harnessed 3.4.4 → 3.6.0

package/workflows/plan/phase/SKILL.md

@@ -3,7 +3,7 @@ name: plan-phase
 description: |
   Stage ②.b 计划层 plan sub-workflow — GSD /gsd-plan-phase Wave A research + Wave B planner +
   Wave C plan-checker + planning-with-files Claude Code plugin /plan 持久化 task_plan.md +
-  progress.md (sister ~/.claude/CLAUDE.md "Plan 阶段 GSD + planning-with-files")。Stage ② 铁律:
+  progress.md (bundled Plan-stage cadence: GSD + planning-with-files)。Stage ② 铁律:
   dual capability (GSD orchestration + planning-with-files plugin)。schema_version:
   harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available [gsd-plan-phase,
   planning-with-files] + 2 phases (01-gsd-plan + 02-persist)。Triggered by harnessed CLI
@@ -34,8 +34,8 @@ claude-code-plugin /plan + Pattern A sub-workflow ship)。
 Sister `workflows/capabilities.yaml` entries:
 - `gsd-plan-phase` — Bucket 2 (impl: gsd, cmd: /gsd-plan-phase)
 - `planning-with-files` — Bucket 4 (impl: claude-code-plugin, cmd: /plan;
-  plugin_path: ~/.claude/plugins/cache/planning-with-files/...; outputs:
-  task_plan.md + progress.md + findings.md)
+  requires the `planning-with-files` Claude Code plugin to be installed via the
+  Claude Code plugin marketplace; outputs: task_plan.md + progress.md + findings.md)
 
 ## Stage ② 铁律 — dual capability
 
@@ -72,6 +72,5 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 
 - D-04 Stage ② Plan 二层 (架构 / 计划)
 - D-15 Q-AUDIT-5a planning-with-files claude-code-plugin reframe (NOT npm-sdk)
-- ~/.claude/CLAUDE.md "Plan 阶段 GSD + planning-with-files"
 - workflows/capabilities.yaml — gsd-plan-phase / planning-with-files (Bucket 4)
 - workflows/defaults.yaml — ralph_max_iterations.plan-phase.* values (W2.2 backfill)

package/workflows/plan/phase/workflow.yaml

@@ -1,9 +1,9 @@
 # workflows/plan/phase/workflow.yaml — Phase v3.0-3.4 W0 T3.4.W0.5
 #
 # Stage ②.b 计划层 sub-workflow — GSD /gsd-plan-phase Wave A research + Wave B planner +
-# Wave C plan-checker + planning-with-files /plan 持久化 task_plan.md (sister
-# ~/.claude/CLAUDE.md "Plan 阶段 GSD + planning-with-files")。Stage ② 铁律: dual capability
-# (gsd-plan-phase + planning-with-files /plan invokes)。
+# Wave C plan-checker + planning-with-files /plan 持久化 task_plan.md
+# (bundled Plan-stage cadence: GSD + planning-with-files).
+# Stage ② 铁律: dual capability (gsd-plan-phase + planning-with-files /plan invokes)。
 #
 # Sister refs:
 #   - workflows/capabilities.yaml — gsd-plan-phase / planning-with-files

package/workflows/plan-feature/SKILL.md

@@ -54,9 +54,9 @@ to brainstorm or planning (D-04 PUSH 任 1 phase 转换前 read = vetoed → 全
 
 ### Phase 5 planning-with-files plugin 真接 (Q-AUDIT-5a LOCKED Option A)
 
-05-persist invokes the **Claude Code plugin** slash command `/plan` via plugin
-cache at `~/.claude/plugins/cache/planning-with-files/planning-with-files/2.34.0/`
-(verified 2026-05-20). The plugin generates 3 markdown files in
+05-persist invokes the **Claude Code plugin** slash command `/plan`. Requires
+the `planning-with-files` Claude Code plugin to be installed via the Claude Code
+plugin marketplace. The plugin generates 3 markdown files in
 `.planning/<phase-id>/`:
 
 - `task_plan.md` — 主计划 (task 列表 + 文件路径 + 依赖顺序 + 验收标准)
@@ -84,7 +84,7 @@ harnessed plan-feature --task "<text>" --apply
 ## Forward-looking note
 
 The `trigger_phrases:` frontmatter is active after `harnessed setup` copies this
-SKILL.md to `~/.claude/skills/plan-feature/` — Claude Code then loads the slash
+SKILL.md to `<claude-home>/skills/plan-feature/` — Claude Code then loads the slash
 command `/plan-feature` automatically (Gap B fix — v1.0.2).
 
 ## References

package/workflows/research/SKILL.md

@@ -16,7 +16,7 @@ phases content (01-fan-out + 02-synth) verbatim reused from v2 SHIPPED unchanged
 
 | # | Phase | Upstream | Capability | Model | Description |
 |---|-------|----------|-----------|-------|-------------|
-| 01 | `01-fan-out` | web-search | (route-by-subtask) | sonnet | 3 source fan-out (Tavily MCP / Exa MCP / ctx7 CLI per ~/.claude/rules/web-search.md + context7.md routing) |
+| 01 | `01-fan-out` | web-search | (route-by-subtask) | sonnet | 3 source fan-out (Tavily MCP / Exa MCP / ctx7 CLI per bundled web-search + context7 routing) |
 | 02 | `02-synth` | gsd | `gsd-discuss-phase` | opus | GSD discuss-phase aggregate + dedup + reconcile |
 
