@mengde1231/rudder 0.6.20 → 0.6.22

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 (47) hide show
  1. package/README.md +148 -136
  2. package/bin/rudder.js +0 -0
  3. package/dist/migrations/manifests/0.4.0-beta.1.json +5 -5
  4. package/dist/migrations/manifests/0.5.14.json +9 -0
  5. package/dist/migrations/manifests/0.5.15.json +9 -0
  6. package/dist/migrations/manifests/0.5.16.json +9 -0
  7. package/dist/migrations/manifests/0.5.17.json +9 -0
  8. package/dist/migrations/manifests/0.5.19.json +9 -0
  9. package/dist/migrations/manifests/0.5.20.json +9 -0
  10. package/dist/migrations/manifests/0.5.21.json +9 -0
  11. package/dist/migrations/manifests/0.5.22.json +9 -0
  12. package/dist/migrations/manifests/0.5.23.json +9 -0
  13. package/dist/migrations/manifests/0.5.30.json +9 -0
  14. package/dist/migrations/manifests/0.6.1.json +9 -0
  15. package/dist/migrations/manifests/0.6.11.json +9 -0
  16. package/dist/migrations/manifests/0.6.20.json +9 -0
  17. package/dist/migrations/manifests/0.6.21.json +9 -0
  18. package/dist/migrations/manifests/0.6.22.json +9 -0
  19. package/dist/templates/codex/config.toml +30 -30
  20. package/dist/templates/common/bundled-skills/rudder-meta/references/customize-local/change-workflow.md +5 -4
  21. package/dist/templates/common/bundled-skills/rudder-meta/references/local-architecture/task-system.md +7 -2
  22. package/dist/templates/common/bundled-skills/rudder-spec-bootstarp/SKILL.md +41 -41
  23. package/dist/templates/common/bundled-skills/rudder-spec-bootstarp/references/mcp-setup.md +90 -90
  24. package/dist/templates/common/bundled-skills/rudder-spec-bootstarp/references/repository-analysis.md +59 -59
  25. package/dist/templates/common/bundled-skills/rudder-spec-bootstarp/references/spec-task-planning.md +61 -61
  26. package/dist/templates/common/bundled-skills/rudder-spec-bootstarp/references/spec-writing.md +70 -70
  27. package/dist/templates/common/commands/continue.md +9 -5
  28. package/dist/templates/common/commands/start.md +8 -8
  29. package/dist/templates/common/skills/brainstorm.md +28 -27
  30. package/dist/templates/common/skills/check.md +8 -1
  31. package/dist/templates/rudder/config.yaml +13 -2
  32. package/dist/templates/rudder/index.d.ts +1 -0
  33. package/dist/templates/rudder/index.d.ts.map +1 -1
  34. package/dist/templates/rudder/index.js +2 -0
  35. package/dist/templates/rudder/index.js.map +1 -1
  36. package/dist/templates/rudder/scripts/common/task_context.py +42 -1
  37. package/dist/templates/rudder/scripts/common/task_readiness.py +176 -0
  38. package/dist/templates/rudder/scripts/common/task_store.py +23 -36
  39. package/dist/templates/rudder/scripts/common/types.py +1 -0
  40. package/dist/templates/rudder/scripts/common/workflow_phase.py +45 -0
  41. package/dist/templates/rudder/scripts/task.py +45 -4
  42. package/dist/templates/rudder/workflow.md +75 -37
  43. package/dist/utils/task-json.d.ts +6 -0
  44. package/dist/utils/task-json.d.ts.map +1 -1
  45. package/dist/utils/task-json.js +6 -0
  46. package/dist/utils/task-json.js.map +1 -1
  47. package/package.json +26 -27
package/README.md CHANGED
@@ -1,136 +1,148 @@
1
- <p align="center">
2
- <picture>
3
- <source srcset="assets/rudder-logo.png" media="(prefers-color-scheme: dark)">
4
- <source srcset="assets/rudder-logo.png" media="(prefers-color-scheme: light)">
5
- <img src="assets/rudder-logo.png" alt="Rudder Logo" width="500" style="image-rendering: -webkit-optimize-contrast; image-rendering: crisp-edges;">
6
- </picture>
7
- </p>
8
-
9
- <p align="center">
10
- <strong>Your AI coding assistant keeps forgetting your project? This fixes that.</strong><br/>
11
- <sub>Start a feature in Gemini, continue in Claude Code, hand it off to a teammate — no one needs to re-explain everything. Context, specs, and standards live in your repo and get injected automatically.</sub>
12
- </p>
13
-
14
- <p align="center">
15
- <a href="./README_CN.md">简体中文</a>
16
- </p>
17
-
18
- <p align="center">
19
- <a href="https://www.npmjs.com/package/@mengde1231/rudder"><img src="https://img.shields.io/npm/v/@mengde1231/rudder.svg?style=flat-square&color=2563eb" alt="npm version" /></a>
20
- <a href="https://www.npmjs.com/package/@mengde1231/rudder"><img src="https://img.shields.io/npm/dw/@mengde1231/rudder?style=flat-square&color=cb3837&label=downloads" alt="npm downloads" /></a>
21
- <a href="https://github.com/MengDe1231/Rudder/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-16a34a.svg?style=flat-square" alt="license" /></a>
22
- <a href="https://github.com/MengDe1231/Rudder/stargazers"><img src="https://img.shields.io/github/stars/MengDe1231/Rudder?style=flat-square&color=eab308" alt="stars" /></a>
23
- </p>
24
-
25
- ## What problem does this solve?
