harnessed 3.4.3 → 3.5.0

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
@@ -45,54 +44,31 @@ 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`
 - 用户明示「独特 / 不要 AI 感」→ frontend-design 主导, 否则 ui-ux-pro-max 优先
 
-<!-- v3.4.3-dual-path-invocation -->
 ## How to invoke
 
-**Preferred path** (when the upstream specialist is installed): use the SlashCommand tool to run `{{ capabilities.gstack-design-review.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 **Design Reviewer (AI-Slop detector + design discipline)**.
->
-> **Mission**: Conditional on `phase.has_design_changes == true`. Evaluate rendered output (not source), with annotated screenshots as evidence. Adapted from gstack `/design-review` — think like a designer, not a QA engineer.
->
-> **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. Classifier: marketing/landing vs app UI vs hybrid — apply matching rule set
->
-> 2. Hard rejection: generic SaaS card grid / beautiful image weak brand / busy imagery behind text / carousel without narrative
->
-> 3. Litmus: brand unmistakable first screen / one strong visual anchor / scannable by headlines / one job per section
->
-> 4. Typography: expressive, not default stacks (Inter / Roboto / Arial / system)
->
-> 5. Hero: full-bleed edge-to-edge / one composition / no cards in hero
->
-> 6. Responsive ≠ stacked desktop on mobile — evaluate whether mobile layout makes design sense
->
-> 7. Quick Wins section: 3-5 highest-impact fixes <30 min each
->
-> 8. Every finding has a screenshot — annotated where possible (Read the file inline so user sees it)
->
-> **Output format**: structured report with severity-classified findings (hard-reject / quick-win / nice-to-have). 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 `gstack-design-review` user-skill / plugin isn't installed.)
-
-(Sister `~/.claude/commands/verify-design.md` is also generated by `harnessed setup` so `/verify-design` is a real platform slash command — both files carry the same dual-path instruction. Previous v3.4.x `harnessed verify-design --apply` CLI claims are removed; that subcommand was never implemented.)
+Use the Bash tool to run:
+
+```bash
+echo "$ARGUMENTS" | harnessed run verify-design --task-stdin
+```
+
+If `$ARGUMENTS` is empty, run `harnessed run verify-design` (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
 - 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

package/workflows/verify/design/workflow.yaml

@@ -1,11 +1,10 @@
 # workflows/verify/design/workflow.yaml — Phase v3.0-3.4 W0 T3.4.W0.13c
 #
 # Stage ④.f verify sub-workflow — gstack /design-review 设计系统一致性 + AI 审美问题
-# (has_design_changes 触发, 可选 conditional, sister ~/.claude/CLAUDE.md "可选 /design-review" verbatim)。
+# (has_design_changes 触发, 可选 conditional; bundled verify-stage optional /design-review step).
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Verify 阶段 — 可选 /design-review" 章节
-#   - ~/.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/judgments/stage-routing.yaml verify-design-changes trigger (has_design_changes)
 #   - workflows/capabilities.yaml — gstack-design-review / ui-ux-pro-max / frontend-design
 #   - workflows/verify-work/workflow.yaml v2 SHIPPED phase 07-design-review-conditional sister pattern
@@ -17,8 +16,8 @@ description: |
   Stage ④.f 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)。Gate: judgments.stage-routing.verify-design-changes.fires
   (phase.has_design_changes == true) — UI module fire only; 后端 / docs PR skip。
-  tools_available 含 ui-ux-pro-max (默认主方案) + frontend-design (创意补充) sister
-  ~/.claude/rules/web-design.md routing。
+  tools_available 含 ui-ux-pro-max (默认主方案) + frontend-design (创意补充) per bundled
+  web-design routing (workflows/judgments/web-design-routing.yaml).
 
 disciplines_applied: [karpathy, output-style, language, operational, priority, protocols]
 tools_available: [gstack-design-review, ui-ux-pro-max, frontend-design]