 ## Capability refs
@@ -30,16 +30,16 @@ Sister `workflows/capabilities.yaml` entries:
 ## Invocation
 - Slash command: `/research <topic>` (after `harnessed setup`)
 
-## Routing rules (sister ~/.claude/rules/web-search.md)
+## Routing rules (bundled web-search routing — `workflows/judgments/web-search-routing.yaml`)
 - 描述式查询 ("找一篇对比 X 和 Y 的博客") → Exa MCP
 - 学术 / 论文 → Exa MCP
-- 库 / API 文档 → ctx7 CLI (per ~/.claude/rules/context7.md)
+- 库 / API 文档 → ctx7 CLI
 - 关键词 / 时效内容 → Tavily MCP (默认)
 - 抓整站 / 站点结构 → Tavily crawl/map
 
 ## How to invoke
 
-**Preferred path** (master orchestrator): dispatch to the per-sub-workflow slash commands in the order this stage prescribes. Each sub command lives at `~/.claude/commands/<sub-name>.md` with its own dual-path fallback.
+**Preferred path** (master orchestrator): dispatch to the per-sub-workflow slash commands in the order this stage prescribes. Each sub command lives at `<claude-home>/commands/<sub-name>.md` (installed by `harnessed setup`) with its own dual-path fallback.
 
 **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:
 
@@ -64,7 +64,7 @@ Sister `workflows/capabilities.yaml` entries:
 
 (Role prompt is self-contained — works even when the upstream `specialist` user-skill / plugin isn't installed.)
 
-(Sister `~/.claude/commands/research.md` is also generated by `harnessed setup` so `/research` is a real platform slash command — both files carry the same dual-path instruction. Previous v3.4.x `harnessed research --apply` CLI claims are removed; that subcommand was never implemented.)
+(`harnessed setup` also installs a `research` Claude Code slash command at `<claude-home>/commands/research.md` so `/research` is a real platform slash command — both files carry the same dual-path instruction. Previous v3.4.x `harnessed research --apply` CLI claims are removed; that subcommand was never implemented.)
 
 ## How to invoke
 

package/workflows/research/workflow.yaml

@@ -2,8 +2,8 @@
 # (v2 19L → v3 ~25L schema bump per RESEARCH-workflows Area 2 Standalone section)
 #
 # Standalone Stage ① alternate — 多源调研 Tavily MCP (默认关键词) + Exa MCP (描述式 / 学术)
-# + ctx7 CLI (库 API 文档) fan-out + GSD discuss synth aggregate; sister
-# ~/.claude/rules/web-search.md + context7.md routing 机器化 per R20.7 + D-08。
+# + ctx7 CLI (库 API 文档) fan-out + GSD discuss synth aggregate; bundled web-search +
+# context7 routing rules (workflows/judgments/web-search-routing.yaml) 机器化 per R20.7 + D-08。
 #
 # v2 → v3 字段 delta (W1.1 schema bump scope):
 #   BUMP `schema_version: harnessed.workflow.v3`              (17th surface — sister Phase 3.3 W0.11)
@@ -26,8 +26,8 @@ schema_version: harnessed.workflow.v3
 workflow: research
 description: |
   Standalone Stage ① alternate — 多源调研 Tavily MCP (默认关键词) + Exa MCP (描述式 /
-  学术) + ctx7 CLI (库 API 文档) fan-out + GSD discuss synth aggregate; sister
-  ~/.claude/rules/web-search.md + context7.md routing 机器化 per R20.7 + D-08。
+  学术) + ctx7 CLI (库 API 文档) fan-out + GSD discuss synth aggregate; bundled
+  web-search + context7 routing rules 机器化 per R20.7 + D-08。
 
 disciplines_applied: [karpathy, output-style, language, operational, priority, protocols]
 tools_available: [tavily-mcp, exa-mcp, ctx7, gsd-discuss-phase]

package/workflows/retro/SKILL.md

@@ -2,8 +2,8 @@
 name: retro
 description: |
   Standalone post-④ Verify retrospective workflow — gstack /retro 经验教训 / 决策 / lessons
-  系统总结 (项目 / 里程碑结束可选, sister ~/.claude/CLAUDE.md "项目 / 里程碑结束: 可选跑
-  /retro 总结" verbatim) + planning-with-files RETROSPECTIVE.md 持久化 (sister Phase
+  系统总结 (项目 / 里程碑结束可选, bundled milestone-close retrospective cadence)
+  + planning-with-files RETROSPECTIVE.md 持久化 (sister Phase
   v2.0-2.5 RETROSPECTIVE pattern)。Capability ref retro-gstack alias suffix per Pattern A
   E.2 LOCK (NOT bare retro 避免 standalone workflow / capability namespace 冲突)。
   schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available
@@ -66,7 +66,6 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 - D-04 NEW v3 standalone workflow (research v3 bump + retro NEW)
 - Pattern A E.2 LOCK — 2 alias suffix `-gstack` 解决 namespace 冲突 (retro-gstack + investigate-gstack)
 - Pattern A reconcile D.2 — gstack 30 optional naming bare 例外
-- ~/.claude/CLAUDE.md "项目 / 里程碑结束: 可选跑 /retro 总结" verbatim
 - workflows/capabilities.yaml — retro-gstack (alias suffix) + planning-with-files
 - workflows/defaults.yaml — ralph_max_iterations.retro.* values (W2.2 backfill)
 - sister Phase v2.0-2.5 RETROSPECTIVE.md sink pattern

