harnessed 3.3.0 → 3.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -1,103 +1,121 @@
1
1
  # harnessed
2
2
 
3
- > AI coding harness 包管理器 + composition orchestrator
4
- > 把三层栈协作方法论 (gstack 决策 + GSD 项目经理 + superpowers 资深工程师 + karpathy 心法 + mattpocock 招式) 机器化为可执行 engine
3
+ **English** | [中文](./README-cn.md)
4
+
5
+ > AI coding harness package manager + composition orchestrator
6
+ > Machine-executes the three-layer-stack collaboration methodology (gstack governance + GSD project manager + superpowers senior engineer + karpathy principles + mattpocock moves) as a runnable engine
5
7
 
6
8
  [![npm](https://img.shields.io/npm/v/harnessed?label=npm&color=blue)](https://npmjs.com/package/harnessed)
7
9
  [![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](./LICENSE)
8
10
  [![Sponsor](https://img.shields.io/github/sponsors/easyinplay?logo=github&label=Sponsor)](https://github.com/sponsors/easyinplay)
9
11
 
10
- > Not affiliated with, endorsed by, or sponsored by Harness Inc. ( [NOTICE](./NOTICE))
12
+ > Not affiliated with, endorsed by, or sponsored by Harness Inc. (see [NOTICE](./NOTICE))
11
13
 
12
14
  ---
13
15
 
14
- ## ✨ 一句话定位
16
+ ## ✨ TL;DR
17
+
18
+ Assembles the best open-source Claude Code ecosystem components, weaving them into a unified workflow via opinionated composition skills; does not vendor upstream code — manifests describe install/check, and composition skills orchestrate multi-upstream collaboration.
19
+
20
+ ---
15
21
 
16
- 装配市面上最优秀的开源 Claude Code 生态组件,用强意见 composition skill 织成统一工作流;不 vendor 上游代码,通过 manifest 描述 install/check + composition skill 编排多上游协作。
22
+ > Wait can harnessed really go toe-to-toe with upstream giants like superpowers / gstack / GSD?
23
+ > Of course — we **stand on the shoulders of giants**. See further, Newton said. 🧐
24
+ > ... *(whispers)* Though on closer look, more like the parrot perched on said shoulder.
25
+ > Eh — parrots mimic; we **orchestrate**. 🦜
17
26
 
18
27
  ---
19
28
 
20
- ## 🎯 关键差异化
29
+ ## 🎯 Key Differentiators
21
30
 
22
- - **三层栈机器化** — `gstack 决策` + `GSD 项目经理` + `superpowers 资深工程师` + `karpathy 4 心法` + `mattpocock 23 招式`,5 支柱 100% capture
23
- - **不 vendor 上游**manifest describe install/check;上游升级用户 re-install 即获最新版
24
- - **Composition Skill** — 自家 workflow skill 当指挥棒,调度多个上游协同。**1 super-master `/auto` + 4 stage master + 18 sub-workflow + 2 standalone = 25 namespace-layered workflow**,完整 4-stage 机器化 (`/auto` stage 一键 / `/discuss /plan /task /verify` stage / 三层栈 18 sub / `/research /retro` 2 standalone)
25
- - **L0 Discipline Substrate** — 全局 cross-stage 行为基准 (karpathy 心法 + output-style + language + operational + priority + protocols),applied universally
26
- - **包管理器思维** — install dependency graph 自动解析, doctor 健康检查, install-base 一键装齐
27
- - **统一入口**用户面对 `/discuss /plan /task /verify` master slash command,不需学每家上游术语;sub command 显式调用单 stage (例如 `/discuss-strategic` 只跑战略层澄清)
31
+ - **Three-layer stack machine-executed** — `gstack governance` + `GSD project manager` + `superpowers senior engineer` + `karpathy 4 principles` + `mattpocock 23 moves`, 5 pillars at 100% capture
32
+ - **No vendoring of upstream** manifests describe install/check; on upstream upgrade users just re-install to get the latest version
33
+ - **Composition Skill** — in-house workflow skills act as the conductor's baton, orchestrating multiple upstreams in concert. **1 super-master `/auto` + 4 stage masters + 18 sub-workflows + 2 standalones = 25 namespace-layered workflows**, full 4-stage machine-execution (`/auto` one-shot across stages / `/discuss /plan /task /verify` single stage / 18 three-layer-stack subs / `/research /retro` 2 standalones)
34
+ - **L0 Discipline Substrate** — global cross-stage behavior baseline (karpathy principles + output-style + language + operational + priority + protocols), applied universally
35
+ - **Package manager mindset** — install dependency graph auto-resolves, doctor health check, install-base one-shot full install
36
+ - **Unified entry point** users face `/discuss /plan /task /verify` master slash commands without learning each upstream's terminology; sub commands explicitly invoke a single stage (e.g. `/discuss-strategic` runs only the strategic-layer clarification)
28
37
 
29
38
  ---
30
39
 
31
- ## 📦 快速安装
40
+ ## 📦 Quick Install
32
41
 
33
42
  ```bash
34
43
  npm install -g harnessed && harnessed setup
35
44
  ```
36
45
 
37
- > Windows PowerShell 5.x 不支持 `&&` 链接,需改 `;` 或分两行 (`npm install -g harnessed; harnessed setup`)bash / zsh / PowerShell 7+ / cmd.exe 都正常。
46
+ > Windows PowerShell 5.x does not support `&&` chaining — use `;` or two lines (`npm install -g harnessed; harnessed setup`). bash / zsh / PowerShell 7+ / cmd.exe all work normally.
47
+
48
+ 🤖 **Or have an AI install it for you** — paste this sentence to Claude Code (or any AI assistant):
49
+
50
+ > Install harnessed for me following the guide at `https://github.com/easyinplay/harnessed/blob/main/INSTALL-WITH-AI.md`
51
+
52
+ The AI will auto-fetch the doc + run the install, handling OS / permissions / PATH / corepack edge cases — no need to copy large chunks of text.
38
53
 
39
- 🤖 **或让 AI 帮你装** — 复制 [INSTALL-WITH-AI.md](./INSTALL-WITH-AI.md) 整段粘贴进 Claude Code (或任何 AI 助手),AI 自动处理 OS / 权限 / PATH / corepack 等 edge case。
54
+ > [!TIP]
55
+ > 🚀 **The much-loved Agent Teams and Subagent features are auto-enabled in harnessed based on the task!**
56
+ > No need to manually configure `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` — `harnessed setup` writes it to `~/.claude/settings.json` automatically. Pattern A full-stack three-way / Pattern C 4-specialist and other multi-agent workflows work out of the box.
40
57
 
