ai-dev-harness 0.1.0 → 0.1.2

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.
Files changed (45) hide show
  1. package/COLLEAGUE_TRIAL_GUIDE.md +175 -0
  2. package/ONLINE_INSTALL_GUIDE.md +458 -0
  3. package/README.md +253 -54
  4. package/dist/agent.js +74 -49
  5. package/dist/approval.js +64 -0
  6. package/dist/audit.js +1 -0
  7. package/dist/checkpoint.js +83 -0
  8. package/dist/cli.js +326 -99
  9. package/dist/config.js +118 -9
  10. package/dist/context.js +62 -21
  11. package/dist/contextScore.js +44 -0
  12. package/dist/diagnostics.js +58 -0
  13. package/dist/doctor.js +100 -0
  14. package/dist/feedback.js +5 -0
  15. package/dist/init.js +8 -20
  16. package/dist/integration.js +84 -93
  17. package/dist/loop.js +116 -0
  18. package/dist/mcp.js +29 -112
  19. package/dist/metrics.js +91 -0
  20. package/dist/replay.js +27 -0
  21. package/dist/runPaths.js +31 -0
  22. package/dist/summarize.js +170 -39
  23. package/dist/templates.js +39 -215
  24. package/package.json +5 -2
  25. package/scripts/read-evidence.ps1 +45 -3
  26. package/scripts/run-harness.ps1 +9 -6
  27. package/templates/default-project/AGENTS.md +9 -0
  28. package/templates/default-project/SKILLS.md +13 -0
  29. package/templates/default-project/TOOLS.md +11 -0
  30. package/templates/default-project/skills/add_feature/SKILL.md +34 -0
  31. package/templates/default-project/skills/add_feature/context.yaml +33 -0
  32. package/templates/default-project/skills/add_feature/verify.yaml +2 -0
  33. package/templates/default-project/skills/fix_bug/SKILL.md +45 -0
  34. package/templates/default-project/skills/fix_bug/context.yaml +33 -0
  35. package/templates/default-project/skills/fix_bug/verify.yaml +2 -0
  36. package/templates/default-project/skills/update_docs/SKILL.md +28 -0
  37. package/templates/default-project/skills/update_docs/context.yaml +30 -0
  38. package/templates/default-project/skills/update_docs/verify.yaml +2 -0
  39. package/templates/default-project/skills/write_tests/SKILL.md +30 -0
  40. package/templates/default-project/skills/write_tests/context.yaml +32 -0
  41. package/templates/default-project/skills/write_tests/verify.yaml +2 -0
  42. package/templates/integrations/claude/SKILL.md +115 -0
  43. package/templates/integrations/codex/AGENTS_BLOCK.md +82 -0
  44. package/templates/integrations/cursor/ai-dev-harness.mdc +55 -0
  45. package/templates/integrations/gemini/GEMINI_BLOCK.md +46 -0
@@ -0,0 +1,175 @@
1
+ # AI Dev Harness Colleague Trial Guide
2
+
3
+ ## 1. Install
4
+
5
+ ```bash
6
+ npm install -g ai-dev-harness
7
+ ```
8
+
9
+ Check:
10
+
11
+ ```bash
12
+ harness --help
13
+ ```
14
+
15
+ ## 2. Initialize In A Business Repository
16
+
17
+ Run inside a Git repository:
18
+
19
+ ```bash
20
+ harness init
21
+ ```
22
+
23
+ This creates Harness config, project skills, Claude/Codex/Cursor/Gemini conversation integration, and helper scripts.
24
+
25
+ Check local pilot readiness:
26
+
27
+ ```bash
28
+ harness doctor
29
+ ```
30
+
31
+ ## 3. Configure MCP Sources
32
+
33
+ Configure MCP in the execution agent so it can call the tools directly. Keep the same source metadata in `harness.yaml` for audit:
34
+
35
+ ```yaml
36
+ mcp:
37
+ codegraph:
38
+ type: sse
39
+ url: http://10.41.83.107:7878/mcp
40
+ headers: {}
41
+ knowledgeGraph:
42
+ type: http
43
+ url: http://10.41.83.107:9200/mcp
44
+ headers:
45
+ Authorization: Bearer ${OKF_TOKEN}
46
+ timeoutMs: 15000
47
+ ```
48
+
49
+ Set secrets outside Git:
50
+
51
+ ```powershell
52
+ $env:OKF_TOKEN="your-token"
53
+ ```
54
+
55
+ The execution agent should call MCP tools before triggering Harness and include important findings in the task text. Harness records MCP source configuration for audit, but does not implement MCP transport itself.
