@openrig/cli 0.1.2 → 0.1.4

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 (104) hide show
  1. package/daemon/assets/guidance/openrig-start.md +16 -1
  2. package/daemon/dist/adapters/claude-code-adapter.d.ts +12 -0
  3. package/daemon/dist/adapters/claude-code-adapter.d.ts.map +1 -1
  4. package/daemon/dist/adapters/claude-code-adapter.js +92 -3
  5. package/daemon/dist/adapters/claude-code-adapter.js.map +1 -1
  6. package/daemon/dist/adapters/codex-runtime-adapter.d.ts +5 -0
  7. package/daemon/dist/adapters/codex-runtime-adapter.d.ts.map +1 -1
  8. package/daemon/dist/adapters/codex-runtime-adapter.js +82 -2
  9. package/daemon/dist/adapters/codex-runtime-adapter.js.map +1 -1
  10. package/daemon/dist/domain/agent-manifest.d.ts.map +1 -1
  11. package/daemon/dist/domain/agent-manifest.js +2 -1
  12. package/daemon/dist/domain/agent-manifest.js.map +1 -1
  13. package/daemon/dist/domain/native-resume-probe.d.ts.map +1 -1
  14. package/daemon/dist/domain/native-resume-probe.js +24 -1
  15. package/daemon/dist/domain/native-resume-probe.js.map +1 -1
  16. package/daemon/dist/domain/profile-resolver.js +1 -1
  17. package/daemon/dist/domain/profile-resolver.js.map +1 -1
  18. package/daemon/dist/domain/runtime-adapter.d.ts +1 -0
  19. package/daemon/dist/domain/runtime-adapter.d.ts.map +1 -1
  20. package/daemon/dist/domain/runtime-adapter.js.map +1 -1
  21. package/daemon/dist/domain/startup-orchestrator.d.ts.map +1 -1
  22. package/daemon/dist/domain/startup-orchestrator.js +10 -1
  23. package/daemon/dist/domain/startup-orchestrator.js.map +1 -1
  24. package/daemon/specs/agents/analyst/agent.yaml +10 -1
  25. package/daemon/specs/agents/design/agent.yaml +10 -1
  26. package/daemon/specs/agents/design/guidance/role.md +13 -0
  27. package/daemon/specs/agents/impl/agent.yaml +10 -1
  28. package/daemon/specs/agents/impl/guidance/role.md +20 -0
  29. package/daemon/specs/agents/lead/agent.yaml +10 -1
  30. package/daemon/specs/agents/lead/guidance/role.md +18 -0
  31. package/daemon/specs/agents/qa/agent.yaml +10 -1
  32. package/daemon/specs/agents/qa/guidance/role.md +52 -0
  33. package/daemon/specs/agents/reviewer/agent.yaml +10 -1
  34. package/daemon/specs/agents/reviewer/guidance/role.md +13 -0
  35. package/daemon/specs/agents/shared/agent.yaml +38 -0
  36. package/daemon/specs/agents/shared/skills/agent-browser/LOCAL-INSIGHTS.md +189 -0
  37. package/daemon/specs/agents/shared/skills/agent-browser/SKILL.md +417 -0
  38. package/daemon/specs/agents/shared/skills/brainstorming/SKILL.md +96 -0
  39. package/daemon/specs/agents/shared/skills/containerized-e2e/SKILL.md +256 -0
  40. package/daemon/specs/agents/shared/skills/containerized-e2e/scripts/Dockerfile +39 -0
  41. package/daemon/specs/agents/shared/skills/containerized-e2e/scripts/build-e2e-image.sh +37 -0
  42. package/daemon/specs/agents/shared/skills/containerized-e2e/templates/control-plane-test.yaml +40 -0
  43. package/daemon/specs/agents/shared/skills/containerized-e2e/templates/e2e-report-template.md +94 -0
  44. package/daemon/specs/agents/shared/skills/containerized-e2e/templates/expansion-collision-fragment.yaml +13 -0
  45. package/daemon/specs/agents/shared/skills/containerized-e2e/templates/expansion-pod-fragment.yaml +14 -0
  46. package/daemon/specs/agents/shared/skills/development-team/SKILL.md +149 -0
  47. package/daemon/specs/agents/shared/skills/dogfood/SKILL.md +220 -0
  48. package/daemon/specs/agents/shared/skills/dogfood/references/issue-taxonomy.md +109 -0
  49. package/daemon/specs/agents/shared/skills/dogfood/templates/dogfood-report-template.md +53 -0
  50. package/daemon/specs/agents/shared/skills/executing-plans/SKILL.md +84 -0