package/workflows/verify/multispec/SKILL.md

@@ -3,8 +3,8 @@ name: verify-multispec
 description: |
   Stage ④.h verify sub-workflow — 4-specialist Agent Team Pattern C 多维度审查 (关键发布 /
   大重构 PR 升级, code-review + gstack-review + gstack-cso + gstack-qa 4 teammate 互相
-  SendMessage 质询, NOT fire-and-forget subagent fan-out, sister ~/.claude/rules/agent-teams.md
-  L42-L52 Pattern C verbatim)。Cleanup mandatory: shutdown_request + TeamDelete (防呆清单)。
+  SendMessage 质询, NOT fire-and-forget subagent fan-out; bundled Agent Teams Pattern C
+  routing). Cleanup mandatory: shutdown_request + TeamDelete (bundled cleanup discipline).
   schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available
   (agent-teams 3 + 4 specialist capability) + 2 phase (01-team-create on critical-release
   invoke / 02-team-cleanup mandatory shutdown)。
@@ -34,7 +34,7 @@ D-11 Agent Teams + Pattern A sub-workflow ship)。
 Per-phase config loads from `workflows/verify/multispec/workflow.yaml`; phase 01 creates 4
 teammate (code-review + gstack-review + gstack-cso + gstack-qa) via TeamCreate, teammates 互相
 SendMessage 质询 findings 是否真问题 (NOT fire-and-forget); phase 02 mandatory shutdown_request
-+ TeamDelete (防呆清单 per ~/.claude/rules/agent-teams.md L46-L48)。
++ TeamDelete (bundled Agent Teams cleanup discipline)。
 
 ## Capability refs
 
@@ -57,53 +57,31 @@ Phase-level `on` clause (critical-release 升级触发):
 - `if: phase.is_major_release == true or phase.is_large_refactor == true` → `action: invoke`
 - else → `action: skip`
 
-## Routing rules (sister ~/.claude/rules/agent-teams.md)
+## Routing rules (bundled Agent Teams routing — `workflows/judgments/parallelism-gate.yaml`)
 
 - ✅ **触发**: 关键发布 / 大重构 PR (≥3 specialist 需互相质询而非 fire-and-forget)
 - ❌ **跳过**: 常规 PR / 单点任务 (sister verify-code-review fan-out + verify-paranoid 已够用且省 token)
-- **Token 估算 prereq**: `team_cost < 2 × subagent_cost` (engine-level check per agent-teams.md L34)
-- **Cleanup mandatory**: phase 02-team-cleanup `agent-teams-shutdown` 必跑 (防呆清单)
+- **Token 估算 prereq**: `team_cost < 2 × subagent_cost` (engine-level check; bundled cost guideline)
+- **Cleanup mandatory**: phase 02-team-cleanup `agent-teams-shutdown` 必跑 (bundled cleanup discipline)
 
-<!-- v3.4.3-dual-path-invocation -->
 ## How to invoke
 
-**Preferred path** (when the upstream specialist is installed): use the SlashCommand tool to run `{{ capabilities.agent-teams-create.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 **Multi-specialist Agent Team orchestrator (Pattern C)**.
->
-> **Mission**: Critical release / large refactor only. Spawn 4 teammates (code-review + gstack-review + gstack-cso + gstack-qa) via TeamCreate, let them cross-question findings via SendMessage (NOT fire-and-forget), lead arbitrates final report. Cleanup mandatory.
->
-> **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. Token-cost gate: estimate team_cost vs 2 × subagent_cost; only escalate when team wins
->
-> 2. TeamCreate with 4 teammates: code-review / gstack-review / gstack-cso / gstack-qa
->
-> 3. Each teammate's brief is self-contained (no shared session context to lean on)
->
-> 4. Round-trip findings: each teammate sends top-3 findings; others rate (real / false-positive / nit)
->
-> 5. Lead arbitrates conflicts; produces final report ordered CRITICAL → HIGH → MEDIUM
->
-> 6. Cleanup MANDATORY: SendMessage shutdown_request to each teammate, then TeamDelete
->
-> 7. If the gate doesn't fire (regular PR), DO NOT escalate — fall back to single-agent fan-out
->
-> **Output format**: structured report with severity-classified findings (ship-blocker / ship-with-action / informational). 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 `agent-teams-create` user-skill / plugin isn't installed.)
-
-(Sister `~/.claude/commands/verify-multispec.md` is also generated by `harnessed setup` so `/verify-multispec` is a real platform slash command — both files carry the same dual-path instruction. Previous v3.4.x `harnessed verify-multispec --apply` CLI claims are removed; that subcommand was never implemented.)
+Use the Bash tool to run:
+
+```bash
+echo "$ARGUMENTS" | harnessed run verify-multispec --task-stdin
+```
+
+If `$ARGUMENTS` is empty, run `harnessed run verify-multispec` (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
 - D-11 Agent Teams 4-specialist Pattern C upgrade
-- ~/.claude/CLAUDE.md "Verify 阶段 — 关键发布 / 大重构 PR 升级 Agent Team Pattern C" verbatim
-- ~/.claude/rules/agent-teams.md Pattern C 多维度审查 + 防呆清单 + 完整生命周期
 - workflows/capabilities.yaml — agent-teams-{create,send-message,shutdown} + 4 specialist
 - workflows/judgments/stage-routing.yaml — verify-multispec-critical-release trigger
 - workflows/judgments/parallelism-gate.yaml — agent-teams-upgrade.fires (5 OR-chain)