41
58
  ---
42
59
 
43
- ## 🚀 快捷使用 — 3 种选择
60
+ ## 🚀 Quick Start — 3 Options
44
61
 
45
- 按介入程度由低到高:
62
+ In order of increasing user intervention:
46
63
 
47
- ### 🎯 整体自动 (推荐新手 / 不想动脑子)
64
+ ### 🎯 Auto Mode (Recommended for newcomers / don't want to think hard)
48
65
 
49
66
  ```
50
- /auto "需求 X"
67
+ /auto "requirement X"
51
68
 
52
- # 大需求可显式分阶段 (一般 AI 自动判断;若自认大需求可强制):
53
- /auto "需求 X" --staged
69
+ # For large requirements you can explicitly stage (usually not needed — AI auto-judges and routes in;
70
+ # force it if you believe it's a large requirement):
71
+ /auto "requirement X" --staged
54
72
  ```
55
73
 
56
- > 不想动脑子或者刚入门一切交给 harnessed。自动跑完 6 stage (research conditional → discuss → plan → task → verify → retro mandatory),中间不停。v3.2.0 NEW:AI 1-shot 自动判断需求复杂度,大需求建议切 `--staged` 模式 ( stage 完停 review);开始前 prompt "对需求清晰认知吗?" n自动加跑 `/research` 多源调研;末尾 `/retro` 强制总结。失败 fail-fast,`harnessed resume` 续。`--pause-between-stages` 保留为 backward-compat alias。
74
+ > Don't want to think hard, or just getting started let harnessed handle everything. Runs the full 6 stages (research conditional → discuss → plan → task → verify → retro mandatory) without stopping. AI 1-shot auto-judges requirement complexity, suggests switching to `--staged` mode for large requirements (stops after each stage for review); before starting prompts "Do you have a clear understanding of the requirement?" if no auto-runs `/research` multi-source investigation; ends with mandatory `/retro` summary. Fail-fast on failure, resume via `harnessed resume`.
57
75
 
58
- ### 📂 分类自动 (推荐熟手 / review 中间结果)
76
+ ### 📂 Stage Mode (Recommended for power users / want to review intermediate results)
59
77
 
60
78
  ```
61
- /discuss "需求 X" # 战略 + Phase + 子任务 3 层澄清
62
- /plan "需求 X" # 架构 (conditional) + 计划持久化
63
- /task "subtask-1" # 4 sub 串行 (clarify → code → test → deliver)
64
- /verify "phase-1" # 7 sub conditional 验证
79
+ /discuss "requirement X" # Strategic + Phase + Subtask 3-layer clarification
80
+ /plan "requirement X" # Architecture (conditional) + plan persistence
81
+ /task "subtask-1" # 4 subs serial (clarify → code → test → deliver)
82
+ /verify "phase-1" # 7 subs conditional verification
65
83
  ```
66
84
 
67
- > 想自己决定从哪个 stage 开始 / review 中间产出 — 4 master 独立调用,每个 master 内部仍自动 fan-out stage 所有 sub。
85
+ > Want to decide which stage to start from / review intermediate outputs — 4 masters callable independently, and each master still auto-fans-out all of that stage's subs internally.
68
86
 
69
- ### 🔬 精确调用 (大神 mode / 知道自己要什么)
87
+ ### 🔬 Surgical Mode (Expert mode / you know what you want)
70
88
 
71
89
  ```
72
- /discuss-phase "..." # 单跑 Phase 层澄清
73
- /plan-architecture "..." # 单跑架构审查
74
- /verify-paranoid "..." # 单跑 Paranoid Staff Engineer 审查
75
- # ... 其他 18 sub-workflow 任选
90
+ /discuss-phase "..." # Run only Phase-layer clarification
91
+ /plan-architecture "..." # Run only architecture review
92
+ /verify-paranoid "..." # Run only the Paranoid Staff Engineer review
93
+ # ... pick any of the other 18 sub-workflows
76
94
  ```
77
95
 
78
- > "我是大神,我自己决定" — 跳过 master,直接调某 sub-workflow。适合已知精确需要哪个 sub 的高级用户 / 复用某单一环节。
96
+ > "I'm an expert, I'll decide myself" — skip the master, invoke a sub-workflow directly. Suits advanced users who know exactly which sub they need, or reuse of a single step.
79
97
 
80
98
  ---
81
99
 
82
- ## 📐 4-stage 流程图
100
+ ## 📐 4-Stage Flow Diagram
83
101
 
84
102
  ```mermaid
85
103
  graph TD
86
- RS([⓪ /research — 前置多源调研 可选]):::optional
87
- subgraph Discuss[① Discuss 战略澄清]
104
+ RS([⓪ /research — pre-stage multi-source investigation, optional]):::optional
105
+ subgraph Discuss[① Discuss — Strategic Clarification]
88
106
  DM[/discuss master/]
89
107
  DS[discuss-strategic]
90
108
  DP[discuss-phase]
91
109
  DT[discuss-subtask]
92
110
  DM --> DS & DP & DT
93
111
  end
94
- subgraph Plan[② Plan 任务规划]
112
+ subgraph Plan[② Plan — Task Planning]
95
113
  PM[/plan master/]
96
114
  PA[plan-architecture]
97
115
  PP[plan-phase]
98
116
  PM --> PA & PP
99
117
  end
100
- subgraph Task[③ Task 执行]
118
+ subgraph Task[③ Task — Execution]
101
119
  TM[/task master/]
102
120
  TC[task-clarify]
103
121
  TCo[task-code]
@@ -105,7 +123,7 @@ graph TD
105
123
  TD[task-deliver]
106
124
  TM --> TC --> TCo --> TT --> TD
107
125
  end
108
- subgraph Verify[④ Verify 验证]
126
+ subgraph Verify[④ Verify — Verification]
109
127
  VMs[/verify master/]
110
128
  VP[verify-progress]
111
129
  VC[verify-code-review]
@@ -117,151 +135,151 @@ graph TD
117
135
  VM[verify-multispec]
118
136
  VMs --> VP & VC & VPa & VQ & VS & VD & VSi & VM
119
137
  end
120
- RT([⑤ /retro — 里程碑总结 可选]):::optional
138
+ RT([⑤ /retro — milestone summary, optional]):::optional
121
139
  RS --> Discuss
122
140
  Discuss --> Plan --> Task --> Verify
123
141
  Verify --> RT
124
142
  classDef optional stroke-dasharray:5 5,fill:#f5f5f5,color:#666
125
143
  ```
126
144
 