56
+
57
+ ## 4. Run A Smoke Test
58
+
59
+ ```bash
60
+ harness smoke --agent claude --live
61
+ ```
62
+
63
+ With Codex:
64
+
65
+ ```bash
66
+ harness smoke --agent codex --live
67
+ ```
68
+
69
+ Cursor / Gemini:
70
+
71
+ ```powershell
72
+ harness smoke --agent cursor --live
73
+ harness smoke --agent gemini --live
74
+ ```
75
+
76
+ `--live` streams Harness lifecycle logs and agent output in the current terminal.
77
+
78
+ ## 5. Use From Claude/Codex/Cursor/Gemini Conversation
79
+
80
+ After `harness init`, open Claude Code, Codex, Cursor, or Gemini in the repository and say:
81
+
82
+ ```text
83
+ Use AI Dev Harness to run fix_bug: fix the download resume progress issue.
84
+ ```
85
+
86
+ The agent should:
87
+
88
+ 1. Use configured MCP tools first.
89
+ 2. Report MCP preflight findings in the current conversation.
90
+ 3. Trigger Harness through `.harness/ai-dev-harness/scripts/run-harness.ps1`.
91
+ 4. Stream Harness lifecycle logs.
92
+ 5. Read and summarize the evidence directory.
93
+
94
+ ## 6. Expected MCP Preflight Shape
95
+
96
+ ```text
97
+ ## MCP Preflight Findings
98
+ - CodeGraph tools used:
99
+ - CodeGraph primary query:
100
+ - Source grouped by file:
101
+ - Current line-numbered source:
102
+ - Call paths:
103
+ - Dynamic dispatch hops:
104
+ - Blast-radius summary:
105
+ - Knowledge Graph tools used:
106
+ - Candidate concept_ids:
107
+ - Read tools used:
108
+ - Evidence sections/chunks:
109
+ - ADRs / decisions:
110
+ - Module notes:
111
+ - API notes / runbooks:
112
+ - Audit/backlink findings:
113
+ - Missing context:
114
+ ```
115
+
116
+ ## 7. Evidence Files
117
+
118
+ Each run writes `runs/<run_id>/`:
119
+
120
+ ```text
121
+ intake.json Task, skill, agent, Git state
122
+ mcp_queries.jsonl Agent-driven MCP source records
123
+ context_pack.md Context assembly protocol and local fallback context
124
+ agent_prompt.md Final prompt sent to the execution agent
125
+ plan.md Harness execution-stage protocol
126
+ execution.log Agent stdout/stderr
127
+ agent_contract.json Required-section contract check
128
+ git_diff.patch Code changes
129
+ verify.json Verification results
130
+ verify_diagnostics.json Verification failure diagnostics
131
+ context_score.json Context evidence score
132
+ approval_required.json Approval gate result
133
+ feedback.jsonl Harness-visible machine feedback events
134
+ checkpoint.json Git checkpoint and restore support
135
+ pre_iteration_diff.patch Diff before the iteration
136
+ post_iteration_diff.patch Diff after the iteration
137
+ loop_review.json Per-iteration evaluation and failure diagnosis
138
+ loop_report.md Human-readable correction-loop report
139
+ summary.md Review/PR summary
140
+ persist_suggestions.md Knowledge persistence suggestions
141
+ audit.jsonl Full audit event log
142
+ ```
143
+
144
+ Read evidence:
145
+
146
+ ```bash
147
+ powershell -ExecutionPolicy Bypass -File ".harness/ai-dev-harness/scripts/read-evidence.ps1" -Run <run_id>
148
+ ```
149
+
150
+ ## 8. Troubleshooting
151
+
152
+ If `harness` is not found, check npm global bin is in `PATH`.
153
+
154
+ If `harness run must execute inside a Git repository`, run inside a business Git repository and confirm:
155
+
156
+ ```bash
157
+ git status
158
+ ```
159
+
160
+ If the current Agent cannot see MCP tools, check that Agent's MCP configuration first:
161
+
162
+ - Wrong MCP URL
163
+ - Missing bearer token
164
+ - Service down
165
+ - Endpoint path is not `/mcp`
166
+
167
+ Harness can still run with local repository fallback context, but the agent should report missing MCP context.