  51. package/daemon/specs/agents/shared/skills/frontend-design/LICENSE.txt +177 -0
  52. package/daemon/specs/agents/shared/skills/frontend-design/SKILL.md +42 -0
  53. package/daemon/specs/agents/shared/skills/openrig-user/SKILL.md +468 -0
  54. package/daemon/specs/agents/shared/skills/orchestration-team/SKILL.md +234 -0
  55. package/daemon/specs/agents/shared/skills/review-team/SKILL.md +210 -0
  56. package/daemon/specs/agents/shared/skills/systematic-debugging/CREATION-LOG.md +119 -0
  57. package/daemon/specs/agents/shared/skills/systematic-debugging/SKILL.md +296 -0
  58. package/daemon/specs/agents/shared/skills/systematic-debugging/condition-based-waiting-example.ts +158 -0
  59. package/daemon/specs/agents/shared/skills/systematic-debugging/condition-based-waiting.md +115 -0
  60. package/daemon/specs/agents/shared/skills/systematic-debugging/defense-in-depth.md +122 -0
  61. package/daemon/specs/agents/shared/skills/systematic-debugging/find-polluter.sh +63 -0
  62. package/daemon/specs/agents/shared/skills/systematic-debugging/root-cause-tracing.md +169 -0
  63. package/daemon/specs/agents/shared/skills/systematic-debugging/test-academic.md +14 -0
  64. package/daemon/specs/agents/shared/skills/systematic-debugging/test-pressure-1.md +58 -0
  65. package/daemon/specs/agents/shared/skills/systematic-debugging/test-pressure-2.md +68 -0
  66. package/daemon/specs/agents/shared/skills/systematic-debugging/test-pressure-3.md +69 -0
  67. package/daemon/specs/agents/shared/skills/test-driven-development/SKILL.md +371 -0
  68. package/daemon/specs/agents/shared/skills/test-driven-development/testing-anti-patterns.md +299 -0
  69. package/daemon/specs/agents/shared/skills/using-superpowers/SKILL.md +95 -0
  70. package/daemon/specs/agents/shared/skills/verification-before-completion/SKILL.md +139 -0
  71. package/daemon/specs/agents/shared/skills/writing-plans/SKILL.md +116 -0
  72. package/daemon/specs/agents/synthesizer/agent.yaml +10 -1
  73. package/daemon/specs/demo.CULTURE.md +92 -0
  74. package/daemon/specs/demo.yaml +91 -0
  75. package/daemon/specs/implementation-pair.yaml +3 -3
  76. package/daemon/specs/product-team.CULTURE.md +137 -0
  77. package/daemon/specs/product-team.yaml +5 -4
  78. package/dist/client.d.ts +8 -1
  79. package/dist/client.d.ts.map +1 -1
  80. package/dist/client.js +15 -6
  81. package/dist/client.js.map +1 -1
  82. package/dist/commands/daemon.d.ts.map +1 -1
  83. package/dist/commands/daemon.js +5 -1
  84. package/dist/commands/daemon.js.map +1 -1
  85. package/dist/commands/up.js +2 -2
  86. package/dist/commands/up.js.map +1 -1
  87. package/dist/daemon-lifecycle.d.ts.map +1 -1
  88. package/dist/daemon-lifecycle.js +54 -7
  89. package/dist/daemon-lifecycle.js.map +1 -1
  90. package/dist/fetch-with-timeout.d.ts +9 -0
  91. package/dist/fetch-with-timeout.d.ts.map +1 -0
  92. package/dist/fetch-with-timeout.js +41 -0
  93. package/dist/fetch-with-timeout.js.map +1 -0
  94. package/dist/index.d.ts.map +1 -1
  95. package/dist/index.js +2 -1
  96. package/dist/index.js.map +1 -1
  97. package/dist/mcp-server.d.ts.map +1 -1
  98. package/dist/mcp-server.js +2 -1
  99. package/dist/mcp-server.js.map +1 -1
  100. package/dist/version.d.ts +2 -0
  101. package/dist/version.d.ts.map +1 -0
  102. package/dist/version.js +8 -0
  103. package/dist/version.js.map +1 -0
  104. package/package.json +1 -1
@@ -0,0 +1,177 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
@@ -0,0 +1,42 @@
1
+ ---
2
+ name: frontend-design
3
+ description: Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
4
+ license: Complete terms in LICENSE.txt
5
+ ---
6
+
7
+ This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.