26
-
27
- If you've used AI for coding, you know the drill: every new session the assistant has no idea about your project. You explain the same things over and over.
28
-
29
- Rudder fixes that. **Your specs, memory, and task state all live in the repo. Every session gets exactly the context it needs — automatically.**
30
-
31
- | Capability | What it changes |
32
- | --- | --- |
33
- | **Auto-injected specs** | Write your conventions once in `.rudder/spec/`, Rudder injects the right files into each session. No more copy-pasting rules every time. |
34
- | **Task-centered flow** | PRDs, implementation records, and review context all live in `.rudder/tasks/`. AI work stays structured, not scattered across chat history. |
35
- | **Project memory** | `.rudder/workspace/` journals carry forward what happened last time. New session? It knows where you left off. |
36
- | **Team-shared standards** | Specs version-control with your code. One person figures out a good pattern, everyone gets it for free. |
37
- | **14 platforms, one setup** | Same Rudder structure everywhere. Switch tools, keep your workflow. |
38
-
39
- ## Supported Platforms
40
-
41
- 14 AI coding platforms, one setup. Pick what you use:
42
-
43
- | Agent | IDE / Platform |
44
- | --- | --- |
45
- | Claude Code | CLI, VS Code, JetBrains, Web |
46
- | Gemini | Gemini CLI |
47
- | Cursor | Cursor IDE |
48
- | Codex | VS Code |
49
- | OpenCode | OpenCode IDE |
50
- | CodeBuddy | CodeBuddy IDE |
51
- | Qoder | Qoder IDE |
52
- | Kiro | Kiro IDE |
53
- | Pi | Pi CLI |
54
- | Windsurf | Windsurf IDE |
55
- | Copilot | VS Code, JetBrains |
56
- | Antigravity | Antigravity CLI |
57
- | Kilo | Kilo CLI |
58
- | Droid | Factory IDE |
59
-
60
- ## What you need
61
-
62
- - **Node.js** >= 18
63
- - **Python** >= 3.9
64
-
65
- ## Quick Start
66
-
67
- ```bash
68
- # 1. Install
69
- npm install -g @mengde1231/rudder@latest
70
-
71
- # 2. Initialize (all platforms)
72
- rudder init -u your-name
73
-
74
- # 3. Or just the ones you actually use (cleaner)
75
- rudder init --cursor --opencode --codex -u your-name
76
- ```
77
-
78
- ## How it works
79
-
80
- Rudder runs a 4-phase loop every session:
81
-
82
- 1. **Plan** — `rudder-brainstorm` walks through requirements and writes `prd.md`. Research-heavy stuff goes to a `rudder-research` sub-agent. Output: curated specs + research files, wired up via `implement.jsonl` / `check.jsonl`.
83
- 2. **Implement** — `rudder-implement` writes code from the PRD with context already injected. No git commit here — that's intentional.
84
- 3. **Verify** — `rudder-check` reviews the diff against specs, runs lint, type-check, compile, and tests. Fixes what it can, reports what it can't.
85
- 4. **Finish** — `rudder-update-spec` promotes new learnings back into `.rudder/spec/` so the next session starts smarter.
86
-
87
- ## FAQ
88
-
89
- <details>
90
- <summary><strong>How is this different from <code>CLAUDE.md</code>, <code>AGENTS.md</code>, or <code>.cursorrules</code>?</strong></summary>
91
-
92
- Those are useful entry points — until they become 3,000-line monoliths nobody reads. Rudder layers things: scoped specs, per-task PRDs, workflow gates, cross-platform adapters. <strong>One simple rule: don't cram everything into one file.</strong>
93
-
94
- </details>
95
-
96
- <details>
97
- <summary><strong>Is Rudder only for Claude Code?</strong></summary>
98
-
99
- Nope. Rudder is a project-layer thing. Works across 14 coding agents and IDEs. Use Gemini for frontend today, Claude Code for backend tomorrow, Codex for review the day after.
100
-
101
- </details>
102
-
103
- <details>
104
- <summary><strong>Solo dev or team?</strong></summary>
105
-
106
- Both. Solo devs get project memory and repeatable workflow. Teams get the bigger win: shared standards, clear task boundaries, reviewable context, and platform portability.
107
-
108
- </details>
109
-
110
- <details>
111
- <summary><strong>Do I have to write every spec file by hand?</strong></summary>
112
-
113
- Nope. Most teams let AI draft specs from existing code first, then tighten the important stuff by hand. Rudder works best when the high-signal rules are explicit and versioned — the rest AI can figure out.
