harnessed 3.4.3 → 3.5.0

package/workflows/verify/simplify/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: verify-simplify
 description: |
-  Stage ④.g verify sub-workflow — code-simplifier 末尾串行 (移除重复 / 多余逻辑,
-  sister ~/.claude/CLAUDE.md "Verify 阶段 — 末尾 code-simplifier" verbatim)。
+  Stage ④.g verify sub-workflow — code-simplifier 末尾串行 (移除重复 / 多余逻辑;
+  bundled verify-stage cadence — tail-step code-simplifier).
   schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available
   (code-simplifier) + 1 phase (gate ref is_final_step 末尾串行)。
   Triggered by slash command
@@ -47,44 +47,23 @@ Sister `workflows/judgments/stage-routing.yaml`:
 - ✅ **触发**: verify chain 末尾步骤 (所有其他 verify sub 已 ship, 准备 code 简化收尾)
 - ❌ **跳过**: verify chain 中间步骤 (避免过早简化干扰后续 review)
 
-<!-- v3.4.3-dual-path-invocation -->
 ## How to invoke
 
-**Preferred path** (when the upstream specialist is installed): use the SlashCommand tool to run `{{ capabilities.code-simplifier.cmd }}` — the upstream specialist takes over.
-
-**Fallback path** (when the upstream isn't installed or returns no result): use the Task tool to spawn a general-purpose subagent with this prompt:
-
-> You are a **Code Simplifier (tail step)**.
->
-> **Mission**: Last step of verify chain (`phase.is_final_step == true`) after all reviews ship. Remove duplication / multi-purpose helpers / unused code / over-abstraction from the diff. Keep tests passing.
->
-> **Default-suspect mode**: assume the change is broken / risky / incomplete until proven otherwise. Cite `file:line` for every finding; do not generalize.
->
-> **Review checklist**:
-> 1. Look only at files changed in this phase — don't simplify unrelated code
->
-> 2. Duplication: same logic in 2+ places → extract once, but only if both sites benefit
->
-> 3. Dead code: unused exports / unreachable branches / commented-out blocks
->
-> 4. Magic numbers used in >1 place → named constant
->
-> 5. Over-abstraction: generics / interfaces with 1 implementer → inline
->
-> 6. Comments that lie or duplicate the code → delete (no-comments-default karpathy rule)
->
-> 7. Run tests after each simplification; revert if anything fails
->
-> **Output format**: structured report with severity-classified findings (applied / candidate-flagged / skipped (too risky for final step)). One finding per line: `[severity] file:line — problem (one sentence); fix: suggested change`. If no findings, say so explicitly. No preamble, no end-of-report summary.
-
-(Role prompt is self-contained — works even when the upstream `code-simplifier` user-skill / plugin isn't installed.)
-
-(Sister `~/.claude/commands/verify-simplify.md` is also generated by `harnessed setup` so `/verify-simplify` is a real platform slash command — both files carry the same dual-path instruction. Previous v3.4.x `harnessed verify-simplify --apply` CLI claims are removed; that subcommand was never implemented.)
+Use the Bash tool to run:
+
+```bash
+echo "$ARGUMENTS" | harnessed run verify-simplify --task-stdin
+```
+
+If `$ARGUMENTS` is empty, run `harnessed run verify-simplify` (no stdin pipe).
+
+After completion, the Bash output prints a `Next:` hint on stderr suggesting the next stage. Decide whether to invoke based on conversation context — the hint is informational, not prescriptive.
+
+<!-- harnessed-generated:v3.4.4 -->
 