package/workflows/retro/workflow.yaml

@@ -1,11 +1,10 @@
 # workflows/retro/workflow.yaml — Phase v3.0-3.4 W1 T3.4.W1.2 NEW
 #
 # Standalone post-④ Verify — gstack /retro 经验教训总结 (项目 / 里程碑结束可选,
-# sister ~/.claude/CLAUDE.md "项目 / 里程碑结束: 可选跑 /retro 总结" verbatim)。
+# bundled milestone-close retrospective cadence).
 # Sink RETROSPECTIVE.md (sister Phase v2.0-2.5 RETROSPECTIVE pattern)。
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "项目 / 里程碑结束: 可选跑 /retro 总结" verbatim
 #   - workflows/capabilities.yaml — retro-gstack (Bucket 7 gstack optional alias suffix per
 #     Pattern A E.2 LOCK, 解决 namespace 冲突 — retro carrier 自带 gstack 字符串 NOT prefix policy)
 #   - workflows/capabilities.yaml — planning-with-files (Bucket 4 核心 capability /plan)

package/workflows/role-prompts.yaml

@@ -1,7 +1,8 @@
 # <packageRoot>/workflows/role-prompts.yaml — harnessed v3.4.3 role-prompt registry.
 #
 # Per-sub-workflow metadata consumed by `src/cli/lib/generateCommands.ts` to
-# emit `~/.claude/commands/<slash-name>.md` files at `harnessed setup` time.
+# emit `<claude-home>/commands/<slash-name>.md` files at `harnessed setup`
+# time (Claude Code slash command install path).
 #
 # Each entry describes:
 #   primary_cap:    Which capability key the "preferred path" invokes (the
@@ -13,9 +14,17 @@
 #                   upstream gstack expert prompts where available (cited inline).
 #                   Self-contained — works even when upstream user-skill missing.
 #   severity:       Severity scale label used in the report format.
-#   description:    YAML frontmatter `description` for ~/.claude/commands/<x>.md.
+#   description:    YAML frontmatter `description` for <claude-home>/commands/<x>.md.
 #
 # Karpathy simplicity: 1 small yaml beats 23 hardcoded strings in TS.
+#
+# Upstream attributions (v3.6.0 Phase 1):
+#   Portions of the `task-clarify` / `task-code` / `discuss-subtask` entries
+#   below are paraphrased from https://github.com/mattpocock/skills
+#   (MIT License, commit b8be62ffacb0118fa3eaa29a0923c87c8c11985c). The full
+#   upstream license is preserved at
+#   .planning/v3.6.0/mattpocock-source/LICENSE and a project-wide attribution
+#   summary is in THIRD-PARTY-NOTICES.md at the repo root.
 
 schema_version: harnessed.role-prompts.v1
 
@@ -45,7 +54,7 @@ prompts:
     specialist: "Stage 1 discuss dispatcher"
     responsibility: |
       Independently evaluate three clarification layers (strategic / phase /
-      subtask) per ~/.claude/CLAUDE.md "澄清/审查触发判据" and run only the
+      subtask) per the bundled 3-tier clarification gate and run only the
       layers whose gate fires. Each layer's command is `/discuss-strategic`,
       `/discuss-phase`, `/discuss-subtask`.
     checklist: []
@@ -176,6 +185,16 @@ prompts:
       Generate ≥2 implementation approaches for a single subtask and compare
       tradeoffs. Fires when core algorithm / data structure / API contract /
       high error-cost. Skip pure CRUD or single-obvious-path tasks.
+
+      # grill-me methodology paraphrased from mattpocock/skills (MIT, b8be62f)
+      # Source: skills/productivity/grill-me/SKILL.md
+      # When the user wants to stress-test a plan or asks to be grilled,
+      # interview them relentlessly about every aspect until shared
+      # understanding is reached. Walk down each branch of the decision tree,
+      # resolving dependencies between decisions one at a time. For each
+      # question, provide your recommended answer. Ask questions ONE at a
+      # time. If a question can be answered by exploring the codebase,
+      # explore the codebase instead of asking.
     checklist:
       - "State the subtask in one sentence; confirm scope with user if ambiguous"
       - "Produce 2-4 distinct approaches (not just '2 flavors of the same idea')"
@@ -183,8 +202,11 @@ prompts:
       - "Recommend one with 1-2 line reason; flag risks of the chosen path"
       - "Output a `findings.md` block the implementer can paste into the task"
       - "If options collapse to one (others clearly bad), say so and exit fast"
+      # grill-me additional checklist (paraphrased from mattpocock/skills)
+      - "Grill mode: walk the decision tree branch-by-branch, ONE question at a time, with your recommended answer"
+      - "Prefer codebase exploration over asking when a question can be answered from code"
     severity: "recommended / acceptable / rejected"
-    description: "Generate 2-4 subtask approaches with tradeoffs and recommend one (brainstorming)."
+    description: "Generate 2-4 subtask approaches with tradeoffs and recommend one (brainstorming + grill-me on stress-test requests)."
 