8
+
9
+ The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints.
10
+
11
+ ## Design Thinking
12
+
13
+ Before coding, understand the context and commit to a BOLD aesthetic direction:
14
+ - **Purpose**: What problem does this interface solve? Who uses it?
15
+ - **Tone**: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction.
16
+ - **Constraints**: Technical requirements (framework, performance, accessibility).
17
+ - **Differentiation**: What makes this UNFORGETTABLE? What's the one thing someone will remember?
18
+
19
+ **CRITICAL**: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.
20
+
21
+ Then implement working code (HTML/CSS/JS, React, Vue, etc.) that is:
22
+ - Production-grade and functional
23
+ - Visually striking and memorable
24
+ - Cohesive with a clear aesthetic point-of-view
25
+ - Meticulously refined in every detail
26
+
27
+ ## Frontend Aesthetics Guidelines
28
+
29
+ Focus on:
30
+ - **Typography**: Choose fonts that are beautiful, unique, and interesting. Avoid generic fonts like Arial and Inter; opt instead for distinctive choices that elevate the frontend's aesthetics; unexpected, characterful font choices. Pair a distinctive display font with a refined body font.
31
+ - **Color & Theme**: Commit to a cohesive aesthetic. Use CSS variables for consistency. Dominant colors with sharp accents outperform timid, evenly-distributed palettes.
32
+ - **Motion**: Use animations for effects and micro-interactions. Prioritize CSS-only solutions for HTML. Use Motion library for React when available. Focus on high-impact moments: one well-orchestrated page load with staggered reveals (animation-delay) creates more delight than scattered micro-interactions. Use scroll-triggering and hover states that surprise.
33
+ - **Spatial Composition**: Unexpected layouts. Asymmetry. Overlap. Diagonal flow. Grid-breaking elements. Generous negative space OR controlled density.
34
+ - **Backgrounds & Visual Details**: Create atmosphere and depth rather than defaulting to solid colors. Add contextual effects and textures that match the overall aesthetic. Apply creative forms like gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, decorative borders, custom cursors, and grain overlays.
35
+
36
+ NEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character.
37
+
38
+ Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations.
39
+
40
+ **IMPORTANT**: Match implementation complexity to the aesthetic vision. Maximalist designs need elaborate code with extensive animations and effects. Minimalist or refined designs need restraint, precision, and careful attention to spacing, typography, and subtle details. Elegance comes from executing the vision well.
41
+
42
+ Remember: Claude is capable of extraordinary creative work. Don't hold back, show what can truly be created when thinking outside the box and committing fully to a distinctive vision.
@@ -0,0 +1,468 @@
1
+ ---
2
+ name: openrig-user
3
+ description: Use when operating OpenRig with the `rig` CLI and you need the shipped command surface for identity, inventory, communication, lifecycle, specs, recovery, or agent-facing JSON output.
4
+ ---
5
+
6
+ # OpenRig User
7
+
8
+ This is an as-built guide to the shipped `rig` CLI.
9
+ Use current code and `rig ... --help` as ground truth if anything here ever conflicts with older planning docs.