 ## References
 
 - D-04 Stage ④ Verify 7 sub 分解
-- ~/.claude/CLAUDE.md "Verify 阶段 — 末尾 code-simplifier" verbatim
 - workflows/capabilities.yaml — code-simplifier
 - workflows/judgments/stage-routing.yaml — verify-simplify-tail trigger
 - workflows/defaults.yaml — ralph_max_iterations.verify-simplify.* values (W2.2 backfill)

package/workflows/verify/simplify/workflow.yaml

@@ -1,10 +1,9 @@
 # workflows/verify/simplify/workflow.yaml — Phase v3.0-3.4 W0 T3.4.W0.13d
 #
 # Stage ④.g verify sub-workflow — code-simplifier 末尾串行 (移除重复 / 多余逻辑)
-# (sister ~/.claude/CLAUDE.md "Verify 阶段 — 末尾 code-simplifier" verbatim)。
+# (bundled verify-stage cadence — tail-step code-simplifier).
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Verify 阶段 — code-simplifier 末尾串行" 章节
 #   - workflows/judgments/stage-routing.yaml verify-simplify-tail trigger (is_final_step)
 #   - workflows/capabilities.yaml — code-simplifier (Bucket 1 mattpocock, fires_when stage=='verify' AND is_final_step)
 #   - workflows/verify-work/workflow.yaml v2 SHIPPED phase 08-code-simplifier sister pattern

package/workflows/verify-work/SKILL.md

@@ -40,13 +40,13 @@ spawns each phase as a sub-agent via `@anthropic-ai/claude-agent-sdk` 0.3.142+.
 
 ## Phase 9 Pattern C 4-specialist Agent Team (D-11 + R20.11)
 
-The Agent Team upgrade phase (`09-agent-team-multispecialist`) follows
-`~/.claude/rules/agent-teams.md` Pattern C 多维度审查 verbatim — 4 teammate
+The Agent Team upgrade phase (`09-agent-team-multispecialist`) follows the
+bundled Agent Teams Pattern C 多维度审查 — 4 teammate
 (code-review + gstack-review + gstack-cso + gstack-qa) 互相 SendMessage 质询
 findings 是否真问题 (NOT fire-and-forget subagent fan-out)。Token estimate
-`team_cost < 2 × subagent_cost` is a prereq per agent-teams.md L34 (engine-level
+`team_cost < 2 × subagent_cost` is a prereq (bundled cost guideline; engine-level
 check, NOT yaml schema scope). Cleanup mandatory: `SendMessage shutdown_request`
-+ `TeamDelete` after round-trip complete (防呆清单 per agent-teams.md L46-L48).
++ `TeamDelete` after round-trip complete (bundled cleanup discipline).
 
 Trigger condition: `phase.is_major_release == true OR phase.is_large_refactor
 == true`. 常规 PR / 单点任务**不触发** Pattern C — code-review fan-out (phase 3)
@@ -73,7 +73,7 @@ harnessed verify-work --phase <num> --apply
 ## Forward-looking note
 
 The `trigger_phrases:` frontmatter is active after `harnessed setup` copies this
-SKILL.md to `~/.claude/skills/verify-work/` — Claude Code then loads the slash
+SKILL.md to `<claude-home>/skills/verify-work/` — Claude Code then loads the slash
 command `/verify-work` automatically (Gap B fix — v1.0.2 sister mechanism).
 
 ## References
@@ -84,8 +84,6 @@ command `/verify-work` automatically (Gap B fix — v1.0.2 sister mechanism).
 - R20.14 — special-purpose /qa /cso /design-review conditional
 - R20.7 — D-08 verify-work NEW 2 之一
 - R20.16 — fallback 3 铁律 chain_isolation
-- ~/.claude/CLAUDE.md "Verify 阶段" 7-step verbatim
-- ~/.claude/rules/agent-teams.md Pattern C 多维度审查
 - `workflows/capabilities.yaml` — gsd-verify-work / gsd-progress / code-review / gstack-{review,qa,cso,design-review} / code-simplifier / agent-teams-create entries
 - `workflows/judgments/parallelism-gate.yaml` — subagent-default + agent-teams-upgrade.fires
 - `workflows/defaults.yaml` — ralph_max_iterations.verify-work.* values