168
+
169
+ ## 9. Acceptance Checklist
170
+
171
+ - `harness init` creates config, skills, and Claude/Codex/Cursor/Gemini integration.
172
+ - Claude/Codex/Cursor/Gemini can trigger Harness from conversation.
173
+ - Agent reports MCP preflight findings.
174
+ - `agent_contract.json` shows whether required sections were produced.
175
+ - `verify.json`, `loop_review.json`, `summary.md`, and `audit.jsonl` are generated.
@@ -0,0 +1,458 @@
1
+ # AI Dev Harness 线上安装使用手册
2
+
3
+ ## 1. 适用对象
4
+
5
+ 本手册面向需要在业务 Git 仓库中使用 AI Dev Harness 的研发同学。
6
+
7
+ AI Dev Harness 的定位是:
8
+
9
+ ```text
10
+ Codex / Claude / Cursor / Gemini 负责理解任务、调用 MCP、使用 Skill、修改代码。
11
+ Harness 负责执行闭环、日志、验证、审计、总结和知识沉淀建议。
12
+ ```
13
+
14
+ Harness 不是 MCP Client。CodeGraph / Knowledge Graph MCP 由当前执行器自己调用。
15
+
16
+ ## 2. 环境要求
17
+
18
+ - Node.js >= 20
19
+ - npm
20
+ - Git
21
+ - Claude Code、Codex CLI、Cursor Agent、Gemini CLI 至少安装一个
22
+ - 业务仓库已经是 Git 仓库
23
+
24
+ 检查命令:
25
+
26
+ ```powershell
27
+ node -v
28
+ npm -v
29
+ git status
30
+ claude --version
31
+ codex --version
32
+ cursor-agent --version
33
+ gemini --version
34
+ ```
35
+
36
+ `claude`、`codex`、`cursor-agent`、`gemini` 任一执行器可用即可;具体命令可在 `harness.yaml` 覆盖。
37
+
38
+ ## 3. 线上安装
39
+
40
+ 全局安装:
41
+
42
+ ```powershell
43
+ npm install -g ai-dev-harness
44
+ ```
45
+
46
+ 检查是否安装成功:
47
+
48
+ ```powershell
49
+ harness --help
50
+ ```
51
+
52
+ 正确入口是:
53
+
54
+ ```powershell
55
+ harness
56
+ ```
57
+
58
+ 不要在业务仓库中执行:
59
+
60
+ ```powershell
61
+ node dist/cli.js init
62
+ ```
63
+
64
+ `node dist/cli.js` 只适用于 AI Dev Harness 源码仓,不适用于普通业务仓。
65
+
66
+ ## 4. 在业务仓库初始化
67
+
68
+ 进入业务仓库:
69
+
70
+ ```powershell
71
+ cd C:\yuntun_app\360download_mobile
72
+ git status
73
+ ```
74
+
75
+ 初始化 Harness:
76
+
77
+ ```powershell
78
+ harness init
79
+ ```
80
+
81
+ 检查本地试点环境:
82
+ ```powershell
83
+ harness doctor
84
+ ```
85
+
86
+ `doctor` 只检查 Git、配置、Skill、Agent 命令、MCP source metadata 和验证命令强度,不会连接 MCP,也不会调用 Agent。
87
+
88
+ 初始化后会生成:
89
+
90
+ ```text
91
+ harness.yaml
92
+ AGENTS.md
93
+ TOOLS.md
94
+ SKILLS.md
95
+ skills/
96
+ .claude/skills/ai-dev-harness/SKILL.md
97
+ .cursor/rules/ai-dev-harness.mdc
98
+ GEMINI.md
99
+ .harness/ai-dev-harness/scripts/run-harness.ps1
100
+ .harness/ai-dev-harness/scripts/read-evidence.ps1
101
+ runs/
102
+ ```
103
+
104