127
- > 虚框 = 可选 standalone (`/research` 战略前调研 / `/retro` 里程碑后总结);实框 = 主流程 4-stage cadence
145
+ > Dashed boxes = optional standalones (`/research` pre-strategic investigation / `/retro` post-milestone summary); solid boxes = main 4-stage cadence.
128
146
 
129
- ### 25 workflow 总览表
147
+ ### 25-Workflow Overview Table
130
148
 
131
149
  | Slash cmd | Stage | Type | Capability / Upstream | Brief |
132
150
  |-----------|-------|------|----------------------|-------|
133
- | `/auto` | All | **Super-master** | masterOrchestrator ( 6 stage) | 一键自动跑 6 stage (research conditional → discuss → plan → task → verify → retro mandatory); v3.2.0 NEW:AI 复杂度 1-shot judge + 理解度 check + retro mandatory; `--staged` (primary, alias `--pause-between-stages` backward-compat) opt-in |
134
- | `/discuss` | ① Discuss | Master | masterOrchestrator | 3 sub 并行 gate-eval (chain-isolation 铁律) |
135
- | `/discuss-strategic` | ① Discuss | Sub | gstack `/office-hours` + `/plan-ceo-review` + planning-with-files | 战略层新功能 / milestone / 产品方向强制治理 (findings.md 持久化) |
136
- | `/discuss-phase` | ① Discuss | Sub | GSD `/gsd-discuss-phase` + planning-with-files | Phase — ≥2 open decisions / 灰色地带澄清 (findings.md + knowledge.md 持久化) |
137
- | `/discuss-subtask` | ① Discuss | Sub | superpowers brainstorming + `/grill-with-docs` | 子任务层 — ≥2 approach / 核心算法 / API contract (ephemeral 短讨论, 不持久化) |
138
- | `/plan` | ② Plan | Master | masterOrchestrator | 串行 invoke 2 sub (architecture conditional → phase always) |
139
- | `/plan-architecture` | ② Plan | Sub | gstack `/plan-eng-review` | 架构层复杂架构强制治理关卡 |
140
- | `/plan-phase` | ② Plan | Sub | GSD `/gsd-plan-phase` + planning-with-files `/plan` | 计划层持久化 `task_plan.md` + `progress.md` |
141
- | `/task` | ③ Task | Master | masterOrchestrator | 串行 invoke 4 sub per subtask (clarify → code → test → deliver) |
142
- | `/task-clarify` | ③ Task | Sub | superpowers brainstorming + `/grill-with-docs` conditional | 子任务起步澄清 gate |
143
- | `/task-code` | ③ Task | Sub | karpathy 4 心法 + `/zoom-out` / `/improve-codebase-architecture` / `/diagnose` conditional | 子任务编码 + session progress.md 同步 |
144
- | `/task-test` | ③ Task | Sub | superpowers TDD red-green-refactor + `/diagnose` conditional | 核心逻辑 TDD 强制 (alias mattpocock `/tdd`) |
145
- | `/task-deliver` | ③ Task | Sub | `ralph-loop` SDK wrapper + Agent Teams conditional | verbatim `COMPLETE` + R20.10 max_iter fallback |
146
- | `/verify` | ④ Verify | Master | masterOrchestrator | 7 sub 按场景 conditional dispatch |
147
- | `/verify-progress` | ④ Verify | Sub | GSD `/gsd-verify-work` + `/gsd-progress` | 必跑串行起点 — UAT 验收 + 状态同步 |
148
- | `/verify-code-review` | ④ Verify | Sub | `code-review` subagent fan-out | 高置信度 finding 并行 |
149
- | `/verify-paranoid` | ④ Verify | Sub | gstack `/review` (Paranoid Staff Engineer) | 关键模块 PR 前强制 |
150
- | `/verify-qa` | ④ Verify | Sub | gstack `/qa` + playwright-cli / `@playwright/test` / webapp-testing | 端到端 QA (has_ui_changes conditional) |
151
+ | `/auto` | All | **Super-master** | masterOrchestrator (across 6 stages) | One-shot full 6-stage run (research conditional → discuss → plan → task → verify → retro mandatory); AI 1-shot complexity judge + understanding check + mandatory retro; `--staged` opt-in stage gate |
152
+ | `/discuss` | ① Discuss | Master | masterOrchestrator | 3 subs parallel gate-eval (chain-isolation rule) |
153
+ | `/discuss-strategic` | ① Discuss | Sub | gstack `/office-hours` + `/plan-ceo-review` + planning-with-files | Strategic layer mandatory governance for new features / new milestones / product direction (findings.md persisted) |
154
+ | `/discuss-phase` | ① Discuss | Sub | GSD `/gsd-discuss-phase` + planning-with-files | Phase layer — ≥2 open decisions / gray-area clarification (findings.md + knowledge.md persisted) |
155
+ | `/discuss-subtask` | ① Discuss | Sub | superpowers brainstorming + `/grill-with-docs` | Subtask layer — ≥2 approaches / core algorithm / API contract (ephemeral short discussion, not persisted) |
156
+ | `/plan` | ② Plan | Master | masterOrchestrator | Serial invoke of 2 subs (architecture conditional → phase always) |
157
+ | `/plan-architecture` | ② Plan | Sub | gstack `/plan-eng-review` | Architecture layer mandatory governance gate for complex architecture |
158
+ | `/plan-phase` | ② Plan | Sub | GSD `/gsd-plan-phase` + planning-with-files `/plan` | Plan layer persists `task_plan.md` + `progress.md` |
159
+ | `/task` | ③ Task | Master | masterOrchestrator | Serial invoke of 4 subs per subtask (clarify → code → test → deliver) |
160
+ | `/task-clarify` | ③ Task | Sub | superpowers brainstorming + `/grill-with-docs` conditional | Subtask startup clarification gate |
161
+ | `/task-code` | ③ Task | Sub | karpathy 4 principles + `/zoom-out` / `/improve-codebase-architecture` / `/diagnose` conditional | Subtask coding + cross-session progress.md sync |
162
+ | `/task-test` | ③ Task | Sub | superpowers TDD red-green-refactor + `/diagnose` conditional | TDD mandatory for core logic (alias mattpocock `/tdd`) |
163
+ | `/task-deliver` | ③ Task | Sub | `ralph-loop` SDK wrapper + Agent Teams conditional | Until verbatim `COMPLETE` + R20.10 max_iter fallback |
164
+ | `/verify` | ④ Verify | Master | masterOrchestrator | 7 subs conditional dispatch by scenario |
165
+ | `/verify-progress` | ④ Verify | Sub | GSD `/gsd-verify-work` + `/gsd-progress` | Mandatory serial starting point — UAT acceptance + state sync |
166
+ | `/verify-code-review` | ④ Verify | Sub | `code-review` multi-subagent fan-out | High-confidence findings in parallel |
167
+ | `/verify-paranoid` | ④ Verify | Sub | gstack `/review` (Paranoid Staff Engineer) | Mandatory for critical-module pre-PR |
168
+ | `/verify-qa` | ④ Verify | Sub | gstack `/qa` + playwright-cli / `@playwright/test` / webapp-testing | End-to-end QA (has_ui_changes conditional) |
151
169
  | `/verify-security` | ④ Verify | Sub | gstack `/cso` | OWASP / auth / secrets (has_auth_or_secrets conditional) |
152
- | `/verify-design` | ④ Verify | Sub | gstack `/design-review` + ui-ux-pro-max + frontend-design | 设计系统一致性 (has_design_changes conditional) |
153
- | `/verify-simplify` | ④ Verify | Sub | `code-simplifier` | 末尾串行简化 |
154
- | `/verify-multispec` | ④ Verify | Sub | 4-specialist Agent Team Pattern C | 关键发布 / 大重构 PR 升级 (互相 SendMessage 质询) |
155
- | `/research` | Standalone | Standalone | Tavily / Exa MCP + ctx7 + GSD `/gsd-discuss-phase` | 多源调研 (Stage ① alternate) |
156
- | `/retro` | Standalone | Standalone | gstack `/retro` + planning-with-files RETROSPECTIVE.md | 项目 / 里程碑结束总结 |
170
+ | `/verify-design` | ④ Verify | Sub | gstack `/design-review` + ui-ux-pro-max + frontend-design | Design system consistency (has_design_changes conditional) |
171
+ | `/verify-simplify` | ④ Verify | Sub | `code-simplifier` | Final serial simplification |
172
+ | `/verify-multispec` | ④ Verify | Sub | 4-specialist Agent Team Pattern C | Critical release / large refactor PR escalation (mutual SendMessage cross-examination) |
173
+ | `/research` | Standalone | Standalone | Tavily / Exa MCP + ctx7 + GSD `/gsd-discuss-phase` | Multi-source investigation (Stage ① alternate) |
174
+ | `/retro` | Standalone | Standalone | gstack `/retro` + planning-with-files RETROSPECTIVE.md | Project / milestone close-out summary |
157
175
 