package/workflows/verify-work/workflow.yaml

@@ -4,8 +4,6 @@
 #   必跑串行 (01-02) → 并行 fan-out (03) → 强制 conditional (04) → 可选 conditional (05-07) → 末尾串行 (08) → Agent Team 升级 (09)
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Verify 阶段" 章节 verbatim 7-step 列表 (gsd-verify-work + gsd-progress + code-review 多 agent + 关键模块 gstack /review 强制 + 可选 /qa /cso /design-review + code-simplifier + 4-specialist Agent Team 升级)
-#   - ~/.claude/rules/agent-teams.md Pattern C 多维度审查 (4-specialist 互相质询, NOT fire-and-forget; lead 委派 + cleanup mandatory)
 #   - workflows/capabilities.yaml — gsd-verify-work / gsd-progress / code-review / gstack-review / gstack-qa / gstack-cso / gstack-design-review / code-simplifier / agent-teams-create 9 entry (Phase 2.3 W0.1 SHIPPED)
 #   - workflows/judgments/parallelism-gate.yaml — subagent-default.fires (default fan-out) + agent-teams-upgrade.fires (5 触发 OR-chain; Phase 2.3 W0.2 SHIPPED)
 #   - workflows/defaults.yaml — ralph_max_iterations.verify-work.{01-gsd-verify-work=3, 02-code-review=5, 03-gstack-review=3, 04-code-simplifier=5} (Phase 2.3 W1.2 SHIPPED)
@@ -26,8 +24,8 @@ description: |
   → gstack /review Paranoid Staff Eng 关键模块强制 → 可选 /qa /cso /design-review conditional
   → code-simplifier 末尾串行 → 关键发布/大重构 PR 升级 4-specialist Agent Team Pattern C
   多维度审查 (code-review + gstack-review + gstack-cso + gstack-qa 互相质询, NOT fire-and-forget)。
-  Cleanup mandatory per ~/.claude/rules/agent-teams.md 防呆清单 (SendMessage shutdown_request +
-  TeamDelete) — engine-level wiring, NOT yaml v2 schema scope.
+  Cleanup mandatory (bundled Agent Teams discipline): SendMessage shutdown_request +
+  TeamDelete — engine-level wiring, NOT yaml v2 schema scope.
 
 phases:
   # ============================================================================
@@ -125,9 +123,9 @@ phases:
   # ============================================================================
   # Agent Team 升级 (1 phase) — 关键发布 / 大重构 PR 4-specialist Pattern C
   # ============================================================================
-  # sister ~/.claude/rules/agent-teams.md L42-L52 Pattern C 多维度审查 (≥3 specialist
-  # 需要互相质询而非 fire-and-forget): code-review + gstack-review + gstack-cso + gstack-qa
-  # team_cost < 2 × subagent_cost 估算前置 (开 team 前必估算 per agent-teams.md L34)
+  # Bundled Agent Teams Pattern C — 多维度审查 (≥3 specialist 需要互相质询而非
+  # fire-and-forget): code-review + gstack-review + gstack-cso + gstack-qa
+  # team_cost < 2 × subagent_cost 估算前置 (开 team 前必估算; bundled cost guideline)
   # cleanup mandatory: SendMessage shutdown_request + TeamDelete (engine-level wiring)
   - id: 09-agent-team-multispecialist
     name: agent-team-upgrade (4-specialist Pattern C — 关键发布/大重构 多维度审查 互相质询)