package/workflows/verify/multispec/workflow.yaml

@@ -1,12 +1,9 @@
 # workflows/verify/multispec/workflow.yaml — Phase v3.0-3.4 W0 T3.4.W0.13e
 #
 # Stage ④.h verify sub-workflow — 4-specialist Agent Team Pattern C 多维度审查 critical-release upgrade
-# (sister ~/.claude/CLAUDE.md "Verify 阶段 — 4-specialist Agent Team Pattern C" verbatim +
-# ~/.claude/rules/agent-teams.md L42-L52 Pattern C 多维度审查 ≥3 specialist 互相质询 NOT fire-and-forget)。
+# (bundled verify-stage Pattern C escalation: ≥3 specialist 互相 SendMessage 质询, NOT fire-and-forget).
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Verify 阶段 — 关键发布 / 大重构 PR 升级 Agent Team Pattern C" verbatim
-#   - ~/.claude/rules/agent-teams.md Pattern C 多维度审查 (≥3 specialist lead 委派 + 互相质询)
 #   - workflows/judgments/stage-routing.yaml verify-multispec-critical-release trigger
 #   - workflows/judgments/parallelism-gate.yaml agent-teams-upgrade.fires (5 OR-chain)
 #   - workflows/capabilities.yaml — agent-teams-create / agent-teams-send-message / agent-teams-shutdown
@@ -14,9 +11,9 @@
 #   - workflows/verify-work/workflow.yaml v2 SHIPPED phase 09-agent-team-multispecialist sister pattern
 #   - .planning/phase-v3.0-3.2/RESEARCH-workflows.md § Area 2 verify/multispec example verbatim
 #
-# Cleanup mandatory per ~/.claude/rules/agent-teams.md 防呆清单 (SendMessage shutdown_request +
-# TeamDelete) — engine-level wiring (phase 02-team-cleanup capability agent-teams-shutdown)。
-# Token estimate prereq per agent-teams.md L34: team_cost < 2 × subagent_cost (engine-level check)。
+# Cleanup mandatory (bundled Agent Teams discipline): SendMessage shutdown_request +
+# TeamDelete — engine-level wiring (phase 02-team-cleanup capability agent-teams-shutdown).
+# Token estimate prereq: team_cost < 2 × subagent_cost (bundled cost guideline; engine-level check).
 
 schema_version: harnessed.workflow.v3
 workflow: verify-multispec
@@ -24,7 +21,7 @@ description: |
   Stage ④.h 4-specialist Agent Team Pattern C 多维度审查 (关键发布 / 大重构 PR 升级,
   code-review + gstack-review + gstack-cso + gstack-qa 4 teammate 互相 SendMessage 质询,
   NOT fire-and-forget subagent fan-out)。Cleanup mandatory: shutdown_request + TeamDelete
-  (sister ~/.claude/rules/agent-teams.md 防呆清单)。
+  (bundled Agent Teams cleanup discipline)。
 
 disciplines_applied: [karpathy, output-style, language, operational, priority, protocols]
 tools_available:

package/workflows/verify/paranoid/SKILL.md

@@ -2,9 +2,9 @@
 name: verify-paranoid
 description: |
   Stage ④.c verify sub-workflow — gstack /review Paranoid Staff Engineer 关键模块 PR 前强制
-  (sister ~/.claude/CLAUDE.md "🔒 关键模块 PR 前强制" verbatim)。Gate:
+  (bundled gstack governance gate — mandatory before critical-module PR)。Gate:
   judgments.stage-routing.verify-paranoid-critical.fires (phase.is_critical_module == true) —
-  默认 critical fire only; 非关键模块 skip (sister CLAUDE.md "关键模块" 限定语)。
+  默认 critical fire only; 非关键模块 skip。
   schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available
   (gstack-review) + 1 phase (gate ref is_critical_module conditional)。
   Triggered by slash command
@@ -50,49 +50,24 @@ Sister `workflows/judgments/stage-routing.yaml`:
 - ✅ **触发**: 关键模块 PR 前 (auth / payment / data migration / core algorithm 等)
 - ❌ **跳过**: 常规 PR / docs / config / 非核心 module
 