158
- > Master orchestrator 自动 gate-route 到合适的 sub (chain-isolation 铁律 fire sub 透明声明跳过)
159
- > 直接调用 sub 也可绕过 master 单跑某 stage,例如 `/discuss-strategic "新功能 X"`。
176
+ > Master orchestrator auto gate-routes to the right sub (chain-isolation rulenon-firing subs are transparently declared skipped).
177
+ > Direct sub invocation also bypasses the master to run a single stage, e.g. `/discuss-strategic "new feature X"`.
160
178
 
161
179
  ---
162
180
 
163
- ## ⚡ 使用流程
181
+ ## ⚡ Usage Flow
164
182
 
165
- 4-stage 三层栈方法论推荐 4 master orchestrator 串行驱动:
183
+ 4-stage three-layer-stack methodology recommended driving via the 4 master orchestrators in series:
166
184
 
167
185
  ```
168
186
  /discuss → /plan → /task → /verify
169
187
  ① ② ③ ④
170
188
  ```
171
189
 
172
- | Stage | Master | 主要 sub-workflow | 上游协同 |
190
+ | Stage | Master | Main sub-workflows | Upstream collaboration |
173
191
  | ---- | ---- | ---- | ---- |
174
- | ① **Discuss** | `/discuss` | strategic / phase / subtask (3 并行) | gstack `/office-hours` + GSD `/gsd-discuss-phase` + superpowers brainstorming |
192
+ | ① **Discuss** | `/discuss` | strategic / phase / subtask (3 in parallel) | gstack `/office-hours` + GSD `/gsd-discuss-phase` + superpowers brainstorming |
175
193
  | ② **Plan** | `/plan` | architecture (conditional) → phase | gstack `/plan-eng-review` + GSD `/gsd-plan-phase` + planning-with-files |
176
- | ③ **Task** | `/task` | clarify → code → test → deliver (4 串行 per subtask) | karpathy 心法 + mattpocock 招式 + superpowers TDD + `ralph-loop` |
194
+ | ③ **Task** | `/task` | clarify → code → test → deliver (4 serial per subtask) | karpathy principles + mattpocock moves + superpowers TDD + `ralph-loop` |
177
195
  | ④ **Verify** | `/verify` | progress → 5 parallel conditional → simplify (+ multispec critical) | GSD `/gsd-verify-work` + code-review + gstack `/review` / `/qa` / `/cso` / `/design-review` + code-simplifier |
178
196
 
179
- 实操示例:
197
+ Practical example:
180
198
 
181
199
  ```bash
182
- # 1. workflow 上游 (一行装齐 gstack + GSD + superpowers + planning-with-files)
200
+ # 1. Install workflow upstreams (one line installs gstack + GSD + superpowers + planning-with-files)
183
201
  harnessed setup
184
202
 
185
- # 2. Claude Code 内跑 4-stage cadence
186
- /discuss "新功能 X" # 战略 + Phase + 子任务 3 层澄清
187
- /plan "新功能 X" # 架构 (conditional) + 计划 (任务图持久化)
188
- /task "subtask-1: API contract" # 4 sub 串行 per subtask
189
- /verify "phase-1" # 7 sub conditional
203
+ # 2. Run the 4-stage cadence inside Claude Code
204
+ /discuss "new feature X" # Strategic + Phase + Subtask 3-layer clarification
205
+ /plan "new feature X" # Architecture (conditional) + plan (task graph persisted)
206
+ /task "subtask-1: API contract" # 4 subs serial per subtask
207
+ /verify "phase-1" # 7 subs conditional
190
208
 
191
- # 3. 中断后恢复 (任何时候)
209
+ # 3. Resume after interruption (any time)
192
210
  harnessed resume
193
211
  ```
194
212
 
195
- > 也可直接调 sub 绕过 master 单跑某一层,例如 `/verify-paranoid` 只跑 Paranoid Staff Engineer 审查。
213
+ > You can also invoke subs directly to bypass the master and run just one layer, e.g. `/verify-paranoid` runs only the Paranoid Staff Engineer review.
196
214
 