10
+
11
+ ## Core Loop
12
+
13
+ Most work in OpenRig reduces to this loop:
14
+ - recover identity: `rig whoami --json`
15
+ - inspect inventory: `rig ps --nodes --json`
16
+ - read context: `rig transcript ...`, `rig ask ...`, `rig chatroom history ...`
17
+ - act: `rig send`, `rig capture`, `rig broadcast`, lifecycle commands
18
+
19
+ ## Identity and Recovery
20
+
21
+ Start here after launch, compaction, or confusion:
22
+
23
+ ```bash
24
+ rig whoami --json
25
+ ```
26
+
27
+ What it gives you today:
28
+ - identity: rig, logical ID, pod/member, session name, runtime
29
+ - peers and directional edges
30
+ - transcript info
31
+ - `contextUsage` when available
32
+
33
+ Flags:
34
+ ```bash
35
+ rig whoami --session <name>
36
+ rig whoami --node-id <id>
37
+ ```
38
+
39
+ If the daemon is unreachable but identity can still be inferred, `--json` may return a partial result instead of crashing.
40
+
41
+ ## Inventory and Monitoring
42
+
43
+ ```bash
44
+ rig ps
45
+ rig ps --json
46
+ rig ps --nodes
47
+ rig ps --nodes --json
48
+ ```
49
+
50
+ Use `rig ps --nodes --json` for the current node inventory across rigs. It is the best machine-readable operator surface for:
51
+ - session name
52
+ - runtime
53
+ - session/startup status
54
+ - restore outcome
55
+ - attach/resume commands
56
+ - latest error
57
+
58
+ Other health surfaces:
59
+
60
+ ```bash
61
+ rig status
62
+ rig daemon status
63
+ rig config
64
+ rig preflight
65
+ rig doctor
66
+ ```
67
+
68
+ ## Transcript and Communication
69
+
70
+ ### Transcript access
71
+
72
+ ```bash
73
+ rig transcript <session> --tail 100
74
+ rig transcript <session> --grep "pattern"
75
+ rig transcript <session> --json
76
+ ```
77
+
78
+ ### Send to one session
79
+
80
+ ```bash
81
+ rig send <session> "message"
82
+ rig send <session> "message" --verify
83
+ rig send <session> "message" --force
84
+ rig send <session> "message" --json
85
+ ```
86
+
87
+ Use `--verify` when you want delivery evidence. Use `--force` only when you intentionally want to bypass activity-risk checks.
88
+
89
+ ### Capture terminal output
90
+
91
+ ```bash
92
+ rig capture <session>
93
+ rig capture <session> --lines 50
94
+ rig capture --rig <name>
95
+ rig capture --pod <name> --rig <name>
96
+ rig capture --rig <name> --json
97
+ ```
98
+
99
+ ### Broadcast
100
+
101
+ ```bash
102
+ rig broadcast --rig <name> "message"
103
+ rig broadcast --pod <name> "message"
104
+ rig broadcast "message"
105
+ rig broadcast --rig <name> "message" --json
106
+ ```
107
+
108
+ Without `--rig` or `--pod`, broadcast targets all running sessions.
109
+
110
+ ### Chatroom
111
+
112
+ ```bash
113
+ rig chatroom send <rig> <message> [--sender <name>]
114
+ rig chatroom history <rig> [--topic <name>] [--after <id>] [--since <ts>] [--sender <name>] [--limit <n>] [--json]
115
+ rig chatroom wait <rig> [--after <id>] [--topic <name>] [--sender <name>] [--timeout <seconds>] [--json]
116
+ rig chatroom clear <rig>
117
+ rig chatroom topic <rig> <topic-name> [--body <text>] [--sender <name>]
118
+ rig chatroom watch <rig> [--tmux]
119
+ ```
120
+
121
+ **Key commands:**
122
+ - `send` — post a message
123
+ - `history` — retrieve with composable filters (sender, since, after, topic)
124
+ - `wait` — block until new matching messages arrive (polls history, times out honestly)
125
+ - `clear` — delete all messages for the rig (destructive, rig-scoped)
126
+ - `topic` — set a topic marker
127
+ - `watch` — SSE or tmux-based live stream
128
+
129
+ **Roundtable protocol:**
130
+ 1. Inspect old room: `rig chatroom history my-rig --limit 5`
131
+ 2. Save if needed: `rig chatroom history my-rig --json > /tmp/old-room.json`
132
+ 3. Clear if needed: `rig chatroom clear my-rig`
133
+ 4. Set topic: `rig chatroom topic my-rig "ROUND START"`
134
+ 5. Post: `rig chatroom send my-rig "position..." --sender <session>`
135
+ 6. Monitor: `rig chatroom wait my-rig --timeout 120`
136
+ 7. Close: `rig chatroom topic my-rig "ROUND CLOSED"`
137
+
138
+ See `docs/planning/roadmaps/chatroom-roundtable-protocol.md` for the full protocol.