+ `harness init` 默认会安装 Claude/Codex/Cursor/Gemini 对话集成。
105
+
106
+ 如果只想初始化 CLI 配置,不安装对话集成:
107
+
108
+ ```powershell
109
+ harness init --no-integration
110
+ ```
111
+
112
+ ## 5. 配置 MCP
113
+
114
+ Claude/Codex 的 MCP 配置示例:
115
+
116
+ ```json
117
+ {
118
+ "mcpServers": {
119
+ "okf-360": {
120
+ "url": "http://10.41.83.107:9200/mcp",
121
+ "headers": {
122
+ "Authorization": "Bearer ${OKF_TOKEN}"
123
+ }
124
+ },
125
+ "code-graph": {
126
+ "type": "sse",
127
+ "url": "http://10.41.83.107:7878/mcp"
128
+ }
129
+ }
130
+ }
131
+ ```
132
+
133
+ 业务仓库中的 `harness.yaml` 也保留 MCP source metadata,用于审计记录:
134
+
135
+ ```yaml
136
+ mcp:
137
+ codegraph:
138
+ type: sse
139
+ url: http://10.41.83.107:7878/mcp
140
+ headers: {}
141
+ knowledgeGraph:
142
+ type: http
143
+ url: http://10.41.83.107:9200/mcp
144
+ headers:
145
+ Authorization: Bearer ${OKF_TOKEN}
146
+ timeoutMs: 15000
147
+ ```
148
+
149
+ 设置 token:
150
+
151
+ ```powershell
152
+ $env:OKF_TOKEN="your-token"
153
+ ```
154
+
155
+ 长期生效可以使用:
156
+
157
+ ```powershell
158
+ setx OKF_TOKEN "your-token"
159
+ ```
160
+
161
+ 注意:不要把真实 token 提交到 Git。
162
+
163
+ ## 6. 命令行使用
164
+
165
+ 推荐先跑只读冒烟:
166
+
167
+ ```powershell
168
+ harness smoke --agent claude --live
169
+ ```
170
+
171
+ 这等价于执行一个 `update_docs` 只读任务,用来确认本地闭环、日志和证据目录都正常。
172
+
173
+ 只读分析:
174
+
175
+ ```powershell
176
+ harness run --task "分析下载模块启动流程。Do not modify repository files." --skill update_docs --agent claude --live
177
+ ```
178
+
179
+ 修 bug:
180
+
181
+ ```powershell
182
+ harness run --task "修复下载续传进度异常问题" --skill fix_bug --agent claude --live
183
+ ```
184
+
185
+ 写测试:
186
+
187
+ ```powershell
188
+ harness run --task "为下载任务状态流转补充测试" --skill write_tests --agent claude --live
189
+ ```
190
+
191
+ 使用 Codex:
192
+
193
+ ```powershell
194
+ harness run --task "分析下载模块启动流程。Do not modify repository files." --skill update_docs --agent codex --live
195
+ ```
196
+
197
+ Cursor / Gemini:
198
+
199
+ ```powershell
200
+ harness run --task "修复下载续传进度异常问题" --skill fix_bug --agent cursor --live
201
+ harness run --task "修复下载续传进度异常问题" --skill fix_bug --agent gemini --live
202
+ ```
203
+
204
+ ## 7. 在 Claude/Codex/Cursor/Gemini 对话中使用
205
+
206
+ 初始化后,可以直接在 Claude Code、Codex、Cursor 或 Gemini 对话中说:
207
+
208
+ ```text
209
+ Use AI Dev Harness to run update_docs: 分析下载模块启动流程。Do not modify repository files.