   # ============================================================================
   # plan-* (2 subs)
@@ -238,6 +260,16 @@ prompts:
       Surface ambiguity in a single subtask spec by asking ONE focused
       question at a time. Fires when ≥2 approaches / core algorithm / API
       contract / high error-cost. Skip if subtask is CRUD or already obvious.
+
+      # grill-with-docs methodology paraphrased from mattpocock/skills (MIT, b8be62f)
+      # Source: skills/engineering/grill-with-docs/SKILL.md
+      # When ambiguity overlaps with existing project docs / ADRs, run a
+      # grill-with-docs cycle: pressure-test the plan against the project's
+      # domain language (CONTEXT.md), sharpen terminology mismatches inline,
+      # and update ADRs as decisions crystallise. Challenge term conflicts
+      # immediately; sharpen vague/overloaded terms by proposing a canonical
+      # name; cross-reference user claims with code and surface contradictions.
+      # Output is BOTH a refined spec AND a doc-diff (CONTEXT.md / docs/adr/*.md).
     checklist:
       - "Read the subtask description; restate it in your own words to confirm"
       - "List every assumption you would make; flag the ones the user must confirm"
@@ -245,6 +277,11 @@ prompts:
       - "Stop asking when you have enough to write 80% of the code without guessing"
       - "Record the resolved spec at the top of the subtask file before implementing"
       - "If `phase.spec_ambiguous == true AND phase.no_docs == true`, request grill-me"
+      # grill-with-docs additional checklist (paraphrased from mattpocock/skills)
+      - "Cross-reference each assumption against CONTEXT.md domain language; flag terminology drift immediately"
+      - "Sharpen vague/overloaded terms (e.g. 'account' → Customer vs User) by proposing a canonical name"
+      - "If a decision crystallises mid-grill, draft the ADR delta inline (don't defer)"
+      - "Output BOTH the refined spec AND any doc-diff (CONTEXT.md / docs/adr/*.md)"
     severity: "blocking-question / nice-to-know / resolved"
     description: "Clarify subtask spec one question at a time (brainstorming + grill-with-docs on ambiguity)."
 
@@ -266,8 +303,17 @@ prompts:
       - "No speculative abstractions (no 'just in case' generics)"
       - "Edit with surgical precision: full path, exact selectors, no broad rewrites"
       - "Update progress.md before declaring done (planning-with-files `/plan`)"
+      # zoom-out methodology paraphrased from mattpocock/skills (MIT, b8be62f)
+      # Source: skills/engineering/zoom-out/SKILL.md
+      - "zoom-out: when unfamiliar with an area, go up a layer of abstraction and map the relevant modules and callers using the project's CONTEXT.md domain glossary vocabulary"
+      # improve-codebase-architecture methodology paraphrased from mattpocock/skills (MIT, b8be62f)
+      # Source: skills/engineering/improve-codebase-architecture/SKILL.md
+      - "improve-arch: hunt deepening opportunities — modules whose interface is nearly as complex as their implementation are shallow; deep modules hide a lot of behaviour behind a small interface"
+      - "improve-arch deletion test: imagine deleting the module — if complexity vanishes it was a pass-through (delete it); if complexity reappears across N callers it was earning its keep (keep / deepen)"
+      - "improve-arch: name candidates using CONTEXT.md domain vocabulary (e.g. 'the Order intake module', not 'FooBarHandler'); if a candidate contradicts an existing ADR, only surface it when the friction is real enough to revisit the ADR"
+      - "improve-arch: present candidates as a before/after report and let the user pick which to explore before designing interfaces"
     severity: "needs-fix / done / blocked"
-    description: "Implement a subtask under karpathy 4 心法 (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven); ≤200 LOC per file."
+    description: "Implement a subtask under karpathy 4 心法 (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven); ≤200 LOC per file. zoom-out for unfamiliar areas; improve-codebase-architecture for shallow-module deepening audits."
 
   task-test:
     primary_cap: "tdd"

package/workflows/task/auto/SKILL.md

@@ -22,7 +22,7 @@ trigger_phrases:
 ## Overview
 
 4-stage cadence Stage ③ master orchestrator delegating to 4 sequential sub-workflows
-per subtask (per ~/.claude/CLAUDE.md "Execute 阶段" 节 + karpathy 心法 always-on):
+per subtask (bundled Execute-stage cadence + karpathy 心法 always-on):
 
 | order | sub | gate ref | mode | when fires |
 | ----- | --- | -------- | ---- | ---------- |
@@ -39,7 +39,7 @@ mode delegate carries explicit `order`。Each subtask 入口走一次此 master
 
 ralph-loop 是正交 wrapper, 套在 deliver sub 的 01-deliver phase 外层保 completion-promise
 verbatim "COMPLETE" (R20.10)。任何执行单元 (subagent / team / 主 session) 都可外层套 ralph-loop
-保 completion-promise (sister ~/.claude/CLAUDE.md 子任务并行执行机制 "正交 wrapper")。
+保 completion-promise (bundled subagent vs Agent Teams routing — orthogonal wrapper rule).
 
 ## Capability refs
 
@@ -76,6 +76,5 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 - D-01 master orchestrator delegation pattern
 - D-02 bare slash cmd convention (ADR 0030 namespace policy LOCK)
 - D-10 ralph-loop orthogonal wrapper
-- ~/.claude/CLAUDE.md "Execute 阶段" 节 verbatim (karpathy 心法 + mattpocock 招式 + ralph-loop COMPLETE)
 - workflows/judgments/{subtask-gate,tdd-gate}.yaml — brainstorming + tdd-strongly-suggested triggers
 - workflows/task/{clarify,code,test,deliver}/workflow.yaml — 4 sub-workflow Phase 3.4 SHIPPED

