross-ref on AndroidManifest / bu",
+      "description": "Google Play Store publication compliance  -  bundletool + aapt2 + apksigner orchestration + 21-rule policy catalog with Play Console error codes + humanizer templates. Consumed by: /multi-agent:test 'store-ready' (primary dispatch), Phase 3 Security Auditor (catalog cross-ref on AndroidManifest / bu",
       "platform": null,
       "group": "core",
       "plugin": null,
@@ -1159,7 +1159,7 @@
     },
     {
       "name": "multi-agent-ios-coding-standard",
-      "description": "Audit an iOS module against the shared coding-standard registry (99 stable-ID rules), produce a remediation plan, then hand off to /multi-agent or :local. Use for a standards pass on a module, or when a review needs rule IDs rather than opinions.",
+      "description": "Audit an iOS module against the shared coding-standard registry (99 stable-ID rules), produce a remediation plan, then hand off to /multi-agent. Use for a standards pass on a module, or when a review needs rule IDs rather than opinions.",
       "platform": null,
       "group": "core",
       "plugin": null,
@@ -1212,28 +1212,6 @@
       "triggerPaths": [],
       "relativePath": "shared/core/multi-agent-language/SKILL.md"
     },
-    {
-      "name": "multi-agent-local",
-      "description": "Full pipeline in local mode  -  no worktree, runs directly on the current branch. Use when the full pipeline should run on the current branch without creating a worktree.",
-      "platform": null,
-      "group": "core",
-      "plugin": null,
-      "invokeAs": "multi-agent-local",
-      "triggerKeywords": [],
-      "triggerPaths": [],
-      "relativePath": "shared/core/multi-agent-local/SKILL.md"
-    },
-    {
-      "name": "multi-agent-local-autopilot",
-      "description": "Full pipeline + local + autopilot  -  no worktree, no confirmations, all 6 phases run end-to-end on the current branch. Use when the full pipeline should run on the current branch with no worktree and no prompts.",
-      "platform": null,
-      "group": "core",
-      "plugin": null,
-      "invokeAs": "multi-agent-local-autopilot",
-      "triggerKeywords": [],
-      "triggerPaths": [],
-      "relativePath": "shared/core/multi-agent-local-autopilot/SKILL.md"
-    },
     {
       "name": "multi-agent-log",
       "description": "Show the agent-log.md for the given task. With no ID, shows the most recent task. Use when asked what a task did, or to read its log.",
@@ -1247,7 +1225,7 @@
     },
     {
       "name": "multi-agent-manual-test",
-      "description": "Switch to the active task's branch and prepare it for manual testing in Xcode. Phase 5 standalone (the UI Bug Hunter lives at multi-agent-test). Use when a finished change needs trying by hand on a device or simulator.",
+      "description": "Switch to the active task's branch and prepare it for manual testing in Xcode. Phase 3 user-test step, standalone (the UI Bug Hunter lives at multi-agent-test). Use when a finished change needs trying by hand on a device or simulator.",
       "platform": null,
       "group": "core",
       "plugin": null,
@@ -1313,7 +1291,7 @@
     },
     {
       "name": "multi-agent-resume",
-      "description": "Resume a stopped or failed task from the phase where it left off. Use when a task stopped or failed and should carry on from where it left off.",
+      "description": "Pick up unfinished work: a pipeline run that stopped mid-phase, or work already written on the current branch that never went through the pipeline. Use when a task stopped or failed, or when hand-written local work needs review, build, PR and reporting.",
       "platform": null,
       "group": "core",
       "plugin": null,
@@ -1322,17 +1300,6 @@
       "triggerPaths": [],
       "relativePath": "shared/core/multi-agent-resume/SKILL.md"
     },
-    {
-      "name": "multi-agent-resume-local",
-      "description": "Continue already-done LOCAL work through the pipeline tail: Review (with its build gate) → Commit/PR → Report (technical analysis + Jira test-scenario comment). No dev phase. Use when local work is already done and only review, build, commit and reporting remain.",
-      "platform": null,
-      "group": "core",
-      "plugin": null,
-      "invokeAs": "multi-agent-resume-local",
-      "triggerKeywords": [],
-      "triggerPaths": [],
-      "relativePath": "shared/core/multi-agent-resume-local/SKILL.md"
-    },
     {
       "name": "multi-agent-review",
       "description": "Run parallel review on a branch diff or a Pull Request: 3 models on Claude Code (Fable + Opus + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). On PR input, posts per-finding inline comments + approve/needs-work. With no input (interactive), lists open GitHub + Bitbucket PRs to multi-select.",