114
-
115
- </details>
116
-
117
- <details>
118
- <summary><strong>Will this cause merge conflicts in a team?</strong></summary>
119
-
120
- Nah. Personal workspace journals are per-developer. Shared specs and tasks go through git like any other artifact — merge conflicts are just merge conflicts, nothing new.
121
-
122
- </details>
123
-
124
- ## Acknowledgments
125
-
126
- Rudder wouldn't exist without the open-source coding agent community. We studied how many projects solve the same problems — context injection, workflow gates, multi-platform support — and built the version we wished we had.
127
-
128
- ## Star History
129
-
130
- [![Star History Chart](https://api.star-history.com/svg?repos=MengDe1231/Rudder&type=Date)](https://star-history.com/#MengDe1231/Rudder&Date)
131
-
132
- <p align="center">
133
- <a href="https://github.com/MengDe1231/Rudder">GitHub</a> •
134
- <a href="https://discord.com/invite/tWcCZ3aRHc">Discord</a> •
135
- <a href="https://github.com/MengDe1231/Rudder/blob/main/LICENSE">AGPL-3.0 License</a>
136
- </p>
1
+ <p align="center">
2
+ <picture>
3
+ <source srcset="assets/rudder-logo.png" media="(prefers-color-scheme: dark)">
4
+ <source srcset="assets/rudder-logo.png" media="(prefers-color-scheme: light)">
5
+ <img src="assets/rudder-logo.png" alt="Rudder Logo" width="500" style="image-rendering: -webkit-optimize-contrast; image-rendering: crisp-edges;">
6
+ </picture>
7
+ </p>
8
+
9
+ <p align="center">
10
+ <strong>Your AI coding assistant keeps forgetting your project? This fixes that.</strong><br/>
11
+ <sub>Start a feature in Gemini, continue in Claude Code, hand it off to a teammate — no one needs to re-explain everything. Context, specs, and standards live in your repo and get injected automatically.</sub>
12
+ </p>
13
+
14
+ <p align="center">
15
+ <a href="./README_CN.md">简体中文</a>
16
+ </p>
17
+
18
+ <p align="center">
19
+ <a href="https://www.npmjs.com/package/@mengde1231/rudder"><img src="https://img.shields.io/npm/v/@mengde1231/rudder.svg?style=flat-square&color=2563eb" alt="npm version" /></a>
20
+ <a href="https://www.npmjs.com/package/@mengde1231/rudder"><img src="https://img.shields.io/npm/dw/@mengde1231/rudder?style=flat-square&color=cb3837&label=downloads" alt="npm downloads" /></a>
21
+ <a href="https://github.com/MengDe1231/Rudder/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-16a34a.svg?style=flat-square" alt="license" /></a>
22
+ <a href="https://github.com/MengDe1231/Rudder/stargazers"><img src="https://img.shields.io/github/stars/MengDe1231/Rudder?style=flat-square&color=eab308" alt="stars" /></a>
23
+ </p>
24
+
25
+ ## What problem does this solve?
26
+
27
+ If you've used AI for coding, you know the drill: every new session the assistant has no idea about your project. You explain the same things over and over.
28
+
29
+ Rudder fixes that. **Your specs, memory, and task state all live in the repo. Every session gets exactly the context it needs — automatically.**
30
+
31
+ | Capability | What it changes |
32
+ | --- | --- |
33
+ | **Auto-injected specs** | Write your conventions once in `.rudder/spec/`, Rudder injects the right files into each session. No more copy-pasting rules every time. |
34
+ | **Task-centered flow** | PRDs, implementation records, and review context all live in `.rudder/tasks/`. AI work stays structured, not scattered across chat history. |
35
+ | **Project memory** | `.rudder/workspace/` journals carry forward what happened last time. New session? It knows where you left off. |
36
+ | **Team-shared standards** | Specs version-control with your code. One person figures out a good pattern, everyone gets it for free. |
37
+ | **14 platforms, one setup** | Same Rudder structure everywhere. Switch tools, keep your workflow. |
38
+
39
+ ## Supported Platforms
40
+
41
+ 14 AI coding platforms, one setup. Pick what you use:
42
+
43
+ | Agent | IDE / Platform |
44
+ | --- | --- |
45
+ | Claude Code | CLI, VS Code, JetBrains, Web |
46
+ | Gemini | Gemini CLI |
47
+ | Cursor | Cursor IDE |
48
+ | Codex | VS Code |
49
+ | OpenCode | OpenCode IDE |
50
+ | CodeBuddy | CodeBuddy IDE |
51
+ | Qoder | Qoder IDE |
52
+ | Kiro | Kiro IDE |
53
+ | Pi | Pi CLI |
54
+ | Windsurf | Windsurf IDE |
55
+ | Copilot | VS Code, JetBrains |
56
+ | Antigravity | Antigravity CLI |
57
+ | Kilo | Kilo CLI |
58
+ | Droid | Factory IDE |
59
+
60
+ ## What you need
61
+
62
+ - **Node.js** >= 18
63
+ - **Python** >= 3.9
64
+
65
+ ## Quick Start
66
+
67
+ ```bash
68
+ # 1. Install
69
+ npm install -g @mengde1231/rudder@latest
70
+
71
+ # 2. Initialize (all platforms)
72
+ rudder init -u your-name
73
+
74
+ # 3. Or just the ones you actually use (cleaner)
75
+ rudder init --cursor --opencode --codex -u your-name
76
+ ```
77
+
78
+ ## How it works
79
+
80
+ Rudder runs a 4-phase loop every session:
81
+
82
+ 1. **Plan** — `rudder-brainstorm` walks through requirements and writes `prd.md`. Research-heavy stuff goes to a `rudder-research` sub-agent. Output: curated specs + research files, wired up via `implement.jsonl` / `check.jsonl`.