package/workflows/task/auto/workflow.yaml

@@ -1,13 +1,12 @@
 # workflows/task/auto/workflow.yaml — Phase v3.0-3.5 W1 T3.5.W1.3
 #
 # Stage ③ Task master orchestrator — 串行 invoke 4 sub per subtask (clarify → code → test → deliver)
-# per ~/.claude/CLAUDE.md "Execute 阶段" 节 + RESEARCH-workflows § Area 2。
+# per bundled Execute-stage cadence + RESEARCH-workflows § Area 2。
 # ralph-loop COMPLETE wrapper 在 deliver phase 内 (D-10 orthogonal wrapper not master concern)。
 # tdd-gate conditional fire on test sub (sister task/test/workflow.yaml gate
 # judgments.tdd-gate.tdd-strongly-suggested.fires)。
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Execute 阶段 (GSD orchestration + superpowers 子任务执行)" 节
 #   - workflows/judgments/subtask-gate.yaml — brainstorming trigger (clarify)
 #   - workflows/judgments/tdd-gate.yaml — tdd-strongly-suggested trigger (test conditional)
 #   - workflows/task/{clarify,code,test,deliver}/workflow.yaml — 4 sub-workflow Phase 3.4 SHIPPED
@@ -27,7 +26,7 @@ description: |
   Stage ③ Task master orchestrator — 串行 invoke 4 sub per subtask (clarify → code → test → deliver);
   ralph-loop COMPLETE wrapper 在 deliver phase 内 (D-10 orthogonal wrapper not master concern)。
   tdd-gate conditional fire on test sub (核心业务 / 算法 / 数据处理 / 回归 risk high / reliability
-  required, 6 fires_when OR-chain per ~/.claude/CLAUDE.md)。execute-task 每个 subtask 入口走一次。
+  required, 6 fires_when OR-chain; bundled tdd-gate judgment)。execute-task 每个 subtask 入口走一次。
 
 disciplines_applied: [karpathy, output-style, language, operational, priority, protocols]
 tools_available:

package/workflows/task/clarify/SKILL.md

@@ -74,7 +74,6 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 - D-05 — phase-level `invokes_tools` conditional tool fire
 - D-04 — `gate` 4-level ref pre-resolved by `judgmentResolver`
 - D-02 — SKILL.md `name:` bare slash cmd (`task-clarify` NOT `task/clarify`) per ADR 0030
-- ~/.claude/CLAUDE.md "Execute 阶段" 节 brainstorming 子任务层判据
 - `workflows/judgments/subtask-gate.yaml` triggers.brainstorming
 - `workflows/capabilities.yaml` — superpowers-brainstorming + grill-with-docs entries
 - `workflows/defaults.yaml` — ralph_max_iterations.task-clarify.* values (T3.4.W2.2 followup)

package/workflows/task/code/SKILL.md

@@ -56,9 +56,9 @@ Phase 01-code 按 phase fact context 条件性 fire 3 mattpocock 招式:
 
 02-progress invokes the **Claude Code plugin** slash command `/plan` to update
 `progress.md` in `.planning/<phase-id>/` — 跟踪 subtask 完成 / blocked / next step
-per CLAUDE.md "跨 session 恢复" 模式 + R20.6 Manus-style 持久化。Plugin path
-verified at `~/.claude/plugins/cache/planning-with-files/planning-with-files/2.34.0/`
-(2026-05-20).
+per bundled "跨 session 恢复" 模式 + R20.6 Manus-style 持久化. Requires the
+`planning-with-files` Claude Code plugin (install via Claude Code plugin
+marketplace).
 
 ## How to invoke
 
@@ -80,7 +80,6 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 - D-05 — phase-level `invokes_tools` conditional tool fire
 - D-15 + Q-AUDIT-5a — planning-with-files = Claude Code plugin slash cmd `/plan`
 - D-02 — SKILL.md `name:` bare slash cmd (`task-code` NOT `task/code`) per ADR 0030
-- ~/.claude/CLAUDE.md "Execute 阶段" 节 karpathy 心法 + mattpocock 招式按需召唤
 - `workflows/disciplines/karpathy.yaml` — 4 心法 + ≤200L hard limit 等 rules (L0 substrate)
 - `workflows/capabilities.yaml` — zoom-out / improve-codebase-architecture / diagnose / planning-with-files entries
 - `workflows/defaults.yaml` — ralph_max_iterations.task-code.* values (T3.4.W2.2 followup)

package/workflows/task/code/workflow.yaml

@@ -8,7 +8,6 @@
 #
 # Sister refs:
 #   - .planning/phase-v3.0-3.2/RESEARCH-workflows.md § Area 2 task/code sub yaml example
-#   - ~/.claude/CLAUDE.md "Execute 阶段" 节 karpathy 4 心法 + mattpocock 招式按需召唤
 #   - workflows/capabilities.yaml zoom-out + improve-codebase-architecture + diagnose +
 #     planning-with-files (Phase 2.3 W0.1 SHIPPED)
 #   - workflows/disciplines/karpathy.yaml (Phase 3.3 W0.4 SHIPPED, L0 substrate always-on)

package/workflows/task/deliver/SKILL.md

@@ -79,8 +79,8 @@ ref / ✅ R20.10 explicit max_iterations_exceeded handler。
 
 02-progress-mark invokes Claude Code plugin slash cmd `/plan` to mark subtask complete
 in `progress.md` — sister Phase 01-code progress update pattern, last call in Stage
-③ task chain。Plugin path `~/.claude/plugins/cache/planning-with-files/
-planning-with-files/2.34.0/` verified (2026-05-20)。
+③ task chain. Requires `planning-with-files` Claude Code plugin (install via
+Claude Code plugin marketplace).
 