package/pipeline/skills/shared/README.md

@@ -2,11 +2,11 @@
 
 Single source of truth for skills delivered to both Claude Code (`~/.claude/skills/`) and Copilot CLI (`~/.copilot/skills/`) by the installer.
 
-**Total:** 216 skills (63 core + 153 external). Auto-generated by `scripts/gen-skills-index.mjs`  -  do not edit by hand.
+**Total:** 213 skills (60 core + 153 external). Auto-generated by `scripts/gen-skills-index.mjs`  -  do not edit by hand.
 
 ## Directory layout
 
-- **`core/`**  -  63 `multi-agent*` orchestration skills that are pipeline-critical. Edits here are core-code changes.
+- **`core/`**  -  60 `multi-agent*` orchestration skills that are pipeline-critical. Edits here are core-code changes.
 - **`external/`**  -  153 iOS / Android / generic skills imported from the upstream skill library. Mirrors of third-party guidance.
 - Install destinations (ADR-0009): Claude Code gets NO local copy of `external/` - it loads those skills from the `multi-agent-plugins` marketplace, namespaced (`ai-<stack>-toolkit:<name>`); only the two compliance catalogs from `core/` land in `~/.claude/skills/`. Copilot CLI and Codex CLI receive a flat copy filtered to the enabled stacks. `external/` remains the single authoring source that `build-stack-plugins.mjs` publishes from.
 
@@ -14,7 +14,7 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 
 ## Categories
 