83
+ 2. **Implement** — `rudder-implement` writes code from the PRD with context already injected. No git commit here — that's intentional.
84
+ 3. **Verify** — `rudder-check` reviews the diff against specs, runs lint, type-check, compile, and tests. Fixes what it can, reports what it can't.
85
+ 4. **Finish** — `rudder-update-spec` promotes new learnings back into `.rudder/spec/` so the next session starts smarter.
86
+
87
+ ## FAQ
88
+
89
+ <details>
90
+ <summary><strong>How is this different from <code>CLAUDE.md</code>, <code>AGENTS.md</code>, or <code>.cursorrules</code>?</strong></summary>
91
+
92
+ Those are useful entry points — until they become 3,000-line monoliths nobody reads. Rudder layers things: scoped specs, per-task PRDs, workflow gates, cross-platform adapters. <strong>One simple rule: don't cram everything into one file.</strong>
93
+
94
+ </details>
95
+
96
+ <details>
97
+ <summary><strong>Is Rudder only for Claude Code?</strong></summary>
98
+
99
+ Nope. Rudder is a project-layer thing. Works across 14 coding agents and IDEs. Use Gemini for frontend today, Claude Code for backend tomorrow, Codex for review the day after.
100
+
101
+ </details>
102
+
103
+ <details>
104
+ <summary><strong>Solo dev or team?</strong></summary>
105
+
106
+ Both. Solo devs get project memory and repeatable workflow. Teams get the bigger win: shared standards, clear task boundaries, reviewable context, and platform portability.
107
+
108
+ </details>
109
+
110
+ <details>
111
+ <summary><strong>Do I have to write every spec file by hand?</strong></summary>
112
+
113
+ Nope. Most teams let AI draft specs from existing code first, then tighten the important stuff by hand. Rudder works best when the high-signal rules are explicit and versioned — the rest AI can figure out.
114
+
115
+ </details>
116
+
117
+ <details>
118
+ <summary><strong>Will this cause merge conflicts in a team?</strong></summary>
119
+
120
+ Nah. Personal workspace journals are per-developer. Shared specs and tasks go through git like any other artifact — merge conflicts are just merge conflicts, nothing new.
121
+
122
+ </details>
123
+
124
+ ## A Note from the Author
125
+
126
+ **Why does the version start at 0.5?**
127
+
128
+ The version numbers aren't skipped — I iterated locally for many rounds before publishing. Rudder was born in May (the 5th month), so the major version is 0.5, with the first public release at 0.5.30.
129
+
130
+ Rudder draws from many open-source projects, and I grew up learning from the open-source community. But open-source covers a broad set of use cases — most of them aren't battle-tested in real production workflows. As a Java full-stack developer, I use Rudder daily myself and keep iterating on it. That makes it relatively more friendly to Java full-stack engineers — the Java spec templates are also being actively updated. That said, every other language works just as well — Rudder itself is completely platform-agnostic.
131
+
132
+ One person can only do so much, but every pit I fall into will be filled. Hope it helps you who are using AI to write code.
133
+
134
+ > 📖 Rudder's online documentation and user manual are being gradually improved. Stay tuned.
135
+
136
+ ## Acknowledgments
137
+
138
+ Rudder wouldn't exist without the open-source coding agent community. We studied how many projects solve the same problems — context injection, workflow gates, multi-platform support — and built the version we wished we had.