 ## How to invoke
 
@@ -100,14 +100,11 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 
 - D-09 — L0 Discipline Substrate always-on (6 disciplines)
 - D-10 — ralph-loop 真接 SDK wrapper (NOT mock reference; v0.2.0 ship)
-- D-11 — Agent Teams 升级 5 触发 OR-chain per ~/.claude/rules/agent-teams.md
+- D-11 — Agent Teams 升级 5 触发 OR-chain per bundled parallelism-gate rules
 - R20.10 — ralph-loop max_iterations_exceeded explicit emit_warning_and_halt
   (acceptance c "NOT silent abort"); ralph-loop 正交 wrapper wraps 3 mode
 - D-02 — SKILL.md `name:` bare slash cmd (`task-deliver` NOT `task/deliver`) per ADR 0030
 - ADR 0011 — SDK + ralph-loop integration v0.2.0 baseline
-- ~/.claude/CLAUDE.md "Execute 阶段" 节 ralph-loop 至 verbatim COMPLETE +
-  `子任务并行执行机制` Agent Teams 升级路由
-- ~/.claude/rules/agent-teams.md — Pattern A/B/C + 防呆清单 cleanup mandatory
 - `workflows/judgments/parallelism-gate.yaml` triggers.ralph-loop-wrapper +
   agent-teams-upgrade + subagent-default + main-session-fallback
 - `workflows/capabilities.yaml` — ralph-loop + agent-teams-{create,send-message,shutdown}

package/workflows/task/deliver/workflow.yaml

@@ -3,8 +3,8 @@
 #
 # Stage ③.d 子任务交付 — ralph-loop COMPLETE wrapper 保 completion-promise verbatim
 # "COMPLETE" (R20.10 + D-10 v0.2.0 ralph-loop SDK pattern)。Parallelism: subagent
-# default fan-out OR Agent Teams 升级 (5 触发 OR-chain per ~/.claude/rules/agent-teams.md
-# + D-11)。02-progress-mark: planning-with-files /plan 更新 progress.md 标记完成。
+# default fan-out OR Agent Teams 升级 (5 触发 OR-chain per bundled Agent Teams
+# routing + D-11)。02-progress-mark: planning-with-files /plan 更新 progress.md 标记完成。
 #
 # Brief enforcement (W0.9 spec MUST include):
 #   - ralph-loop completion_promise = COMPLETE (R20.10 verbatim acceptance string)
@@ -20,8 +20,9 @@
 #   - workflows/judgments/parallelism-gate.yaml triggers.ralph-loop-wrapper (Phase 2.3 W0.2 SHIPPED)
 #   - workflows/capabilities.yaml ralph-loop + agent-teams-{create,send-message,shutdown} +
 #     planning-with-files (Phase 2.3 W0.1 + 3.3 W0.2 SHIPPED)
-#   - ~/.claude/rules/agent-teams.md 5 升级触发 OR-chain (teammate_send_message_needed /
-#     subagent_context_overflow / shared_task_list / opposing_hypothesis_debate / fullstack_three_way)
+#   - workflows/judgments/parallelism-gate.yaml — 5 升级触发 OR-chain
+#     (teammate_send_message_needed / subagent_context_overflow / shared_task_list /
+#     opposing_hypothesis_debate / fullstack_three_way)
 #   - src/workflow/schema/workflow.ts WorkflowSchemaV3 FallbackMaxIterationsExceeded
 #     Type.Literal('emit_warning_and_halt') (Phase 3.3 W0.5 SHIPPED)
 #
@@ -33,11 +34,11 @@ workflow: task-deliver
 description: |
   Stage ③.d 子任务交付 — ralph-loop COMPLETE wrapper 保 completion-promise verbatim
   "COMPLETE" (R20.10 + D-10 v0.2.0 ralph-loop SDK pattern)。Parallelism subagent
-  default fan-out OR Agent Teams 升级 (5 触发 OR-chain per ~/.claude/rules/agent-teams.md
+  default fan-out OR Agent Teams 升级 (5 触发 OR-chain per bundled Agent Teams routing
   + D-11)。R20.10 explicit max_iterations_exceeded handler: emit_warning_and_halt
   exit_code 1 (NOT silent abort, sister Phase 2.4 W1.2 fallbackHandlers.ts engine.ts
   wire pattern)。Cleanup mandatory when Agent Teams escalation path fires (shutdown_request
-  + TeamDelete per agent-teams.md 防呆清单)。
+  + TeamDelete per bundled Agent Teams cleanup discipline)。
 
 disciplines_applied: [karpathy, output-style, language, operational, priority, protocols]
 tools_available:

package/workflows/task/test/SKILL.md

@@ -84,7 +84,6 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 - D-05 — phase-level `invokes_tools` conditional tool fire
 - D-13 — tdd capability 2 impl 候选 alias (superpowers 主 + mattpocock /tdd 备)
 - D-02 — SKILL.md `name:` bare slash cmd (`task-test` NOT `task/test`) per ADR 0030
-- ~/.claude/CLAUDE.md "Execute 阶段" TDD 强烈建议开启 6 触发 + 3 跳过
 - `workflows/judgments/tdd-gate.yaml` triggers.tdd-strongly-suggested
 - `workflows/capabilities.yaml` — tdd (superpowers + mattpocock alias) + diagnose entries
 - `workflows/defaults.yaml` — ralph_max_iterations.task-test.* values (T3.4.W2.2 followup)