-- [Pipeline Orchestration](#pipeline-orchestration)  -  63
+- [Pipeline Orchestration](#pipeline-orchestration)  -  60
 - [iOS / Apple Ecosystem](#ios-apple-ecosystem)  -  90
 - [Android / Kotlin](#android-kotlin)  -  13
 - [Web](#web)  -  10
@@ -52,17 +52,14 @@ Source layout is logical grouping only  -  skill discovery at runtime is unchang
 | [`multi-agent-jira`](./core/multi-agent-jira/) | `core` | List open Jira issues, pick one, and launch the multi-agent pipeline. Use when a Jira issue should be picked up and started without knowing  |
 | [`multi-agent-kill`](./core/multi-agent-kill/) | `core` | Stop the given task, then remove its worktree and branch. Asks for confirmation. Use when a running or stuck task should be stopped and its  |
 | [`multi-agent-language`](./core/multi-agent-language/) | `core` | Toggle outputLanguage (assistant explanations, picker questions, PR/Jira/Confluence bodies). promptLanguage is fixed to English; commit mess |
-| [`multi-agent-local`](./core/multi-agent-local/) | `core` | Full pipeline in local mode  -  no worktree, runs directly on the current branch. Use when the full pipeline should run on the current branc |
-| [`multi-agent-local-autopilot`](./core/multi-agent-local-autopilot/) | `core` | Full pipeline + local + autopilot  -  no worktree, no confirmations, all 6 phases run end-to-end on the current branch. Use when the full pi |
 | [`multi-agent-log`](./core/multi-agent-log/) | `core` | Show the agent-log.md for the given task. With no ID, shows the most recent task. Use when asked what a task did, or to read its log. |
-| [`multi-agent-manual-test`](./core/multi-agent-manual-test/) | `core` | Switch to the active task's branch and prepare it for manual testing in Xcode. Phase 5 standalone (the UI Bug Hunter lives at multi-agent-te |
+| [`multi-agent-manual-test`](./core/multi-agent-manual-test/) | `core` | Switch to the active task's branch and prepare it for manual testing in Xcode. Phase 3 user-test step, standalone (the UI Bug Hunter lives a |
 | [`multi-agent-model`](./core/multi-agent-model/) | `core` | Turn the top model rung on or off and keep the cost ledger's pricing in step with it. Use when asked to enable or disable Fable, or which mo |
 | [`multi-agent-prune-logs`](./core/multi-agent-prune-logs/) | `core` | Delete per-task project logs under ~/.claude/logs/multi-agent (filter by age/project/task). Audit trail + metrics are preserved. Dry-run fir |
 | [`multi-agent-prune-prompts`](./core/multi-agent-prune-prompts/) | `core` | Zero-base prompt review: measure the always-on instruction footprint, classify every rule block, propose keep/trial-removal/delete; applies  |
 | [`multi-agent-purge`](./core/multi-agent-purge/) | `core` | ⚠️ Wipes every worktree, branch, log, and state file. Irreversible; asks for double confirmation. Use when every worktree, branch, log and s |
 | [`multi-agent-refactor`](./core/multi-agent-refactor/) | `core` | Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, research th |
-| [`multi-agent-resume`](./core/multi-agent-resume/) | `core` | Resume a stopped or failed task from the phase where it left off. Use when a task stopped or failed and should carry on from where it left o |
-| [`multi-agent-resume-local`](./core/multi-agent-resume-local/) | `core` | Continue already-done LOCAL work through the pipeline tail: Review (with its build gate) → Commit/PR → Report (technical analysis + Jira tes |
+| [`multi-agent-resume`](./core/multi-agent-resume/) | `core` | Pick up unfinished work: a pipeline run that stopped mid-phase, or work already written on the current branch that never went through the pi |
 | [`multi-agent-review`](./core/multi-agent-review/) | `core` | Run parallel review on a branch diff or a Pull Request: 3 models on Claude Code (Fable + Opus + Sonnet), 3 models on Copilot CLI (GPT + Opus |
 | [`multi-agent-review-analysis`](./core/multi-agent-review-analysis/) | `core` | Review a written analysis document instead of a diff: resolve it from a path, a Confluence page or a Jira issue, run the deterministic gates |
 | [`multi-agent-review-issue`](./core/multi-agent-review-issue/) | `core` | Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / sta |

package/pipeline/skills/shared/core/multi-agent/SKILL.md

@@ -311,25 +311,22 @@ Every user-facing phase title  -  TaskCreate cards, `phase-banner.sh` headers, a
 
 All TaskCreate calls fire in strict phase-number order BEFORE any TaskUpdate is applied (Claude Code path; Copilot CLI does not have a TaskList widget so this rule is Claude-only). The native widget renders by creation order, not by phase-number metadata  -  out-of-order calls produce visually scrambled tile stacks (e.g. `1 ✓ · 2 ✓ · 4 ✓ · 0 ▶ · 3 ☐`) even when the underlying state file is correct. Pre-marking phases as completed/skipped before Phase 0 starts is FORBIDDEN: register the tile in order with default `pending` status, then flip via TaskUpdate when the phase actually short-circuits. Mode-specific phase sets:
 
-- `multi-agent`: 0 → 1 → 2 → 3 → 4 → 5 → 6 → 7
-- `multi-agent-local`, `multi-agent-autopilot`, `multi-agent-local-autopilot`: 0 → 1 → 2 → 3 → 4 → 5 (the interactive Phase 5 gate needs a worktree checkout and an attended run)
-- `multi-agent-analysis`: 0 → 1 → 2 → 4 → 6 → 7 (no code, so no Dev and no Test)
+- `multi-agent`, `multi-agent-autopilot`: 0 → 1 → 2 → 3 → 4 → 5 (the user-test gate inside Phase 3 needs a worktree checkout and an attended run; the phase set is the same either way)
+- `multi-agent-analysis`: 0 → 1 → 3 → 4 → 5 (no code is written, so Dev is not in the set)
 
-Depth decides WHICH of the command's set is registered. The tracker boots at Step -1, long before the depth question can be asked, so it registers Phase 0 alone and the remaining tiles are created at Step 7.5 once the answer is known - a Short run never draws an Analysis or Planning tile.
+Every mode registers its whole set at Step -1: the set is a property of the command, so nothing is deferred.
 