139
+
140
+ ## Star History
141
+
142
+ [![Star History Chart](https://api.star-history.com/svg?repos=MengDe1231/Rudder&type=Date)](https://star-history.com/#MengDe1231/Rudder&Date)
143
+
144
+ <p align="center">
145
+ <a href="https://github.com/MengDe1231/Rudder">GitHub</a> •
146
+ <a href="https://discord.com/invite/tWcCZ3aRHc">Discord</a> •
147
+ <a href="https://github.com/MengDe1231/Rudder/blob/main/LICENSE">AGPL-3.0 License</a>
148
+ </p>
package/bin/rudder.js CHANGED
File without changes
@@ -24,7 +24,7 @@
24
24
  "type": "safe-file-delete",
25
25
  "from": ".claude/commands/rudder/check-backend.md",
26
26
  "description": "Replaced by check.md",
27
- "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3"]
27
+ "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3", "8117a8fc9df4e392be8fe5e167c2ed3e3a70d32d2f69f726f0bdc4ee4a8581ca"]
28
28
  },
29
29
  {
30
30
  "type": "safe-file-delete",
@@ -48,7 +48,7 @@
48
48
  "type": "safe-file-delete",
49
49
  "from": ".cursor/commands/rudder-check-backend.md",
50
50
  "description": "Replaced by rudder-check.md",
51
- "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3"]
51
+ "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3", "8117a8fc9df4e392be8fe5e167c2ed3e3a70d32d2f69f726f0bdc4ee4a8581ca"]
52
52
  },
53
53
  {
54
54
  "type": "safe-file-delete",
@@ -72,7 +72,7 @@
72
72
  "type": "safe-file-delete",
73
73
  "from": ".iflow/commands/rudder/check-backend.md",
74
74
  "description": "Replaced by check.md",
75
- "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3"]
75
+ "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3", "8117a8fc9df4e392be8fe5e167c2ed3e3a70d32d2f69f726f0bdc4ee4a8581ca"]
76
76
  },
77
77
  {
78
78
  "type": "safe-file-delete",
@@ -96,7 +96,7 @@
96
96
  "type": "safe-file-delete",
97
97
  "from": ".opencode/commands/rudder/check-backend.md",
98
98
  "description": "Replaced by check.md",
99
- "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3"]
99
+ "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3", "8117a8fc9df4e392be8fe5e167c2ed3e3a70d32d2f69f726f0bdc4ee4a8581ca"]
100
100
  },
101
101
  {
102
102
  "type": "safe-file-delete",
@@ -120,7 +120,7 @@
120
120
  "type": "safe-file-delete",
121
121
  "from": ".kilocode/workflows/check-backend.md",
122
122
  "description": "Replaced by check.md",
123
- "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3"]
123
+ "allowed_hashes": ["4e81a28d681ea770f780df55a212fd504ce21ee49b44ba16023b74b5c243cef3", "8117a8fc9df4e392be8fe5e167c2ed3e3a70d32d2f69f726f0bdc4ee4a8581ca"]
124
124
  },
125
125
  {
126
126
  "type": "safe-file-delete",
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.14",
3
+ "description": "Patch: `task.py archive` auto-commit no longer leaks dirty changes from other task dirs into the archive commit, and source-side deletes now stage correctly (no more phantom-delete fixups).",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Bug Fixes:**\n- fix(scripts): `task.py archive` auto-commit is now scoped to just the archived task's source + destination paths (plus any child task dirs whose `task.json` was edited as part of the parent-to-children relationship update). Dirty changes in OTHER active task dirs no longer get bundled into the archive commit.\n- fix(scripts): after `shutil.move` of a tracked task dir, the source-side deletions are now explicitly staged via `git rm -r --cached --ignore-unmatch`, so the working tree stays clean against HEAD without needing a follow-up fixup commit.\n\n**Internal:**\n- `safe_archive_paths_to_add()` accepts optional `task_name` + `modified_children` parameters; backward-compatible when called with no args (legacy wide scope preserved).\n- New integration test `test/scripts/task-archive.integration.test.ts` covers scope-creep + phantom-delete regressions against the real Python script.",
7
+ "migrations": [],
8
+ "notes": "Run `trellis update` to pull in the fixed `.trellis/scripts/common/task_store.py` + `safe_commit.py`. No migration required - script signatures changed but file paths did not."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.15",
3
+ "description": "Patch: prevent Trellis template manifests from owning user runtime files, and force UTF-8 for Windows hook I/O.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Bug Fixes:**\n- fix(uninstall): `trellis init` now tracks platform/root template hashes from files actually written by Trellis instead of walking `.codex/`, `.claude/`, and other platform dirs that can contain user runtime data.\n- fix(uninstall): `trellis update` and `trellis uninstall` prune orphan `.trellis/.template-hashes.json` entries before planning, preserving user-owned files from manifests created by older versions.\n- fix(hooks): Windows hook templates force UTF-8 for stdin, stdout, and stderr so non-ASCII task names and prompt payloads do not fail under cp936/cp1252 code pages.",
7
+ "migrations": [],
8
+ "notes": "Run `trellis update` to pull in the manifest ownership fixes and updated hook templates. No migration required because file paths did not change."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.16",
3
+ "description": "Patch: align Cursor sessionStart hook output with Cursor's supported schema and remove the unsupported beforeSubmitPrompt injector.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Bug Fixes:**\n- fix(hooks): Cursor `sessionStart` hooks now emit top-level `additional_context`, matching Cursor's supported hook schema.\n- fix(hooks): Cursor templates no longer install the unsupported `beforeSubmitPrompt` workflow-state injector or `.cursor/hooks/inject-workflow-state.py`.",
7
+ "migrations": [],
8
+ "notes": "Run `trellis update` to refresh Cursor hook templates. No migration required because Trellis removes the unsupported Cursor workflow-state hook from generated templates."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.17",
3
+ "description": "Patch: bundle the Trellis spec bootstrap skill and update the marketplace/docs entry for project-specific spec generation.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Enhancements:**\n- feat(skills): `trellis-spec-bootstarp` is now a built-in bundled skill installed by `trellis init` and refreshed by `trellis update` for supported AI platforms.\n- feat(skills): the bundled skill helps AI bootstrap `.trellis/spec/` from the real repository with source-backed references for repository analysis, spec task planning, spec writing, and MCP setup.\n- docs(skills): replace the older marketplace-only `cc-codex-spec-bootstrap` docs entry with the built-in `trellis-spec-bootstarp` flow.",
7
+ "migrations": [],
8
+ "notes": "Run `trellis update` to install or refresh the bundled `trellis-spec-bootstarp` skill. No migration command is required."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.19",
3