197
- 📊 详细 mermaid + stage 完整说明:[docs/WORKFLOW.md](./docs/WORKFLOW.md)
215
+ 📊 Detailed mermaid + full stage walkthroughs: [docs/WORKFLOW.md](./docs/WORKFLOW.md)
198
216
 
199
217
  ---
200
218
 
201
- ## 🗂️ 架构 (4-stage namespace-layered)
219
+ ## 🗂️ Architecture (4-stage namespace-layered)
202
220
 
203
- ### 1. 目录结构
221
+ ### 1. Directory Structure
204
222
 
205
223
  ```
206
224
  harnessed/
207
- ├── manifests/ # L1: 上游描述层 (NOT vendored)
208
- ├── workflows/ # L6: composition skill (4-stage 指挥棒)
209
- │ ├── discuss/ # Stage ① 3 layer (strategic + phase + subtask)
225
+ ├── manifests/ # L1: upstream description layer (NOT vendored)
226
+ ├── workflows/ # L6: composition skills (4-stage conductor's baton)
227
+ │ ├── discuss/ # Stage ① 3 layers (strategic + phase + subtask)
210
228
  │ │ ├── auto/ # /discuss master gate-route
211
229
  │ │ ├── strategic/ # /discuss-strategic (gstack /office-hours + /plan-ceo-review)
212
230
  │ │ ├── phase/ # /discuss-phase (GSD /gsd-discuss-phase)
213
231
  │ │ └── subtask/ # /discuss-subtask (superpowers brainstorming)
214
- │ ├── plan/ # Stage ② (architecture + phase 任务图)
232
+ │ ├── plan/ # Stage ② (architecture + phase task graph)
215
233
  │ ├── task/ # Stage ③ (clarify + code + test + deliver)
216
234
  │ ├── verify/ # Stage ④ (progress + code-review + paranoid + qa + cso + design + simplify + multispec)
217
235
  │ ├── research/ # standalone Stage ① alternate
218
236
  │ ├── retro/ # standalone post-④ milestone close
219
- │ ├── capabilities.yaml # L5a: ~70 entry, 7 category SoT
237
+ │ ├── capabilities.yaml # L5a: ~70 entries, 7 categories SoT
220
238
  │ ├── defaults.yaml # ralph_max_iterations per workflow phase
221
- │ ├── judgments/ # L5a: 三层栈判据 + parallelism + tdd + fallback + rules-routing
239
+ │ ├── judgments/ # L5a: three-layer-stack criteria + parallelism + tdd + fallback + rules-routing
222
240
  │ │ ├── strategic-gate.yaml
223
241
  │ │ ├── phase-gate.yaml
224
242
  │ │ ├── subtask-gate.yaml
225
243
  │ │ ├── parallelism-gate.yaml # L5b execution mechanism routing
226
244
  │ │ ├── tdd-gate.yaml
227
- │ │ ├── fallback.yaml # 3 铁律: skip_with_transparency + override + chain_isolation
228
- │ │ ├── web-design-routing.yaml # UI 设计工具路由
229
- │ │ ├── web-testing-routing.yaml # E2E / 浏览器测试工具路由
230
- │ │ ├── web-search-routing.yaml # 网页搜索 / 文档抓取路由
231
- │ │ └── stage-routing.yaml # master orchestrator sub-stage 路由
232
- │ └── disciplines/ # L0: 全局 cross-stage 行为基准
233
- │ ├── karpathy.yaml # 4 心法 + ≤200L
245
+ │ │ ├── fallback.yaml # 3 rules: skip_with_transparency + override + chain_isolation
246
+ │ │ ├── web-design-routing.yaml # UI design tool routing
247
+ │ │ ├── web-testing-routing.yaml # E2E / browser testing tool routing
248
+ │ │ ├── web-search-routing.yaml # Web search / doc fetch routing
249
+ │ │ └── stage-routing.yaml # master orchestrator sub-stage routing
250
+ │ └── disciplines/ # L0: global cross-stage behavior baseline
251
+ │ ├── karpathy.yaml # 4 principles + ≤200L
234
252
  │ ├── output-style.yaml # BLUF + no-emoji + no-em-dash
235
253
  │ ├── language.yaml # zh-Hans default + English preserve
236
254
  │ ├── operational.yaml # biome preempt + A7 + commit safety
237
- │ ├── priority.yaml # skill conflict 仲裁
238
- │ └── protocols.yaml # cc-handoff design doc 自包含
255
+ │ ├── priority.yaml # skill conflict arbitration
256
+ │ └── protocols.yaml # cc-handoff design doc self-contained
239
257
  ├── routing/ # L4: routing engine SSOT (decision_rules.yaml)
240
258
  ├── schemas/ # L3: JSON Schema (IDE / CI consume)
241
259
  ├── src/ # L4: TS engine (workflow + routing + cli + installers + checkpoint + audit + state)
242
260
  ├── tests/ # vitest unit + integration + dogfood (R8.1 dogfood-first)
243
261
  ├── scripts/ # CI gate (check-workflow-schema, transparency-verdict, state-archive)
244
262
  ├── .planning/ # project memory (STATE + ROADMAP + REQUIREMENTS + per-phase + milestones)
245
- └── docs/adr/ # 架构决策记录
263
+ └── docs/adr/ # architecture decision records
246
264
  ```
247
265
 
248
- ### 2. 逻辑分层 (8 )
266
+ ### 2. Logical Layering (8 layers)
249
267
 
250
268
  ```
251
269
  ┌────────────────────────────────────────────────────────────┐
252
270
  │ L7 User-facing slash cmd + harnessed CLI │
253
- │ /discuss /plan /task /verify (master) + 14 sub + /research /retro
271
+ │ /discuss /plan /task /verify (master) + 18 sub + /research /retro + /auto super-master
254
272
  │ + direct gstack invoke (30+ optional): /office-hours /review /qa /...
255
273
  ├────────────────────────────────────────────────────────────┤
256
274
  │ L6 Workflow orchestration (workflows/<stage>/<sub>/) │
257
275
  ├────────────────────────────────────────────────────────────┤
258
276
  │ L5b Execution Mechanism (orthogonal): subagent / Agent Teams │
259
- │ / session + ralph-loop wrapper
260
- │ parallelism-gate.yaml: 默认 subagent → escalate 5 触发
261
- │ Pattern A 全栈三路 / B 对立假设 / C 多维度审查
277
+ │ / main session + ralph-loop wrapper
278
+ │ parallelism-gate.yaml: default subagent → escalate 5 triggers
279
+ │ Pattern A full-stack three-way / B opposing hypotheses / C multi-dim review
262
280
  ├────────────────────────────────────────────────────────────┤
263
281
  │ L5a Capability + Judgment + Defaults SoT │
264
- │ capabilities.yaml (7 category) + judgments/ (10 file) +
282
+ │ capabilities.yaml (7 categories) + judgments/ (10 files) +
265
283
  │ defaults.yaml │
266
284
  ├────────────────────────────────────────────────────────────┤
267
285
  │ L4 Runtime engine (workflow / routing / handlers) │
@@ -272,17 +290,17 @@ harnessed/
272
290
  ├────────────────────────────────────────────────────────────┤
273
291
  │ L1 Upstream components (NOT vendored) │
274
292
  ├────────────────────────────────────────────────────────────┤
275
- │ L0 Discipline Substrate (全局生效)
276
- │ karpathy 心法 + output-style + language + operational +
293
+ │ L0 Discipline Substrate (applies globally)
294
+ │ karpathy principles + output-style + language + operational +
277
295
  │ priority + protocols (applied universally to L1-L7) │
278
296
  └────────────────────────────────────────────────────────────┘
279
297
  ```
280
298
 