210
+ ```
211
+
212
+ 或者:
213
+
214
+ ```text
215
+ Use AI Dev Harness to run fix_bug: 修复下载续传进度异常问题。
216
+ ```
217
+
218
+ Agent 应该执行以下流程:
219
+
220
+ 1. 先调用 CodeGraph MCP / Knowledge Graph MCP。
221
+ 2. 在当前对话中输出 MCP Preflight Findings。
222
+ 3. 调用 Harness CLI。
223
+ 4. 实时展示 Harness 生命周期日志。
224
+ 5. 读取并总结 `runs/<run_id>/` 证据目录。
225
+
226
+ ## 8. MCP Preflight 输出格式
227
+
228
+ Agent 在触发 Harness 前,应按以下格式汇报:
229
+
230
+ 如果 CodeGraph 使用的是 `colbymchenry/codegraph`,默认优先调用 `codegraph_explore`。用任务里的业务流程、文件路径、函数/类/符号名或错误现象作为 query,并重点读取它返回的 grouped source、line-numbered source、call paths、dynamic dispatch hops 和 blast-radius summary。
231
+
232
+ 如果 Knowledge Graph 使用的是 `browser_knowledge_service`,推荐读取顺序:
233
+
234
+ 1. 用 `list_path`、`search_docs`、`search_sections`、`search_chunks` 缩小范围。
235
+ 2. RAG 场景优先用 `answer_context`;需要自控排序时用 `hybrid_search`。
236
+ 3. 定位 concept_id 后先用 `read_doc_outline` 看结构。
237
+ 4. 再用 `read_section`、`read_doc_range`、`read_chunk`、`get_related_chunks` 精读证据。
238
+ 5. 需要关系时用 `get_backlinks`,需要近期变更记录时用 `get_audit_log`。
239
+ 6. v1 不直接调用 `propose_doc` 写入知识库;只生成 `persist_suggestions.md`。
240
+
241
+ ```text
242
+ ## MCP Preflight Findings
243
+ - CodeGraph tools used:
244
+ - CodeGraph primary query:
245
+ - Source grouped by file:
246
+ - Current line-numbered source:
247
+ - Call paths:
248
+ - Dynamic dispatch hops:
249
+ - Blast-radius summary:
250
+ - Knowledge Graph tools used:
251
+ - Candidate concept_ids:
252
+ - Read tools used:
253
+ - Evidence sections/chunks:
254
+ - ADRs / decisions:
255
+ - Module notes:
256
+ - API notes / runbooks:
257
+ - Audit/backlink findings:
258
+ - Missing context:
259
+ ```
260
+
261
+ 这些发现应写入 Harness 的 task 文本,进入审计证据。
262
+
263
+ ## 9. OKF 知识沉淀建议
264
+
265
+ `persist_suggestions.md` 只生成可评审的 OKF 候选内容,不自动写入 Knowledge Graph。
266
+
267
+ - 候选文档路径应落到 `/<project>/overview/`、`/<project>/features/`、`/<project>/metrics/`、`/<project>/api/`、`/<project>/playbooks/` 或 `/<project>/references/`。
268
+ - 每个候选 concept 应包含 `type`、`title`、`description`、`tags`、`timestamp`;API/数据类建议补充 `resource`。
269
+ - `## 相关` 必须使用有效 Markdown 链接,推荐 bundle 根相对路径。
270
+ - `type: API Reference` 需要包含 `## 关键实现锚点` 和 `### Agent 使用建议`。
271
+ - 合入知识库前应同步更新对应目录的 `index.md` 和 `log.md`。
272
+ - 不要写入密钥、Token、明文密码、未脱敏用户数据、未公开内网 IP。
273
+
274
+ ## 10. 运行证据目录
275
+
276
+ 每次运行会生成:
277
+
278
+ ```text
279
+ runs/<run_id>/
280
+ ```
281
+
282
+ 核心文件:
283
+
284
+ ```text
285
+ intake.json 任务、Skill、Agent、Git 状态
286
+ mcp_queries.jsonl Agent-driven MCP source metadata
287
+ context_pack.md 上下文组装协议和本地兜底上下文
288
+ agent_prompt.md 发给当前执行器的最终提示词
289
+ plan.md Harness 执行阶段协议
290
+ execution.log Agent stdout/stderr
291
+ agent_contract.json Agent 输出契约检查
292
+ git_diff.patch 代码变更
293
+ verify.json 验证结果
294
+ verify_diagnostics.json 验证失败诊断
295
+ context_score.json 上下文证据评分
296
+ approval_required.json 审批门禁结果
297
+ feedback.jsonl Harness 可见机器反馈事件
298
+ checkpoint.json Git checkpoint 和 restore 支持状态
299
+ pre_iteration_diff.patch 本轮前 diff
300
+ post_iteration_diff.patch 本轮后 diff
301
+ loop_review.json 每轮评估、失败归因和下一步动作