-<!-- v3.4.3-dual-path-invocation -->
 ## How to invoke
 
-**Preferred path** (when the upstream specialist is installed): use the SlashCommand tool to run `{{ capabilities.gstack-review.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 **Paranoid Staff Engineer (pre-landing review)**.
->
-> **Mission**: Mandatory on critical modules (auth / payment / data migration / core algorithm). Default-suspect mode — assume the change is broken until proven otherwise. Adapted from gstack `/review` Pass 1 CRITICAL + Pass 2 INFORMATIONAL checklist.
->
-> **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. SQL & Data Safety — string interpolation, TOCTOU races, validation bypass, N+1
->
-> 2. Race conditions & concurrency — read-check-write without unique constraint, missing atomic UPDATE
->
-> 3. LLM output trust boundary — unvalidated LLM-generated values to DB / SSRF / stored prompt injection
->
-> 4. Shell injection — subprocess shell=True with interpolation, os.system, eval/exec on LLM output
->
-> 5. Enum & value completeness — new enum/status/tier value reached every consumer (case/if-chains/allowlists)
->
-> 6. Async/sync mixing — sync I/O inside async def, time.sleep in async
->
-> 7. Column/field name safety — ORM .select/.eq columns match schema
->
-> 8. Type coercion at boundaries — hash/digest inputs normalized before serialize
->
-> 9. Time window safety — date-key lookups assuming 24h coverage; mismatched buckets between features
->
-> **Output format**: structured report with severity-classified findings (CRITICAL / INFORMATIONAL (Fix-First Heuristic — critical → ASK, informational → AUTO-FIX)). 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 `gstack-review` user-skill / plugin isn't installed.)
-
-(Sister `~/.claude/commands/verify-paranoid.md` is also generated by `harnessed setup` so `/verify-paranoid` is a real platform slash command — both files carry the same dual-path instruction. Previous v3.4.x `harnessed verify-paranoid --apply` CLI claims are removed; that subcommand was never implemented.)
+Use the Bash tool to run:
+
+```bash
+echo "$ARGUMENTS" | harnessed run verify-paranoid --task-stdin
+```
+
+If `$ARGUMENTS` is empty, run `harnessed run verify-paranoid` (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
 - D-12 gstack 治理关卡强制
-- ~/.claude/CLAUDE.md "gstack 治理关卡 🔒 关键模块 PR 前强制" verbatim
 - workflows/capabilities.yaml — gstack-review
 - workflows/judgments/stage-routing.yaml — verify-paranoid-critical trigger
 - workflows/defaults.yaml — ralph_max_iterations.verify-paranoid.* values (W2.2 backfill)

package/workflows/verify/paranoid/workflow.yaml

@@ -1,10 +1,9 @@
 # workflows/verify/paranoid/workflow.yaml — Phase v3.0-3.4 W0 T3.4.W0.12
 #
 # Stage ④.c verify sub-workflow — gstack /review Paranoid Staff Engineer 关键模块 PR 前强制
-# (sister ~/.claude/CLAUDE.md "🔒 关键模块 PR 前强制" verbatim)。
+# (bundled gstack governance gate — mandatory before critical-module PR).
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "gstack 治理关卡 🔒 关键模块 PR 前强制" verbatim
 #   - workflows/judgments/stage-routing.yaml verify-paranoid-critical trigger (phase.is_critical_module)
 #   - workflows/capabilities.yaml — gstack-review (Bucket 3 治理关卡, impl: gstack, cmd: /review)
 #   - workflows/verify-work/workflow.yaml v2 SHIPPED phase 04-gstack-review-conditional sister pattern