281
- ### 3. Cross-cutting Capabilities (capabilities.yaml 7 category, ~83 entry)
299
+ ### 3. Cross-cutting Capabilities (capabilities.yaml 7 categories, ~83 entries)
282
300
 
283
301
  ```
284
302
  behavioral (6): karpathy-guidelines + output-style + language + operational + priority + protocols
285
- tool-slash-cmd (~60): gstack 30+ optional + gsd 10+ + mattpocock 12 高频 +
303
+ tool-slash-cmd (~60): gstack 30+ optional + gsd 10+ + mattpocock 12 high-frequency + etc.
286
304
  tool-mcp (3): chrome-devtools-mcp / tavily-mcp / exa-mcp
287
305
  tool-cli (2): ctx7 / gws
288
306
  tool-plugin (2): planning-with-files / @playwright/test
@@ -290,18 +308,18 @@ tool-bundled (3): ralph-loop / webapp-testing / playwright-cli
290
308
  agent-platform (3): agent-teams-create / send-message / shutdown
291
309
  ```
292
310
 
293
- ### 4. 数据流示例 (用户调用 `/discuss "新功能 X"`)
311
+ ### 4. Data Flow Example (user invokes `/discuss "new feature X"`)
294
312
 
295
313
  ```
296
- [L7] User invokes /discuss "新功能 X"
314
+ [L7] User invokes /discuss "new feature X"
297
315
 
298
316
  [L6] workflows/discuss/auto/workflow.yaml master orchestrator
299
317
 
300
- [L5a] judgments.strategic-gate.fires + phase-gate.fires + subtask-gate.fires (3-way 并行 eval)
318
+ [L5a] judgments.strategic-gate.fires + phase-gate.fires + subtask-gate.fires (3-way parallel eval)
301
319
 
302
320
  [L4] judgmentResolver.ts (4-level ref split) + exprBuilder.ts (expr-eval evaluate)
303
321
 
304
- [L0] discipline.priority-hierarchy 仲裁工具冲突 / output-style 格式化输出
322
+ [L0] discipline.priority-hierarchy arbitrates tool conflicts / output-style formats output
305
323
 
306
324
  [fires=true sub] → invoke sub-workflow (/discuss-strategic / /discuss-phase / /discuss-subtask)
307
325
  ↓ for each sub:
@@ -310,150 +328,149 @@ agent-platform (3): agent-teams-create / send-message / shutdown
310
328
  ├─ parallelism: judgments.parallelism-gate.<route>.fires (L5b mechanism)
311
329
  └─ phase invocations execute via capability template interpolation
312
330
 
313
- [fallback.yaml chain-isolation] 三层独立判断, 不串行依赖
314
- [Skip 透明声明] fire 的 sub → "⚠️ 跳过 <sub>, 因为 <reason>"
331
+ [fallback.yaml chain-isolation] 3 layers judged independently, not serially dependent
332
+ [Skip transparency declaration] non-firing subs → "⚠️ Skipped <sub> because <reason>"
315
333
 
316
334
  planning-with-files /plan (cross-cutting tool) → write artifacts to .planning/<phase-id>/
317
335
 
318
336
  [L4] state.ts writeCurrentWorkflow (proper-lockfile) + audit.append (12-field JSONL)
319
337
  ```
320
338
 
321
- ### 5. 抉择路由矩阵 (rules-based, codified in judgments + capabilities)
339
+ ### 5. Decision Routing Matrix (rules-based, codified in judgments + capabilities)
322
340
 
323
- | 场景 | Default → Escalate |
341
+ | Scenario | Default → Escalate |
324
342
  |------|---------------------|
325
- | 并行机制 | subagent → Agent Teams Pattern A/B/C (5 触发) |
326
- | UI 设计主方案 | ui-ux-pro-max → frontend-design (用户明示风格) |
327
- | E2E 浏览器探查 | playwright-cli (Bash 一行 token) |
328
- | E2E commit-able TS | @playwright/test 默认 |
329
- | E2E Python 后端联动 | webapp-testing |
330
- | 性能 / a11y / 内存诊断 | chrome-devtools-mcp |
331
- | Web 搜索 (关键词) | Tavily MCP 默认 |
332
- | Web 搜索 (描述式 / 学术) | Exa MCP |
333
- | API 文档 | ctx7 CLI |
343
+ | Parallelism mechanism | subagent → Agent Teams Pattern A/B/C (5 triggers) |
344
+ | UI design primary plan | ui-ux-pro-max → frontend-design (user explicitly asks for style) |
345
+ | E2E browser exploration | playwright-cli (one-line Bash, token-efficient) |
346
+ | E2E commit-able TS | @playwright/test default |
347
+ | E2E Python backend linkage | webapp-testing |
348
+ | Performance / a11y / memory diagnostics | chrome-devtools-mcp |
349
+ | Web search (keyword) | Tavily MCP default |
350
+ | Web search (descriptive / academic) | Exa MCP |
351
+ | Library API docs | ctx7 CLI |
334
352
  | GitHub URL | gh CLI |
335
- | URL 抓取 | WebFetch 内置 |
353
+ | Single URL fetch | WebFetch built-in |
336
354
  | Gmail / Drive / Calendar | gws CLI |
337
- | 架构审查 (复杂) | gstack /plan-eng-review |
338
- | TDD 强制 (核心算法) | superpowers TDD OR mattpocock /tdd |
339
- | 关键模块 PR | gstack /review |
340
- | 大重构 PR 多维度审查 | 4-specialist Agent Team Pattern C |
341
- | session hand-off | discipline.protocols self-contained design doc |
342
- | `/auto` 复杂度大需求 | AI 1-shot judge → 自动建议 `--staged` (v3.2.0 NEW;n abort 建议手动 `/discuss`) |
343
- | `/auto` 需求理解度 | 开始前 prompt → n 自动加 `/research` 多源调研 (v3.2.0 NEW) |
355
+ | Architecture review (complex) | gstack /plan-eng-review |
356
+ | TDD mandatory (core algorithm) | superpowers TDD OR mattpocock /tdd |
357
+ | Critical module PR | gstack /review |
358
+ | Large refactor PR multi-dim review | 4-specialist Agent Team Pattern C |
359
+ | Cross-session hand-off | discipline.protocols self-contained design doc |
360
+ | `/auto` complexity for large requirements | AI 1-shot judge → auto-suggest `--staged` (n abort suggests manual `/discuss`) |
361
+ | `/auto` requirement understanding | prompt before start → n auto-adds `/research` multi-source investigation |
344
362
 