139
+
140
+ ### `rig ask`
141
+
142
+ ```bash
143
+ rig ask <rig> "question"
144
+ rig ask <rig> "question" --json
145
+ ```
146
+
147
+ Current shipped behavior:
148
+ - queries the daemon for evidence
149
+ - returns rig summary
150
+ - returns transcript excerpts
151
+ - may return chat excerpts
152
+ - returns insufficiency state and optional guidance
153
+
154
+ This is an evidence/context command. It is not a hidden second-LLM call.
155
+
156
+ ## Lifecycle
157
+
158
+ ### Bring a rig up
159
+
160
+ ```bash
161
+ rig up <source>
162
+ rig up <source> --plan
163
+ rig up <source> --yes
164
+ rig up <source> --json
165
+ ```
166
+
167
+ `<source>` can be:
168
+ - a rig spec path
169
+ - a `.rigbundle` path
170
+ - a bare name
171
+
172
+ Bare names are special:
173
+ - if they match a library spec, `rig up` launches from the spec library
174
+ - if they do not match a library spec, `rig up` treats the name as an existing-rig restore/power-on target
175
+ - if both exist, `rig up` fails loudly on ambiguity
176
+
177
+ Current behavior notes:
178
+ - `--target <root>` is only for `.rigbundle` / package installation. It does not change agent cwd.
179
+ - `local:` `agent_ref` values resolve relative to the rig spec directory, not your shell cwd.
180
+ - if you copy a built-in spec elsewhere, keep its `agents/` tree beside the YAML or rewrite those refs to `path:/absolute/path`
181
+ - there is no shipped `rig up --cwd` override yet
182
+
183
+ Legacy/spec-specific surfaces still ship too:
184
+
185
+ ```bash
186
+ rig bootstrap <spec> [--plan] [--yes] [--json]
187
+ rig requirements <spec> [--json]
188
+ ```
189
+
190
+ ### Tear a rig down
191
+
192
+ ```bash
193
+ rig down <rigId>
194
+ rig down <rigId> --snapshot
195
+ rig down <rigId> --delete
196
+ rig down <rigId> --force
197
+ rig down <rigId> --json
198
+ ```
199
+
200
+ If `--snapshot` succeeds, human output includes the restore hint.
201
+
202
+ ### Release management without killing live claimed sessions
203
+
204
+ ```bash
205
+ rig release <rigId>
206
+ rig release <rigId> --delete
207
+ rig release <rigId> --json
208
+ ```
209
+
210
+ Use `rig release` for adopted/claimed-session rigs when you want OpenRig to stop managing the rig but leave the tmux sessions alive.
211
+ This is the safe recovery/reset surface for the "sessions still exist, management is broken or stale" case.
212
+ If the rig contains OpenRig-launched nodes, `rig release` refuses loudly instead of pretending the mixed rig is safe to detach.
213
+
214
+ ### Snapshots and restore
215
+
216
+ ```bash
217
+ rig snapshot <rigId>
218
+ rig snapshot list <rigId>
219
+ rig restore <snapshotId> --rig <rigId>
220
+ ```
221
+
222
+ `rig restore` requires `--rig <rigId>`.