package/workflows/task/test/workflow.yaml

@@ -9,7 +9,6 @@
 #   - .planning/phase-v3.0-3.2/RESEARCH-workflows.md § Area 2 task/test sub yaml example
 #   - workflows/judgments/tdd-gate.yaml triggers.tdd-strongly-suggested (Phase 2.3 W0.2 SHIPPED)
 #   - workflows/capabilities.yaml tdd + diagnose (Phase 2.3 W0.1 SHIPPED + D-13 alias)
-#   - ~/.claude/CLAUDE.md "Execute 阶段" 节 TDD 强烈建议开启 6 触发 + 3 跳过
 #   - src/workflow/schema/workflow.ts WorkflowSchemaV3 (Phase 3.3 W0.5 SHIPPED)
 #
 # Brief enforcement:
@@ -24,7 +23,7 @@ workflow: task-test
 description: |
   Stage ③.c 子任务测试 — superpowers TDD red-green-refactor 强制 (核心业务 / 算法 /
   数据处理 / 回归 risk high / reliability required, 6 fires_when OR-chain per
-  ~/.claude/CLAUDE.md), 其他可选 mattpocock /tdd alias。Conditional diagnose
+  bundled tdd-gate judgment), 其他可选 mattpocock /tdd alias。Conditional diagnose
   invoke when test_fail (D-05 invokes_tools phase-level fire). Gate:
   judgments.tdd-gate.tdd-strongly-suggested.fires (4-level ref, pre-resolved per D-04)。
 

package/workflows/verify/auto/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: verify
 description: |
-  Stage ④ Verify master orchestrator — 7 sub conditional per ~/.claude/CLAUDE.md "Verify 阶段"
-  verbatim: progress 必跑 → code-review 并行 → paranoid 关键模块强制 → qa/security/design 可选
+  Stage ④ Verify master orchestrator — 7 sub conditional per bundled Verify-stage cadence:
+  progress 必跑 → code-review 并行 → paranoid 关键模块强制 → qa/security/design 可选
   并行 conditional → simplify 末尾 → multispec 关键发布 Pattern C 4-specialist Agent Team。
   schema_version: harnessed.workflow.v3 with delegates_to (7 sub: progress serial order 1 +
   5 parallel conditional + simplify serial order 99) + disciplines_applied (6 default) +
@@ -21,8 +21,8 @@ trigger_phrases:
 ## Overview
 
 4-stage cadence Stage ④ master orchestrator delegating to 7 sub-workflows
-(per ~/.claude/CLAUDE.md "Verify 阶段" 节 verbatim — 9-phase composition compressed
-into 7 sub delegation via stage-routing.yaml):
+(bundled Verify-stage cadence — 9-phase composition compressed into 7 sub delegation
+via stage-routing.yaml):
 
 | order/mode | sub | gate ref | mode | when fires |
 | ---------- | --- | -------- | ---- | ---------- |
@@ -83,8 +83,7 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 - D-01 master orchestrator delegation pattern
 - D-02 bare slash cmd convention (ADR 0030 namespace policy LOCK)
 - D-12 gstack 治理关卡 ref (paranoid / qa / security / design subs)
-- ~/.claude/CLAUDE.md "Verify 阶段" 节 verbatim
-- ~/.claude/rules/agent-teams.md Pattern C 多维度审查 (multispec sub 4-specialist 互相质询)
+- workflows/judgments/parallelism-gate.yaml — Pattern C 多维度审查 (multispec sub 4-specialist 互相质询)
 - workflows/judgments/stage-routing.yaml — verify-* 6 triggers (7 sub delegation)
 - workflows/verify/{progress,code-review,paranoid,qa,security,design,simplify,multispec}/workflow.yaml
   — 8 sub-workflow Phase 3.4 SHIPPED

package/workflows/verify/auto/workflow.yaml

@@ -1,7 +1,7 @@
 # workflows/verify/auto/workflow.yaml — Phase v3.0-3.5 W1 T3.5.W1.4
 #
-# Stage ④ Verify master orchestrator — 7 sub conditional per ~/.claude/CLAUDE.md "Verify 阶段"
-# verbatim + RESEARCH-workflows § Area 2 verify master:
+# Stage ④ Verify master orchestrator — 7 sub conditional per bundled Verify-stage cadence
+# + RESEARCH-workflows § Area 2 verify master:
 #   progress 必跑 (serial order 1) →
 #   code-review 并行 (parallel) +
 #   paranoid 关键模块 (parallel + gate is-critical-module) +
@@ -10,7 +10,6 @@
 #   multispec 关键发布 Pattern C (parallel + gate critical-release-upgrade)
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Verify 阶段 (GSD + gstack)" 节 verbatim
 #   - workflows/judgments/stage-routing.yaml — verify-* triggers (7 sub delegation)
 #   - workflows/judgments/parallelism-gate.yaml — agent-teams-upgrade trigger (multispec gate)
 #   - workflows/verify/{progress,code-review,paranoid,qa,security,design,simplify,multispec}/workflow.yaml
@@ -30,8 +29,8 @@
 schema_version: harnessed.workflow.v3
 workflow: verify
 description: |
-  Stage ④ Verify master orchestrator — 7 sub conditional per ~/.claude/CLAUDE.md "Verify 阶段"
-  verbatim: progress 必跑串行 → code-review 并行 → paranoid 关键模块强制 → qa/security/design
+  Stage ④ Verify master orchestrator — 7 sub conditional per bundled Verify-stage cadence:
+  progress 必跑串行 → code-review 并行 → paranoid 关键模块强制 → qa/security/design
   可选 conditional 并行 → simplify 末尾串行 → multispec 关键发布 Pattern C 4-specialist Agent Team。
   serial mode 必带 explicit order (K9 invariant); progress order 1 起点, simplify order 99 末尾。
 