345
363
  ---
346
364
 
347
- ## 🛠️ 维护命令 (Operational)
365
+ ## 🛠️ Operational Commands
348
366
 
349
- > 这些是 harnessed 自身维护命令(setup / 健康检查 / 备份回滚 / 状态恢复等),日常 feature 开发用上面的 slash command 即可,这块通常不需要。
367
+ > These are harnessed's own maintenance commands (setup / health check / backup-rollback / state recovery, etc.). For day-to-day feature development just use the slash commands above — you usually don't need these.
350
368
 
351
- ### CLI 命令
369
+ ### CLI Commands
352
370
 
353
- | 命令 | 说明 |
371
+ | Command | Description |
354
372
  | ---- | ---- |
355
- | `harnessed setup` | 一次性 setup,装 workflow skills `~/.claude/skills/` + MCP `~/.claude.json` |
356
- | `harnessed resume` | session 中断后恢复至最近 checkpoint |
357
- | `harnessed status` | 当前 phase + lock holder |
358
- | `harnessed doctor` | 8-check 健康检查 (Node / MCP / jq / Win bash / 路由 / token budget ) |
359
- | `harnessed install <name>` | 装上游 manifest |
360
- | `harnessed uninstall <name>` | 反向卸载 |
361
- | `harnessed backup` | snapshot 备份管理 |
362
- | `harnessed rollback <timestamp>` | 一行回滚 (EOL preserve + sha1 verify) |
363
- | `harnessed gc` | 清理过期 backups |
364
- | `harnessed audit-log` | 路由透明日志 query (支持 `--filter` jq 表达式) |
365
-
366
- ### 参数 (Flags)
367
-
368
- > 所有命令默认 **apply (immediate write)**,无需加 flag。高级用户可加 `--dry-run` 预览。
369
-
370
- | Flag | 说明 |
373
+ | `harnessed setup` | One-time setup; installs workflow skills to `~/.claude/skills/` + MCP to `~/.claude.json` |
374
+ | `harnessed resume` | Resume from the most recent checkpoint after a session interruption |
375
+ | `harnessed status` | Current phase + lock holder |
376
+ | `harnessed doctor` | 8-check health check (Node / MCP / jq / Win bash / routing / token budget, etc.) |
377
+ | `harnessed install <name>` | Install an upstream manifest |
378
+ | `harnessed uninstall <name>` | Reverse uninstall |
379
+ | `harnessed backup` | Snapshot backup management |
380
+ | `harnessed rollback <timestamp>` | One-line rollback (EOL preserve + sha1 verify) |
381
+ | `harnessed gc` | Clean up expired backups |
382
+ | `harnessed audit-log` | Routing transparency log query (supports `--filter` jq expression) |
383
+
384
+ ### Flags
385
+
386
+ > All commands **apply (immediate write)** by default — no flag needed. Advanced users can add `--dry-run` to preview.
387
+
388
+ | Flag | Description |
371
389
  | ---- | ---- |
372
- | `--dry-run` | 预览不写盘 (高级用户 opt-in) |
373
- | `--non-interactive` | CI / 脚本场景 |
374
- | `--system` | L4 全局装允许 (否则降级 L1 npx ephemeral) |
375
- | `--yes` | uninstall 跳过交互 confirm |
376
- | `--full-diff` | 展开 > 200 行的 diff 折叠 |
377
- | `--no-color` | 强制 nocolor (即使 TTY) |
390
+ | `--dry-run` | Preview without writing to disk (advanced opt-in) |
391
+ | `--non-interactive` | CI / scripted scenarios |
392
+ | `--system` | Allow L4 global install (otherwise downgrade to L1 npx ephemeral) |
393
+ | `--yes` | Skip interactive confirm on uninstall |
394
+ | `--full-diff` | Expand diffs folded above 200 lines |
395
+ | `--no-color` | Force nocolor (even on TTY) |
378
396
 
379
- > `--apply` flag 仍保留为向后兼容 alias (no-op, 旧脚本不破)。
380
397
 
381
398
  ---
382
399
 
383
400
  ## ❓ FAQ
384
401
 
385
402
  <details>
386
- <summary><b>Q1. 装了 harnessed 还需要装 superpowers / gstack / GSD 上游吗?</b></summary>
403
+ <summary><b>Q1. Do I still need to install superpowers / gstack / GSD upstreams after installing harnessed?</b></summary>
387
404
 
388
405
  <br>
389
406
 
390
- 需要,但**用户感知 = 一行命令**:
407
+ Yes, but **the user experience = one command**:
391
408
 
392
409
  ```bash
393
- harnessed setup --apply # 自动装齐 gstack + GSD + superpowers + planning-with-files,24 workflow skill 一并落到 ~/.claude/skills/
410
+ harnessed setup # Auto-installs gstack + GSD + superpowers + planning-with-files; 25 workflow skills land in ~/.claude/skills/ + Agent Teams env var auto-written to ~/.claude.json
394
411
  ```
395
412
 
396
- 类比 `brew install <formula>` 装全套依赖你不需要单独 `brew install` 每个依赖项。
413
+ Think `brew install <formula>` pulling the full dependency set you don't need to `brew install` each dependency separately.
397
414
 
398
415
  </details>
399
416
 
400
417
  <details>
401
- <summary><b>Q2. 为什么不直接 vendor superpowers / gstack harnessed 仓库?</b></summary>
418
+ <summary><b>Q2. Why not just vendor superpowers / gstack into the harnessed repo?</b></summary>
402
419
 