package/workflows/verify/progress/SKILL.md

@@ -2,8 +2,8 @@
 name: verify-progress
 description: |
   Stage ④.a verify sub-workflow — gsd-verify-work + gsd-progress 必跑串行 (verify-work 起点)
-  + planning-with-files progress.md 持久化 (sister ~/.claude/CLAUDE.md "Verify 阶段" verbatim
-  必跑串行 — gsd-verify-work UAT-driven acceptance + gsd-progress 状态同步 顺序不可调换)。
+  + planning-with-files progress.md 持久化 (bundled verify-stage cadence — mandatory serial:
+  gsd-verify-work UAT-driven acceptance + gsd-progress 状态同步 顺序不可调换)。
   schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available
   (gsd-verify-work + gsd-progress + planning-with-files) + 3 phases (serial 01→02 + persist
   progress.md sink)。Triggered by harnessed CLI `harnessed verify-progress --phase <num>` or
@@ -46,43 +46,24 @@ Sister `workflows/capabilities.yaml` entries:
 总 fire 当 `phase.stage == 'verify'` (sister `workflows/judgments/stage-routing.yaml`
 verify-progress-always trigger)。无 skip 条件 — verify-work 起点必跑。
 
-<!-- v3.4.3-dual-path-invocation -->
 ## How to invoke
 
-**Preferred path** (when the upstream specialist is installed): use the SlashCommand tool to run `{{ capabilities.gsd-verify-work.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 **Progress / UAT verifier**.
->
-> **Mission**: Mandatory serial start of the verify stage. Run UAT-driven acceptance via GSD `/gsd-verify-work` then sync state via `/gsd-progress` and persist updates to `progress.md`. Order is locked: verify-work → progress.
->
-> **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. Read the phase's acceptance criteria from PLAN.md / task_plan.md
->
-> 2. For each criterion, demonstrate it passes (test result, manual UAT log, screenshot)
->
-> 3. Flag any criterion that is partial / stubbed / TODO — do NOT mark complete
->
-> 4. Sync ROADMAP.md / STATE.md / REQUIREMENTS.md via gsd-progress
->
-> 5. Append `progress.md` with completed subtask hash + verification artifact
->
-> 6. If acceptance is incomplete, route to bug-fix and re-verify; do not advance
->
-> **Output format**: structured report with severity-classified findings (accepted / partial / blocked / failed). 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 `gsd-verify-work` user-skill / plugin isn't installed.)
-
-(Sister `~/.claude/commands/verify-progress.md` is also generated by `harnessed setup` so `/verify-progress` is a real platform slash command — both files carry the same dual-path instruction. Previous v3.4.x `harnessed verify-progress --apply` CLI claims are removed; that subcommand was never implemented.)
+Use the Bash tool to run:
+
+```bash
+echo "$ARGUMENTS" | harnessed run verify-progress --task-stdin
+```
+
+If `$ARGUMENTS` is empty, run `harnessed run verify-progress` (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
 - D-12 gstack 治理关卡 ref (verify-paranoid 后续 sub)
-- ~/.claude/CLAUDE.md "Verify 阶段 — gsd-verify-work + gsd-progress 必跑串行" verbatim
 - workflows/capabilities.yaml — gsd-verify-work / gsd-progress / planning-with-files
 - workflows/judgments/stage-routing.yaml — verify-progress-always trigger
 - workflows/defaults.yaml — ralph_max_iterations.verify-progress.* values (W2.2 backfill)

package/workflows/verify/progress/workflow.yaml

@@ -4,7 +4,6 @@
 # + planning-with-files persist (progress.md sink, sister CLAUDE.md "Verify 阶段" verbatim)。
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Verify 阶段" 章节 verbatim (gsd-verify-work + gsd-progress 必跑串行)
 #   - workflows/judgments/stage-routing.yaml verify-progress-always trigger (总 fire 当 stage=='verify')
 #   - workflows/capabilities.yaml — gsd-verify-work / gsd-progress / planning-with-files
 #   - workflows/verify-work/workflow.yaml v2 SHIPPED phase 01-02 verbatim pattern

package/workflows/verify/qa/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: verify-qa
 description: |
-  Stage ④.d verify sub-workflow — gstack /qa 端到端 QA 验收 (has_ui_changes 触发, 可选 conditional,
-  sister ~/.claude/CLAUDE.md "Verify 阶段 — 可选 /qa" verbatim)。
+  Stage ④.d verify sub-workflow — gstack /qa 端到端 QA 验收 (has_ui_changes 触发, 可选 conditional;
+  bundled verify-stage optional /qa step).
   schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available
   (gstack-qa + playwright-cli + playwright-test + webapp-testing) + 1 phase (gate ref
   has_ui_changes conditional)。
@@ -45,53 +45,32 @@ Sister `workflows/capabilities.yaml` entries:
 Sister `workflows/judgments/stage-routing.yaml`:
 - `verify-qa-ui.fires` — `phase.stage == 'verify' and phase.has_ui_changes == true`
 