+ "description": "Patch: stop writing the [features.multi_agent_v2] block to the generated Codex config.toml so Codex CLI 0.130 and the Codex desktop app can load the config.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Bug Fixes:**\n- fix(codex): `trellis init` / `trellis update` no longer write a `[features.multi_agent_v2]` block to `.codex/config.toml`. Codex CLI changed `features` deserialization between 0.130 and 0.131; the structured table form is only accepted by 0.131+. On 0.130 and earlier - including the Codex CLI bundled in the Codex desktop app - it failed with `data did not match any variant of untagged enum FeatureToml in features.multi_agent_v2`, aborting the entire config load and blocking Codex from starting. Codex's own default for multi_agent_v2 is used instead.",
7
+ "migrations": [],
8
+ "notes": "Patch on top of 0.5.18. Run `trellis update` to regenerate `.codex/config.toml` without the multi_agent_v2 block. Tune multi_agent_v2 in your user-level ~/.codex/config.toml if needed."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.20",
3
+ "description": "Historical manifest continuity backfill.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Maintenance:**\n- This version was published without a migration manifest. The shipped npm tarball contains no recoverable version-specific migration metadata.\n- This backfill preserves a continuous update chain without inventing migration actions.",
7
+ "migrations": [],
8
+ "notes": "No recoverable version-specific migration is available. Run `rudder update` to refresh current hash-tracked templates."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.21",
3
+ "description": "Historical manifest continuity backfill.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Maintenance:**\n- This version was published without a migration manifest. The shipped npm tarball contains no recoverable version-specific migration metadata.\n- This backfill preserves a continuous update chain without inventing migration actions.",
7
+ "migrations": [],
8
+ "notes": "No recoverable version-specific migration is available. Run `rudder update` to refresh current hash-tracked templates."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.22",
3
+ "description": "Historical manifest continuity backfill.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Maintenance:**\n- This version was published without a migration manifest. The shipped npm tarball contains no recoverable version-specific migration metadata.\n- This backfill preserves a continuous update chain without inventing migration actions.",
7
+ "migrations": [],
8
+ "notes": "No recoverable version-specific migration is available. Run `rudder update` to refresh current hash-tracked templates."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.23",
3
+ "description": "Historical manifest continuity backfill.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Maintenance:**\n- This version was published without a migration manifest. The shipped npm tarball contains no recoverable version-specific migration metadata.\n- This backfill preserves a continuous update chain without inventing migration actions.",
7
+ "migrations": [],
8
+ "notes": "No recoverable version-specific migration is available. Run `rudder update` to refresh current hash-tracked templates."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.5.30",
3
+ "description": "Historical manifest continuity backfill.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Maintenance:**\n- This version was published without a migration manifest. The shipped npm tarball contains no recoverable version-specific migration metadata.\n- This backfill preserves a continuous update chain without inventing migration actions.",
7
+ "migrations": [],
8
+ "notes": "No recoverable version-specific migration is available. Run `rudder update` to refresh current hash-tracked templates."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.6.1",
3
+ "description": "Historical manifest continuity backfill.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Maintenance:**\n- This version was published without a migration manifest. The shipped npm tarball contains no recoverable version-specific migration metadata.\n- This backfill preserves a continuous update chain without inventing migration actions.",
7
+ "migrations": [],
8
+ "notes": "No recoverable version-specific migration is available. Run `rudder update` to refresh current hash-tracked templates."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.6.11",
3
+ "description": "Historical manifest continuity backfill.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Maintenance:**\n- This version was published without a migration manifest. The shipped npm tarball contains no recoverable version-specific migration metadata.\n- This backfill preserves a continuous update chain without inventing migration actions.",
7
+ "migrations": [],
8
+ "notes": "No recoverable version-specific migration is available. Run `rudder update` to refresh current hash-tracked templates."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.6.20",
3
+ "description": "Historical manifest continuity backfill.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Maintenance:**\n- This version was published without a migration manifest. The shipped npm tarball contains no recoverable version-specific migration metadata.\n- This backfill preserves a continuous update chain without inventing migration actions.",
7
+ "migrations": [],
8
+ "notes": "No recoverable version-specific migration is available. Run `rudder update` to refresh current hash-tracked templates."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.6.21",
3
+ "description": "Patch: require a confirmed, internally consistent PRD before implementation and separate complete-diff review from post-implementation verification.",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Enhancements:**\n- feat(task): add `task.py confirm <task-dir>` and gate `task.py start` on a confirmed PRD hash, acceptance criteria, resolved open questions, conflict checks, and curated applicable context files.\n- feat(workflow): require the complete implementation batch before Check, then run Verify for lint, type-check, tests, build, and business acceptance commands; failures are fixed and re-verified without incremental per-file checks.\n- feat(config): document a commented `skip_rudder` project-policy placeholder without changing current Fast Path behavior.\n\n**Bug Fixes:**\n- fix(check): Claude and Codex check templates prefer project-declared build commands before generic fallback commands.\n- fix(codex): remove an incompatible project-level multi_agent_v2 configuration that can prevent older Codex clients from loading the repository config.\n\n**Maintenance:**\n- restore and backfill missing historical migration manifests so `rudder update` has a continuous published-version manifest chain.",
7
+ "migrations": [],
8
+ "notes": "Run `rudder update` to refresh hash-tracked workflow, task, check-agent, and configuration templates. No migration command is required."