403
420
  <br>
404
421
 
405
- 4 条理由:
422
+ 4 reasons:
406
423
 
407
- 1. **差异化哲学** — harnessed 是「装配主义包管理器」对位「all-in-one 自建派」。vendor = 失去 wedge → 沦为又一个 plugin pack
408
- 2. **License + attribution 噩梦**vendor 4-5 个主动维护的上游 = 复杂 license 拼盘
409
- 3. **上游升级反向**当前 manifest 描述,上游升级用户 re-install 即得新版;vendor 后手动 sync code 永远落后
410
- 4. **Bus factor 1** — maintainer 维护 vendor 4-5 上游 = 加速 burnout
424
+ 1. **Differentiation philosophy** — harnessed is the "assembly-ist package manager" counterposed to the "all-in-one self-built" camp. Vendoring = losing the wedge → becoming yet another plugin pack
425
+ 2. **License + attribution nightmare**vendoring 4-5 actively maintained upstreams = a complex license patchwork
426
+ 3. **Upstream upgrades flip direction** current manifest description lets users re-install for the latest version on upstream upgrade; vendoring forces manual code sync and falls perpetually behind
427
+ 4. **Bus factor 1** — a single maintainer keeping 4-5 vendored upstreams in sync = accelerated burnout
411
428
 
412
429
  </details>
413
430
 
414
431
  <details>
415
- <summary><b>Q3. gstack / GSD / superpowers 看起来都是 plan/discuss 类,是不是重叠?</b></summary>
432
+ <summary><b>Q3. gstack / GSD / superpowers all look like plan/discuss tools — aren't they overlapping?</b></summary>
416
433
 
417
434
  <br>
418
435
 
419
- **不是**。它们是三层栈的不同阶段:
436
+ **No**. They are different stages of the three-layer stack:
420
437
 
421
- | 阶段 | 上游 | 职责 |
438
+ | Stage | Upstream | Responsibility |
422
439
  | ---- | ---- | ---- |
423
- | Governance | gstack | 多角色决策关卡 (CEO / EM / Designer / Paranoid Engineer) |
424
- | Brainstorming | superpowers | 子任务设计澄清、方案对比 |
425
- | Orchestration | GSD | 高层 phase 任务图 + 依赖分析 |
426
- | Persistence | planning-with-files | 持久化 `task_plan.md` / `progress.md` / `findings.md` |
440
+ | Governance | gstack | Multi-role decision gates (CEO / EM / Designer / Paranoid Engineer) |
441
+ | Brainstorming | superpowers | Subtask design clarification, alternative comparison |
442
+ | Orchestration | GSD | High-level phase task graph + dependency analysis |
443
+ | Persistence | planning-with-files | Persists `task_plan.md` / `progress.md` / `findings.md` |
427
444
 
428
- `/discuss /plan /task /verify` 4 master 4 阶段串起来,每个 master 内部再 delegate 到对应 sub。每个阶段做不同事,输出喂给下一阶段。**没有合并**。
445
+ `/discuss /plan /task /verify` — the 4 masters string the 4 stages together; each master internally delegates to its sub. Each stage does a different thing and feeds the next. **No merging**.
429
446
 
430
447
  </details>
431
448
 
432
449
  <details>
433
- <summary><b>Q4. workflow phase 之间是自动跑还是等用户?</b></summary>
450
+ <summary><b>Q4. Do workflow phases run automatically or wait for the user?</b></summary>
434
451
 
435
452
  <br>
436
453
 
437
- `workflows/<name>/SKILL.md` frontmatter 的 `pause` 字段:
454
+ Depends on the `pause` field in `workflows/<name>/SKILL.md` frontmatter:
438
455
 
439
- - `pause: human_review` → 阻塞等用户 approve (governance gate / final lock,如 `/discuss-strategic` gstack `/office-hours` + `/plan-architecture` `/plan-eng-review` 锁定关卡)
440
- - `pause` → 自动 chain 到下一 phase
456
+ - `pause: human_review` → blocks waiting for user approval (governance gate / final lock, e.g. `/discuss-strategic` gstack `/office-hours` + `/plan-architecture` `/plan-eng-review` lock-in gate)
457
+ - No `pause` → auto-chains to the next phase
441
458
 
442
- 每个 phase 输出写到 `.harnessed/checkpoints/`,session 中断后 `harnessed resume` 从最近 checkpoint 继续。
459
+ Each phase output is written to `.harnessed/checkpoints/`; after a session interruption `harnessed resume` continues from the latest checkpoint.
443
460
 
444
461
  </details>
445
462
 
446
463
  <details>
447
- <summary><b>Q5. harnessed 自己是 CC plugin 吗?</b></summary>
464
+ <summary><b>Q5. Is harnessed itself a CC plugin?</b></summary>
448
465
 
449
466
  <br>
450
467
 
451
- 混合体:
468
+ A hybrid:
452
469
 
453
- - `npx harnessed@latest setup` 跑的是 **Node.js CLI** (`bin/harnessed`)
454
- - setup 装的 **workflow skills** (markdown) `~/.claude/skills/`,由 Claude Code 运行时加载
455
- - `/discuss` / `/plan` / `/task` / `/verify` 等是 CC 内的 slash command,触发 skill 执行
456
- - CLI CC skill 共享 `.harnessed/checkpoints/` 状态目录
470
+ - `npx harnessed@latest setup` runs the **Node.js CLI** (`bin/harnessed`)
471
+ - setup installs **workflow skills** (markdown) into `~/.claude/skills/`, loaded by the Claude Code runtime
472
+ - `/discuss` / `/plan` / `/task` / `/verify` etc. are slash commands inside CC that trigger skill execution
473
+ - The CLI and the CC skills share the `.harnessed/checkpoints/` state directory
457
474
 
458
475
  </details>
459
476
 
@@ -462,6 +479,6 @@ harnessed setup --apply # 自动装齐 gstack + GSD + superpowers + planning-wi
462
479
 
463
480
  ## License
464
481
 
465
- [Apache-2.0](./LICENSE) — [NOTICE](./NOTICE) ( Harness Inc. 商标 disclaimer)
482
+ [Apache-2.0](./LICENSE) — see [NOTICE](./NOTICE) (includes Harness Inc. trademark disclaimer)
466
483
 
467
- 支持开发: [![Sponsor](https://img.shields.io/github/sponsors/easyinplay?logo=github&label=Sponsor)](https://github.com/sponsors/easyinplay)
484
+ Support development: [![Sponsor](https://img.shields.io/github/sponsors/easyinplay?logo=github&label=Sponsor)](https://github.com/sponsors/easyinplay)