223
+
224
+ Claude Code autonomy note:
225
+ - unattended `rig whoami` on boot may require the local permission allow list to include `Bash(rig:*)`
226
+
227
+ ### Import/export and bundles
228
+
229
+ ```bash
230
+ rig export <rigId> -o rig.yaml
231
+ rig import <path> [--instantiate] [--materialize-only] [--preflight] [--target-rig <rigId>] [--rig-root <root>]
232
+ rig bundle create <spec> -o out.rigbundle
233
+ rig bundle inspect <bundle>
234
+ rig bundle install <bundle> [--plan] [--yes] [--target <root>] [--json]
235
+ ```
236
+
237
+ ### Legacy package surface
238
+
239
+ This still ships, but is explicitly marked legacy:
240
+
241
+ ```bash
242
+ rig package validate <path>
243
+ rig package plan <path> [--target <dir>] [--runtime <runtime>] [--role <name>]
244
+ rig package install <path> [--target <dir>] [--runtime <runtime>] [--role <name>] [--allow-merge]
245
+ rig package list
246
+ rig package rollback <installId>
247
+ ```
248
+
249
+ ## Discovery and Topology Mutation
250
+
251
+ ### Discover unmanaged tmux sessions
252
+
253
+ ```bash
254
+ rig discover
255
+ rig discover --json
256
+ rig discover --draft
257
+ ```
258
+
259
+ ### Bind a discovered session
260
+
261
+ ```bash
262
+ rig bind <discoveredId> --rig <rigId> --node <logicalId>
263
+ rig bind <discoveredId> --rig <rigId> --pod <namespace> --member <name>
264
+ ```
265
+
266
+ There is no shipped top-level `rig claim` command.
267
+ The current adoption surface is `discover`, `bind`, `adopt`, and `unclaim`.
268
+
269
+ ### Self-attach the current shell or agent
270
+
271
+ ```bash
272
+ rig attach --self --rig <rigId> --node <logicalId>
273
+ rig attach --self --rig <rigId> --node <logicalId> --print-env
274
+ rig attach --self --rig <rigId> --pod <namespace> --member <name> --runtime <runtime>
275
+ ```
276
+
277
+ Use `rig attach --self` when the current agent should attach itself directly instead of going through `discover` + `bind`.
278
+
279
+ Current proven behavior:
280
+ - inside `tmux`: attaches as a normal tmux-backed node, preserving inbound `rig send` / `rig capture`
281
+ - outside `tmux`: attaches as `external_cli`
282
+ - `--print-env` prints the `OPENRIG_NODE_ID` and `OPENRIG_SESSION_NAME` exports for the current shell
283
+
284
+ Recommended flow:
285
+
286
+ ```bash
287
+ rig attach --self --rig <rigId> --node <logicalId> --print-env > /tmp/openrig-self-attach.env
288
+ . /tmp/openrig-self-attach.env
289
+ rig whoami --json
290
+ ```
291
+
292
+ Notes:
293
+ - for tmux-backed self-attach, `rig whoami --json` is the right verification
294
+ - for raw/external self-attach, `rig ps --nodes --json` is currently the more reliable verification surface
295
+ - if the current shell is outside tmux, pass `--display-name <name>` when you want a stable human session label recorded
296
+
297
+ ### Adopt a topology and bind live sessions
298
+
299
+ ```bash
300
+ rig adopt <path> --bind <logicalId=tmuxSessionOrDiscoveryId>
301
+ rig adopt <path> --bind <logicalId=...> --bind <logicalId=...> --json
302
+ rig adopt <path> --bindings-file <bindings.yaml>
303
+ rig adopt <path> --bind <logicalId=...> --target-rig <rigId> --rig-root <root>
304
+ ```
305
+
306
+ Use `rig adopt` when the sessions already exist and you want OpenRig to start managing them.
307
+
308
+ A bindings file is the durable map from authored logical IDs to live sessions. Shape:
309
+
310
+ ```yaml
311
+ bindings:
312
+ dev1.impl2: dev1-impl2@rigged-buildout
313
+ dev1.qa: dev1-qa@rigged-buildout
314
+ ```
315
+
316
+ Spec + bindings is the proven recovery pair for adopted rigs.