9
+ }
@@ -0,0 +1,9 @@
1
+ {
2
+ "version": "0.6.22",
3
+ "description": "Route development work by task relevance and align inline readiness",
4
+ "breaking": false,
5
+ "recommendMigrate": false,
6
+ "changelog": "**Enhancements:**\n- feat(workflow): route direct requests, related work, and independent objectives by business goal and acceptance scope; reuse approval already given for agreed plans.\n\n**Bug Fixes:**\n- fix(tasks): share execution-mode readiness between task creation and startup. Inline execution ignores existing JSONL seeds, while sub-agent execution requires both curated context files.",
7
+ "migrations": [],
8
+ "notes": "No migration required."
9
+ }
@@ -1,30 +1,30 @@
1
- # Project-scoped Codex defaults for Rudder workflows.
2
- # Codex merges this layer after the user-level config when the project
3
- # is marked as a trusted project. To trust this project, add it under
4
- # `[projects]` in ~/.codex/config.toml, e.g.:
5
- #
6
- # [projects."/abs/path/to/this/repo"]
7
- # trust_level = "trusted"
8
- #
9
- # Without trust, the [features] block below is loaded but disabled.
10
-
11
- # Keep AGENTS.md as the primary project instruction file.
12
- project_doc_fallback_filenames = ["AGENTS.md"]
13
-
14
- # Codex hooks (`hooks.json` in this directory) only fire when the user
15
- # has enabled them in their USER-level config: `[features].hooks = true`
16
- # in ~/.codex/config.toml (Codex 0.129+; legacy name: `codex_hooks = true`,
17
- # still works but emits a deprecation warning on 0.129+). Project-level
18
- # config.toml cannot set feature flags; they must be user-level.
19
- # Codex 0.129+ additionally gates each installed hook behind a one-time
20
- # `/hooks` TUI review; until the user approves it, the hook stays inactive.
21
-
22
- # NOTE: Rudder intentionally does NOT write a [features.multi_agent_v2]
23
- # block here. Codex CLI changed `features` deserialization between 0.130
24
- # and 0.131: the structured table form (with max_concurrent_threads_per_session
25
- # / *_wait_timeout_ms) is only accepted by 0.131+. On 0.130 and earlier —
26
- # including the codex CLI bundled inside the Codex desktop app — it fails
27
- # with `data did not match any variant of untagged enum FeatureToml`, which
28
- # aborts the entire config load and blocks Codex from starting. Codex's own
29
- # default for multi_agent_v2 is used instead; tune it in your user-level
30
- # config if needed.
1
+ # Project-scoped Codex defaults for Rudder workflows.
2
+ # Codex merges this layer after the user-level config when the project
3
+ # is marked as a trusted project. To trust this project, add it under
4
+ # `[projects]` in ~/.codex/config.toml, e.g.:
5
+ #
6
+ # [projects."/abs/path/to/this/repo"]
7
+ # trust_level = "trusted"
8
+ #
9
+ # Without trust, the [features] block below is loaded but disabled.
10
+
11
+ # Keep AGENTS.md as the primary project instruction file.
12
+ project_doc_fallback_filenames = ["AGENTS.md"]
13
+
14
+ # Codex hooks (`hooks.json` in this directory) only fire when the user
15
+ # has enabled them in their USER-level config: `[features].hooks = true`
16
+ # in ~/.codex/config.toml (Codex 0.129+; legacy name: `codex_hooks = true`,
17
+ # still works but emits a deprecation warning on 0.129+). Project-level
18
+ # config.toml cannot set feature flags; they must be user-level.
19
+ # Codex 0.129+ additionally gates each installed hook behind a one-time
20
+ # `/hooks` TUI review; until the user approves it, the hook stays inactive.