 Full contract: `refs/tracker-contract.md` section "TaskCreate ordering (strict)".
 
 ### Phase 0: Init
 
-> **Contract (strict)**  -  Phase 0 has **8 sequential interactive steps** plus the
-> Step 7.5 depth question (`/multi-agent` and `:local` only; the autopilot entries
-> skip it and always run Full), defined in
+> **Contract (strict)**  -  Phase 0 has **8 sequential interactive steps**, defined in
 > `refs/phases/phase-0-init.md`. Read it before every Phase 0 run and execute all of
 > them. Do **NOT** short-circuit: even when the input is a Jira ID plus a branch, the
 > prefs load, the multi-repo offer, the branch picker and the branch-name confirm are
-> required UX checkpoints. A run once took a Jira ID and implemented straight onto the
-> local checkout with neither the project nor the branch picker ever shown, and nothing
-> failed, so nothing caught it. The walkthrough below covers input parsing and worktree
+> required UX checkpoints. Skipping them lets a Jira ID land straight on the local
+> checkout with neither the project nor the branch picker ever shown, and nothing
+> fails, so nothing catches it. The walkthrough below covers input parsing and worktree
 > creation only; it is not the contract.
 >
 > **Exit gate (BLOCKING).** Prose alone did not stop that run. Before marking Phase 0
@@ -434,7 +431,7 @@ Two halves, one phase, one approval gate (Phases 1 and 2 until 19.0.0).
 2. Launch **ios-architect** agent for architecture review (if structural changes)
 3. Determine development approach per todo (new file, modify, refactor)
 4. Log: `🧠 Phase 1: Plan  -  {N} todos created`
-5. **Plan Approval Gate** (Full + interactive only  -  a Short run has no plan, autopilot may not ask). Full flow in `refs/phases/phase-1-plan.md` Step 5:
+5. **Plan Approval Gate** (interactive only  -  autopilot may not ask). Full flow in `refs/phases/phase-1-plan.md` Step 5:
    - **5a  -  Clarification** (conditional, max 2 rounds): if the Jira/issue description is ambiguous (vague acceptance, UI task without Figma, API task without endpoint contract, `ambiguityScore >= 2`, parent-story scope drift), ask structured questions before rendering the plan. User answers → plan regenerated. If it is still unclear after the 2nd round, render the plan with a "best-effort" banner.
    - **5b  -  Approval loop**: render plan → user: `onayla`/`iptal`/free-text. A free-text edit request → the planning model (Fable) revises the plan → show it again. No iteration cap; user controls exit via `onayla` or `iptal`.
    - Persist `clarificationRounds`, `clarificationQuestions`, `clarificationAnswers`, `planIterations`, `planApprovedAt`, `planEditRequests` to `state.phases["1"]`.

package/pipeline/skills/shared/core/multi-agent-autopilot-status/SKILL.md

@@ -37,7 +37,7 @@ not a fault.
 
 When `swiftc` was available at `autopilot-on` time, `~/.claude/autopilot/bin/menubar`
 shows the same thing in the top right, refreshing on its own: one row per item
-with its id, whether it is running Full or Short, the phase as a fraction, the
+with its id, the phase as a fraction, the
 elapsed time and the stack, then the queue, then what is waiting, then the PRs of
 the last day - each one clickable.
 

package/pipeline/skills/shared/core/multi-agent-help/SKILL.md

@@ -38,8 +38,8 @@ Render **exactly one** of the two blocks below  -  the one matching `LANG`. Do n
   multi-agent "#316"                              -> GitHub Issue #
   multi-agent "bug/feature description"           -> Free-text
 
-(Copilot CLI uses the dash form: multi-agent-local, multi-agent-channels, etc.
- Claude Code uses colon form: /multi-agent:local, /multi-agent:channels, etc.)
+(Copilot CLI uses the dash form: multi-agent-channels, etc.
+ Claude Code uses colon form: /multi-agent:channels, etc.)
 