-## Routing rules (sister ~/.claude/rules/web-testing.md)
+## Routing rules (bundled web-testing routing — `workflows/judgments/web-testing-routing.yaml`)
 
 - 写测试 提交 repo / CI 跑 → `@playwright/test` (默认 frontend/e2e/*.spec.ts)
 - 探查 / 调试 / 一次性确认 → `playwright-cli` (token 最省)
 - setup 需 Python 后端 (Tortoise ORM / pandas) → `webapp-testing` skill
 - 性能 / a11y / 内存诊断 → 不在此 sub-workflow,用 `chrome-devtools-mcp`
 
-<!-- v3.4.3-dual-path-invocation -->
 ## How to invoke
 
-**Preferred path** (when the upstream specialist is installed): use the SlashCommand tool to run `{{ capabilities.gstack-qa.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 **QA Engineer (end-to-end)**.
->
-> **Mission**: Hands-on UAT for the changed surface — orient → explore → exercise forms / nav / states / console / responsive. Use `playwright-cli` for probes, `@playwright/test` for committed tests, `webapp-testing` for Python-backend setups. Adapted from gstack `/qa`.
->
-> **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. Orient: map the application (links, framework detection, initial console errors)
->
-> 2. Per page: visual scan, interactive elements work, console clean, responsive check
->
-> 3. Forms: empty / invalid / edge cases — error messages clear and actionable
->
-> 4. Navigation: every path in and out works, no dead-ends
->
-> 5. States: empty, loading, error, overflow — none look like AI placeholder
->
-> 6. Mobile: 375x812 viewport — real layout, not stacked desktop
->
-> 7. Authenticated paths if creds / cookies provided; depth > breadth on core flows
->
-> **Output format**: structured report with severity-classified findings (blocker / major / minor / nit). 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 `gstack-qa` user-skill / plugin isn't installed.)
-
-(Sister `~/.claude/commands/verify-qa.md` is also generated by `harnessed setup` so `/verify-qa` is a real platform slash command — both files carry the same dual-path instruction. Previous v3.4.x `harnessed verify-qa --apply` CLI claims are removed; that subcommand was never implemented.)
+Use the Bash tool to run:
+
+```bash
+echo "$ARGUMENTS" | harnessed run verify-qa --task-stdin
+```
+
+If `$ARGUMENTS` is empty, run `harnessed run verify-qa` (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
 - D-12 gstack 治理关卡可选
-- ~/.claude/CLAUDE.md "Verify 阶段 — 可选 /qa" verbatim
-- ~/.claude/rules/web-testing.md — 三层职责矩阵 (脑 / 手 / 筋骨)
+- workflows/judgments/web-testing-routing.yaml — 三层职责矩阵 (脑 / 手 / 筋骨)
 - workflows/capabilities.yaml — gstack-qa / playwright-cli / playwright-test / webapp-testing
 - workflows/judgments/stage-routing.yaml — verify-qa-ui trigger
 - workflows/verify-work/workflow.yaml v2 SHIPPED phase 05-qa-conditional sister verbatim

package/workflows/verify/qa/workflow.yaml

@@ -1,10 +1,9 @@
 # workflows/verify/qa/workflow.yaml — Phase v3.0-3.4 W0 T3.4.W0.13a
 #
 # Stage ④.d verify sub-workflow — gstack /qa 端到端 QA 验收 (has_ui_changes 触发, 可选 conditional)
-# (sister ~/.claude/CLAUDE.md "Verify 阶段" "可选 /qa" verbatim)。
+# (bundled verify-stage optional /qa step).
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Verify 阶段 — 可选 /qa" 章节
 #   - workflows/judgments/stage-routing.yaml verify-qa-ui trigger (has_ui_changes)
 #   - workflows/capabilities.yaml — gstack-qa (Bucket 3 治理关卡, impl: gstack, cmd: /qa)
 #   - workflows/verify-work/workflow.yaml v2 SHIPPED phase 05-qa-conditional sister pattern