21
+
22
+ # NOTE: Rudder intentionally does NOT write a [features.multi_agent_v2]
23
+ # block here. Codex CLI changed `features` deserialization between 0.130
24
+ # and 0.131: the structured table form (with max_concurrent_threads_per_session
25
+ # / *_wait_timeout_ms) is only accepted by 0.131+. On 0.130 and earlier —
26
+ # including the codex CLI bundled inside the Codex desktop app — it fails
27
+ # with `data did not match any variant of untagged enum FeatureToml`, which
28
+ # aborts the entire config load and blocks Codex from starting. Codex's own
29
+ # default for multi_agent_v2 is used instead; tune it in your user-level
30
+ # config if needed.
@@ -45,13 +45,14 @@ If the user wants only one platform to avoid sub-agents, first confirm whether t
45
45
 
46
46
  ## `/rudder:continue` Route Table
47
47
 
48
- `/rudder:continue` resumes a task by deciding which phase step to load next. The decision combines `task.json.status` with the presence of artifacts inside the task directory. The mapping is fixed in the command itself; forks that add custom statuses must extend both the workflow.md tag block and this table.
48
+ `/rudder:continue` first checks request intent and task relevance by business objective and acceptance scope. Direct questions/inspection/commit-wording requests do not advance the task; independent goals follow direct-low-risk/new-task routing. For related work, the decision combines `task.json.status`, PRD completeness and approval, and the invoking platform's execution mode. Forks that add custom statuses must extend both the workflow.md tag block and this table.
49
49
 
50
50
  | `status` | Artifact state | Resume at |
51
51
  | --- | --- | --- |
52
- | `planning` | `prd.md` missing | Phase 1.1 (load `rudder-brainstorm`) |
53
- | `planning` | `prd.md` exists, `implement.jsonl` only has the seed `_example` row | Phase 1.3 (curate JSONL context) |
54
- | `planning` | `prd.md` exists, `implement.jsonl` curated | Phase 1.4 (run `task.py start`) |
52
+ | `planning` | PRD missing/incomplete, unresolved decisions, or no approval | Phase 1.1 (resolve only outstanding decisions; reuse prior approval of the agreed plan) |
53
+ | `planning` | PRD approved, confirmation missing/stale | Record approval with `task.py confirm`; do not ask again unless requirements materially changed |
54
+ | `planning` | Confirmed PRD; sub-agent mode; either JSONL missing/invalid/seed-only | Phase 1.3 (curate both context files) |
55
+ | `planning` | Confirmed PRD; inline mode OR both required context files valid/curated | Phase 1.4 (`task.py start <task> --platform <platform>`; inline ignores old seeds) |
55
56
  | `in_progress` | no implementation in conversation history | Phase 2.1 (`rudder-implement`) |
56
57
  | `in_progress` | implementation done, no `rudder-check` run | Phase 2.2 (`rudder-check`) |
57
58
  | `in_progress` | check passed | Phase 3.1 (verify quality + spec update) |
@@ -44,6 +44,8 @@ The Rudder task system is stored entirely under `.rudder/tasks/` in the user pro
44
44
 
45
45
  The AI should not treat phase numbers as task status. Task progress is mainly determined by `status`, `prd.md`, whether JSONL context is configured, and the phase descriptions in `workflow.md`.
46
46
 
47
+ Task ownership follows business objective and acceptance scope. An active pointer alone does not make a new request part of that task. Reuse related unfinished work, including design-to-development; create separate tracked tasks for independent objectives. Direct answers, scheduler administration, commit-message drafting, and clear/local/low-risk independent edits follow direct routing in `workflow.md`.
48
+
47
49
  ## Active Task
48
50
 
49
51
  The user sees a "current task," but Rudder stores active task state per session.
@@ -69,6 +71,8 @@ Format:
69
71
 
70
72
  Rules:
71
73
 
74
+ - JSONL is required only for the invoking platform's sub-agent execution mode. `task.py create` and `start` share `common.workflow_phase.requires_task_context`; explicit `--platform` takes precedence over `RUDDER_PLATFORM`, then conservative configured-platform detection. Codex uses `codex.dispatch_mode` (default inline).
75
+ - Inline startup ignores existing seed files; sub-agent startup requires both valid curated files even if neither exists. PRD completeness and confirmation/hash checks apply to both modes.
72
76
  - Include spec and research files.
73
77
  - Do not include code files that are about to be modified.
74
78
  - Do not treat temporary conclusions in chat as the only context.
@@ -77,8 +81,9 @@ Rules:
77
81
  ## Common Commands
78
82
 
79
83
  ```bash
80
- python3 ./.rudder/scripts/task.py create "<title>" --slug <slug>
81
- python3 ./.rudder/scripts/task.py start <task>
84
+ python3 ./.rudder/scripts/task.py create "<title>" --slug <slug> --platform <platform>
85
+ python3 ./.rudder/scripts/task.py confirm <task>
86
+ python3 ./.rudder/scripts/task.py start <task> --platform <platform>
82
87
  python3 ./.rudder/scripts/task.py current --source
83
88
  python3 ./.rudder/scripts/task.py add-context <task> implement <file> <reason>
84
89
  python3 ./.rudder/scripts/task.py validate <task>