 ------------------------------------------------------------
 
@@ -52,7 +52,7 @@ How It Works (Phase 0  -  Interactive Flow):
   5. BRANCH NAME bugfix/{jiraId} or feature/{jiraId} -> confirm
   6. GIT ID      Select identity from preferences (multiple supported)
   7. INSTRUCTION Auto-detect if .instructions/ exists (figma etc.)
-  8. WORKSPACE   Create worktree (default) or local branch (--local)
+  8. WORKSPACE   Ask where the branch lives: worktree (default) or project root
 
 ------------------------------------------------------------
 
@@ -76,17 +76,15 @@ Pipeline (after Phase 0):
 
 Modes:
 
-  Depth is asked at Phase 0 Step 7.5, not passed as a flag:
-    Full   Plan -> Dev(Sonnet) -> Review -> Commit -> Report
-    Short  Dev(Opus, self-contained) -> Review -> Commit -> Report
-  Recommended from taskType. Review is never skipped either way.
+  One pipeline. Every mode runs its whole phase set:
+    Plan -> Dev(Sonnet) -> Review -> Commit -> Report
+  What a run costs follows the evidence the task carries.
 
-  --local              No worktree  -  works directly on local branch
-  autopilot            Skip all confirmations, including the depth question, so
-                       it always runs Full (EXCEPT Phase 5 channels menu)
+  autopilot            Skip all confirmations and resolve the workspace to a
+                       worktree (EXCEPT Phase 5 channels menu)
 
 Dedicated dash commands (Copilot):
-  multi-agent-local, multi-agent-autopilot, multi-agent-local-autopilot
+  multi-agent-autopilot
 
 ------------------------------------------------------------
 
@@ -212,8 +210,8 @@ Logs: $HOME/.copilot/logs/multi-agent/{project}/{task-id}/  (Copilot)
   multi-agent "#316"                              -> GitHub Issue #
   multi-agent "bug/özellik açıklaması"            -> Serbest metin
 
-(Copilot CLI dash form kullanır: multi-agent-local, multi-agent-channels vb.
- Claude Code colon form kullanır: /multi-agent:local, /multi-agent:channels vb.)
+(Copilot CLI dash form kullanır: multi-agent-channels vb.
+ Claude Code colon form kullanır: /multi-agent:channels vb.)
 
 ------------------------------------------------------------
 
@@ -226,7 +224,7 @@ Nasıl Çalışır (Phase 0  -  İnteraktif Akış):
   5. BRANCH NAME bugfix/{jiraId} veya feature/{jiraId} -> onayla
   6. GIT ID      Kimlik seç (prefs'ten; birden fazla desteklenir)
   7. INSTRUCTION .instructions/ varsa otomatik algıla
-  8. WORKSPACE   Worktree yarat (default) ya da local branch (--local)
+  8. WORKSPACE   Branch nerede yaşayacak: worktree (default) ya da proje kökü
 
 ------------------------------------------------------------
 
@@ -255,12 +253,11 @@ Modlar:
     Kısa   Dev(Opus, kendi kendine yeten) -> Review -> Commit -> Report
   taskType'a göre önerilir. Review iki durumda da atlanmaz.
 
-  --local              Worktree yok  -  doğrudan local branch'te çalışır
   autopilot            Derinlik sorusu dahil tüm onayları atlar, bu yüzden her
                        zaman Tam koşar (İSTİSNA: Phase 5 channels menüsü)
 
 Dedicated dash komutlar (Copilot):
-  multi-agent-local, multi-agent-autopilot, multi-agent-local-autopilot
+  multi-agent-autopilot
 
 ------------------------------------------------------------