package/workflows/verify/code-review/SKILL.md

@@ -2,7 +2,7 @@
 name: verify-code-review
 description: |
   Stage ④.b verify sub-workflow — code-review 多 agent 并行 fan-out 高置信度 finding
-  (subagent default per ~/.claude/CLAUDE.md 子任务并行机制 — Task / Agent 工具 spawn
+  (subagent default per bundled parallelism gate — Task / Agent 工具 spawn
   多 subagent fan-out, context 隔离, token 敏感)。
   schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available
   (code-review) + 1 phase (parallelism ref judgments.parallelism-gate.subagent-default.fires)。
@@ -29,8 +29,8 @@ onto harnessed runtime (Phase v3.0-3.4 W0.11 — D-04 Stage ④ Verify 7 sub +
 | 1 | `01-code-review` | mattpocock-skills | sonnet | `{{ capabilities.code-review.cmd }}` | `judgments.parallelism-gate.subagent-default.fires` |
 
 Per-phase config loads from `workflows/verify/code-review/workflow.yaml`; engine spawns
-multiple subagent in parallel fan-out (sister `~/.claude/CLAUDE.md` 子任务并行机制 默认 —
-Task / Agent 工具 spawn 多任务并发, context 隔离, summary 折叠回主 context)。
+multiple subagent in parallel fan-out (bundled subagent-default rule — Task / Agent
+工具 spawn 多任务并发, context 隔离, summary 折叠回主 context)。
 
 ## Capability refs
 
@@ -65,8 +65,6 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 ## References
 
 - D-04 Stage ④ Verify 7 sub 分解
-- ~/.claude/CLAUDE.md "Verify 阶段 — code-review 多 agent 并行" verbatim
-- ~/.claude/CLAUDE.md "子任务并行执行机制 — subagent vs Agent Teams 路由" subagent default
 - workflows/capabilities.yaml — code-review
 - workflows/judgments/parallelism-gate.yaml — subagent-default.fires
 - workflows/defaults.yaml — ralph_max_iterations.verify-code-review.* values (W2.2 backfill)

package/workflows/verify/code-review/workflow.yaml

@@ -1,12 +1,10 @@
 # workflows/verify/code-review/workflow.yaml — Phase v3.0-3.4 W0 T3.4.W0.11
 #
 # Stage ④.b verify sub-workflow — code-review 多 agent 并行 fan-out 高置信度 finding
-# (subagent default per CLAUDE.md 子任务并行机制 — Task / Agent 工具 spawn 多任务 fan-out,
+# (subagent default per bundled parallelism gate — Task / Agent 工具 spawn 多任务 fan-out,
 # context 隔离, token 敏感)。
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Verify 阶段" — "code-review 多 agent 并行" 章节
-#   - ~/.claude/CLAUDE.md "子任务并行执行机制 — subagent vs Agent Teams 路由" subagent default
 #   - workflows/judgments/parallelism-gate.yaml — subagent-default.fires 默认 fan-out
 #   - workflows/capabilities.yaml — code-review (Bucket 1 mattpocock 高频招式)
 #   - workflows/verify-work/workflow.yaml v2 SHIPPED phase 03-code-review-parallel sister pattern

package/workflows/verify/design/SKILL.md

@@ -2,8 +2,7 @@
 name: verify-design
 description: |
   Stage ④.f verify sub-workflow — gstack /design-review 设计系统一致性 + AI 审美问题识别
-  (has_design_changes 触发, 可选 conditional, sister ~/.claude/CLAUDE.md "Verify 阶段 — 可选
-  /design-review" verbatim)。
+  (has_design_changes 触发, 可选 conditional; bundled verify-stage optional /design-review step).
   schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available
   (gstack-design-review + ui-ux-pro-max + frontend-design) + 1 phase (gate ref has_design_changes
   conditional)。Triggered by harnessed CLI `harnessed verify-design --phase <num>` or slash
@@ -45,7 +44,7 @@ Sister `workflows/capabilities.yaml` entries:
 Sister `workflows/judgments/stage-routing.yaml`:
 - `verify-design-changes.fires` — `phase.stage == 'verify' and phase.has_design_changes == true`
 
-## Routing rules (sister ~/.claude/rules/web-design.md)
+## Routing rules (bundled web-design routing — `workflows/judgments/web-design-routing.yaml`)
 
 - 默认主方案 → `ui-ux-pro-max` (数据驱动、标准化、可解释)
 - 创意补充 / 不要 AI 味 → `frontend-design`
@@ -69,8 +68,7 @@ After completion, the Bash output prints a `Next:` hint on stderr suggesting the
 
 - D-04 Stage ④ Verify 7 sub 分解
 - D-12 gstack 治理关卡可选
-- ~/.claude/CLAUDE.md "Verify 阶段 — 可选 /design-review" verbatim
-- ~/.claude/rules/web-design.md — ui-ux-pro-max 默认 + frontend-design 补充
+- workflows/judgments/web-design-routing.yaml — ui-ux-pro-max 默认 + frontend-design 补充
 - workflows/capabilities.yaml — gstack-design-review / ui-ux-pro-max / frontend-design
 - workflows/judgments/stage-routing.yaml — verify-design-changes trigger
 - workflows/verify-work/workflow.yaml v2 SHIPPED phase 07-design-review-conditional sister verbatim