302
+ loop_report.md 自纠偏循环报告
303
+ summary.md 评审/PR 总结
304
+ persist_suggestions.md 知识沉淀建议
305
+ audit.jsonl 完整审计事件流
306
+ ```
307
+
308
+ 读取证据:
309
+
310
+ ```powershell
311
+ powershell -ExecutionPolicy Bypass -File ".harness/ai-dev-harness/scripts/read-evidence.ps1" -Run <run_id>
312
+ ```
313
+
314
+ ## 11. 自纠偏循环
315
+
316
+ 默认只跑 1 轮,行为等同普通执行。需要允许 Harness 在低风险失败后自动 rework,可在 `harness.yaml` 中配置:
317
+
318
+ ```yaml
319
+ loop:
320
+ maxIterations: 2
321
+ stopOn:
322
+ - same_failure_repeated
323
+ - max_iterations_reached
324
+ ```
325
+
326
+ 自动 rework 的典型触发条件:
327
+
328
+ - Agent 命令失败。
329
+ - Agent 输出不符合固定报告契约。
330
+ - 验证命令失败。
331
+
332
+ 停止并人工评审的典型条件:
333
+
334
+ - 连续两轮同类失败。
335
+ - 达到最大轮次。
336
+ - 需要扩大范围、修改公共接口、安全策略,或目标本身不明确。
337
+
338
+ ## 12. 重新验证和总结
339
+
340
+ 重新运行验证:
341
+
342
+ ```powershell
343
+ harness verify --run <run_id>
344
+ ```
345
+
346
+ 重新生成总结:
347
+
348
+ ```powershell
349
+ harness summarize --run <run_id>
350
+ ```
351
+
352
+ 恢复 clean baseline 下的某轮修改:
353
+
354
+ ```powershell
355
+ harness restore --run <run_id> --iteration 1
356
+ ```
357
+
358
+ 查看本地 runs 指标:
359
+
360
+ ```powershell
361
+ harness runs metrics
362
+ harness runs metrics --json
363
+ ```
364
+
365
+ 回放历史任务:
366
+
367
+ ```powershell
368
+ harness replay --run <run_id> --dry
369
+ harness replay --run <run_id> --agent claude
370
+ ```
371
+
372
+ ## 13. 常见问题
373
+
374
+ ### 1. `Cannot find module '...\dist\cli.js'`
375
+
376
+ 原因:在业务仓库里执行了错误命令:
377
+
378
+ ```powershell
379
+ node dist/cli.js init
380
+ ```
381
+
382
+ 解决:
383
+
384
+ ```powershell
385
+ harness init
386
+ ```
387
+
388
+ ### 2. `harness` 命令不存在
389
+
390
+ 重新安装:
391
+
392
+ ```powershell
393
+ npm install -g ai-dev-harness
394
+ ```
395
+
396
+ 检查 npm 全局 bin 是否在 `PATH`。
397
+
398
+ ### 3. `harness run 必须在 Git 仓库内执行`
399
+
400
+ 进入业务 Git 仓库后再执行:
401
+
402
+ ```powershell
403
+ git status
404
+ harness run --task "..." --skill update_docs --agent claude --live
405
+ ```
406
+
407
+ ### 4. Claude/Codex 看不到 MCP 工具
408
+
409
+ 优先检查 Claude/Codex 的 MCP 配置,而不是 Harness:
410
+
411
+ - MCP URL 是否正确
412
+ - token 是否有效
413
+ - 服务是否可访问
414
+ - CodeGraph 是否配置为 `type: sse`
415
+ - Knowledge Graph 是否带 Authorization header
416
+
417
+ ### 5. Agent 输出不符合要求
418
+
419
+ 查看:
420
+
421
+ ```text
422
+ runs/<run_id>/agent_contract.json
423
+ ```
424
+
425
+ Harness 会检查 Agent 是否输出:
426
+
427
+ - `Impact Analysis`
428
+ - `Plan`
429
+ - `Execution Notes`
430
+ - `Verification Notes`
431
+ - `Final Report`
432
+
433
+ ## 14. 推荐团队使用方式
434
+
435
+ 第一次接入:
436
+
437
+ ```powershell
438
+ npm install -g ai-dev-harness
439
+ cd <business-repo>
440
+ harness init
441
+ harness doctor
442
+ harness smoke --agent claude --live
443
+ ```
444
+
445
+ 日常使用:
446
+
447
+ ```text
448
+ 在 Claude/Codex 对话中说:
449
+ Use AI Dev Harness to run <skill>: <task>
450
+ ```
451
+
452
+ 推荐从只读任务开始:
453
+
454
+ ```text
455
+ Use AI Dev Harness to run update_docs: 分析下载模块启动流程。Do not modify repository files.
456
+ ```
457
+
458
+ 确认流程稳定后,再用于 `fix_bug`、`write_tests`、`add_feature`。