package/workflows/execute-task/phases.yaml

@@ -1,73 +0,0 @@
-# workflows/execute-task/phases.yaml — Phase v2.0-2.4 W1.1 v2 schema upgrade
-# Sister v1 (28L, ADR 0011 errata Phase 2.2 W3 T3.3 ship) → v2 (~60L, T2.4.W1.1).
-#
-# v2 delta (per PLAN.md L327-330 verbatim + RESEARCH § 3.3 + D-09 + D-10 + D-13):
-#   - schema_version: harnessed.workflow.v2 (sister Phase 2.2 schemaVersion 7 surface)
-#   - 02-code:    on[] mattpocock route by condition (tdd-gate / grill-with-docs / zoom-out)
-#   - 03-test:    on[] diagnose if test_fail
-#   - 04-deliver: capability + args + gate + parallelism + on[] + fallback (R20.10 explicit halt)
-#
-# Per-phase model tier (ADR 0011 errata / intel CD-2 § 第 4 条) — unchanged from v1.
-# Default table sourced from `.planning/intel/omc-comparison.md` § CD-2 (phase 2.2 W3 T3.3).
-# Override via CLI: `--model-tier inherit` (B-10 escape hatch).
-#
-# capability template — '{{ capabilities.<name>.cmd }}' resolves at workflow runtime
-# (sister D-02 gstack_prefix interpolation pattern from workflows/plan-feature/workflow.yaml).
-# gate / parallelism — 4-level ref 'judgments.<file>.<gate>.fires' pre-resolves via
-# T2.3.W0.4 judgmentResolver BEFORE expr-eval (per src/workflow/schema/workflow.ts L18-19).
-
-schema_version: harnessed.workflow.v2
-workflow: execute-task
-description: 子任务执行 workflow — 4-phase 真接 ralph-loop SDK + tdd-gate conditional + mattpocock route by condition
-phases:
-  - id: 01-clarify
-    name: brainstorming
-    upstream: superpowers brainstorming
-    capability: '{{ capabilities.superpowers-brainstorming.cmd }}'
-    model: opus
-    max_iterations: '{{ defaults.ralph_max_iterations.execute-task.01-clarify }}'
-    gate: judgments.subtask-gate.brainstorming.fires
-
-  - id: 02-code
-    name: code (karpathy 心法 always-on + mattpocock conditional route)
-    upstream: karpathy
-    model: sonnet
-    max_iterations: '{{ defaults.ralph_max_iterations.execute-task.02-code }}'
-    on:
-      - if: 'judgments.tdd-gate.tdd-strongly-suggested.fires'
-        invoke: '{{ capabilities.tdd.cmd }}'
-      - if: 'phase.spec_ambiguous == true'
-        invoke: '{{ capabilities.grill-with-docs.cmd }}'
-      - if: 'phase.unfamiliar_module == true'
-        invoke: '{{ capabilities.zoom-out.cmd }}'
-
-  - id: 03-test
-    name: test (conditional TDD + diagnose on fail)
-    upstream: superpowers TDD
-    capability: '{{ capabilities.tdd.cmd }}'
-    model: sonnet
-    max_iterations: '{{ defaults.ralph_max_iterations.execute-task.03-test }}'
-    on:
-      - if: 'test_fail == true'
-        invoke: '{{ capabilities.diagnose.cmd }}'
-
-  - id: 04-deliver
-    name: deliver (ralph-loop COMPLETE gate + max-iter fallback)
-    upstream: ralph-loop
-    capability: '{{ capabilities.ralph-loop.cmd }}'
-    model: haiku
-    args:
-      completion_promise: COMPLETE
-      max_iterations: '{{ defaults.ralph_max_iterations.execute-task.04-deliver }}'
-    gate: judgments.parallelism-gate.fires
-    parallelism: judgments.parallelism-gate.ralph-loop-wrapper.fires
-    on:
-      - if: 'subtask.lines >= 20 and subtask.type != "single_command_query"'
-        invoke: '{{ capabilities.ralph-loop.cmd }}'
-      - if: 'subtask.lines < 20 or subtask.type == "single_command_query"'
-        action: skip
-    fallback:
-      max_iterations_exceeded:
-        action: emit_warning_and_halt
-        message: '⚠️ ralph-loop max-iterations ({{ args.max_iterations }}) exceeded for execute-task 04-deliver. Sub-task likely incomplete — see workflow engine catch handler for manual options.'
-        exit_code: 1