package/workflows/verify/security/SKILL.md

@@ -2,7 +2,7 @@
 name: verify-security
 description: |
   Stage ④.e verify sub-workflow — gstack /cso 安全审查 OWASP/auth/secrets (has_auth_or_secrets
-  触发, 可选 conditional, sister ~/.claude/CLAUDE.md "Verify 阶段 — 可选 /cso" verbatim)。
+  触发, 可选 conditional; bundled verify-stage optional /cso step).
   schema_version: harnessed.workflow.v3 with disciplines_applied (6 default) + tools_available
   (gstack-cso) + 1 phase (gate ref has_auth_or_secrets conditional)。
   Triggered by slash command
@@ -47,47 +47,24 @@ Sister `workflows/judgments/stage-routing.yaml`:
 - ✅ **触发**: auth flow / session / credentials / API keys / SQL injection 路径 / OWASP top 10 area
 - ❌ **跳过**: docs / 纯 UI styling / 内部 refactor / non-security PR
 
-<!-- v3.4.3-dual-path-invocation -->
 ## How to invoke
 
-**Preferred path** (when the upstream specialist is installed): use the SlashCommand tool to run `{{ capabilities.gstack-cso.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 **Chief Security Officer (CSO audit)**.
->
-> **Mission**: Conditional on `phase.has_auth_or_secrets == true`. Audit auth flows, credentials, OWASP Top 10 surface, secrets, infrastructure security (CI/CD, Docker, IaC). Adapted from gstack `/cso`.
->
-> **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. OWASP Top 10: injection / broken auth / sensitive data exposure / XXE / broken access control / misconfig / XSS / insecure deserialize / known-vuln deps / insufficient logging
->
-> 2. Secrets archaeology: git history scan for leaked credentials, .env tracked files, CI inline secrets
->
-> 3. Auth boundaries: every protected route enforces auth (not just CSR check); authorization not transitive across requests
->
-> 4. CSRF / SSRF / stored prompt injection where LLM output enters knowledge bases
->
-> 5. CI/CD: pull_request_target + checkout PR code, script injection via github.event.*, unpinned third-party actions
->
-> 6. Dockerfiles: missing USER (root), secrets as ARG, .env in image, exposed ports without purpose
->
-> 7. IaC: wildcard IAM, hardcoded secrets in .tfvars, privileged containers, hostNetwork in K8s
->
-> 8. Dependency audit (npm audit / pip-audit / bundler-audit) — note SKIPPED tools rather than fail audit
->
-> **Output format**: structured report with severity-classified findings (CRITICAL / HIGH / MEDIUM / LOW / INFO). 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 `gstack-cso` user-skill / plugin isn't installed.)
-
-(Sister `~/.claude/commands/verify-security.md` is also generated by `harnessed setup` so `/verify-security` is a real platform slash command — both files carry the same dual-path instruction. Previous v3.4.x `harnessed verify-security --apply` CLI claims are removed; that subcommand was never implemented.)
+Use the Bash tool to run:
+
+```bash
+echo "$ARGUMENTS" | harnessed run verify-security --task-stdin
+```
+
+If `$ARGUMENTS` is empty, run `harnessed run verify-security` (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
 - D-12 gstack 治理关卡可选
-- ~/.claude/CLAUDE.md "Verify 阶段 — 可选 /cso" verbatim
 - workflows/capabilities.yaml — gstack-cso
 - workflows/judgments/stage-routing.yaml — verify-security-secrets trigger
 - workflows/verify-work/workflow.yaml v2 SHIPPED phase 06-cso-conditional sister verbatim

package/workflows/verify/security/workflow.yaml

@@ -1,10 +1,9 @@
 # workflows/verify/security/workflow.yaml — Phase v3.0-3.4 W0 T3.4.W0.13b
 #
 # Stage ④.e verify sub-workflow — gstack /cso 安全审查 OWASP/auth/secrets
-# (has_auth_or_secrets 触发, 可选 conditional, sister ~/.claude/CLAUDE.md "可选 /cso" verbatim)。
+# (has_auth_or_secrets 触发, 可选 conditional; bundled verify-stage optional /cso step).
 #
 # Sister refs:
-#   - ~/.claude/CLAUDE.md "Verify 阶段 — 可选 /cso" 章节
 #   - workflows/judgments/stage-routing.yaml verify-security-secrets trigger (has_auth_or_secrets)
 #   - workflows/capabilities.yaml — gstack-cso (Bucket 3 治理关卡, impl: gstack, cmd: /cso)
 #   - workflows/verify-work/workflow.yaml v2 SHIPPED phase 06-cso-conditional sister pattern