317
+ Spec gives OpenRig the intended topology. Bindings tells OpenRig which discovered live session belongs in each logical node.
318
+
319
+ ### Proven adopted-rig recovery workflow
320
+
321
+ This workflow is proven for the case where the external tmux sessions are still alive:
322
+
323
+ ```bash
324
+ rig release <rigId> --delete
325
+ rig discover --json
326
+ rig adopt <spec.yaml> --bindings-file <bindings.yaml>
327
+ ```
328
+
329
+ What this does:
330
+ - removes OpenRig management without killing the sessions
331
+ - re-discovers those same sessions as unmanaged
332
+ - re-attaches them to the topology defined by the spec + bindings
333
+
334
+ Important limits:
335
+ - this is for `sessions still alive`
336
+ - spec alone is not enough for adopted rigs; you also need bindings
337
+ - this does not yet mean OpenRig can recreate dead external sessions from nothing
338
+
339
+ ### Add unmanaged pods into an existing rig
340
+
341
+ This is the proven workflow when a rig is already managed, but a new pod was created outside OpenRig and you want to add it later:
342
+
343
+ ```bash
344
+ rig adopt <pod-fragment.yaml> --bindings-file <pod.bindings.yaml> --target-rig <rigId>
345
+ ```
346
+
347
+ Use this when:
348
+ - the target rig already exists
349
+ - the new sessions are live and visible in `rig discover --json`
350
+ - you want additive topology growth, not a full rebuild
351
+
352
+ What to prepare:
353
+ - a pod fragment spec with only the new pod
354
+ - a bindings file mapping the new logical IDs to the live session names
355
+
356
+ Verification loop:
357
+
358
+ ```bash
359
+ rig discover --json
360
+ rig adopt <fragment.yaml> --bindings-file <bindings.yaml> --target-rig <rigId>
361
+ rig ps --nodes --json
362
+ rig export <rigId> -o rig.yaml
363
+ ```
364
+
365
+ Success looks like:
366
+ - the new sessions stop appearing in `rig discover`
367
+ - the new logical IDs appear in `rig ps --nodes --json`
368
+ - `rig export` includes the new pod
369
+
370
+ ### Mixed-origin rigs are allowed
371
+
372
+ One rig can contain both:
373
+ - adopted nodes bound from already-running sessions
374
+ - OpenRig-launched nodes created later with `rig expand` / `rig launch`
375
+
376
+ Current safety rule:
377
+ - `rig release` is for claimed/adopted-only rigs
378
+ - if a rig contains launched nodes, `rig release` fails with `contains_launched_nodes`
379
+
380
+ ### Manager-assisted recovery
381
+
382
+ The proven operator pattern is:
383
+ - keep one OpenRig manager session outside the rig it manages
384
+ - address the target by rig name, not cached rig ID
385
+ - resolve the current owner from fresh `rig ps --nodes --json`
386
+ - send the manager the spec path, bindings path, and verification steps with `rig send`
387
+
388
+ This lets ordinary agents ask the manager for OpenRig help instead of every agent needing to be an OpenRig expert.
389
+
390
+ ### Add/remove running topology parts
391
+
392
+ ```bash
393
+ rig expand <rig-id> <pod-fragment-path> [--rig-root <path>] [--json]
394
+ rig launch <rigId> <nodeRef> [--json]
395
+ rig remove <rigId> <nodeRef> [--json]
396
+ rig shrink <rigId> <podRef> [--json]
397
+ rig unclaim <sessionRef> [--json]
398
+ ```
399
+
400
+ ## Specs and Validation
401
+
402
+ ### Validate specs
403
+
404
+ ```bash
405
+ rig spec validate <path> [--json]
406
+ rig spec preflight <path> [--rig-root <root>] [--json]
407
+ rig agent validate <path> [--json]
408
+ ```
409
+
410
+ ### Spec library
411
+
412
+ ```bash
413
+ rig specs ls [--kind <kind>] [--json]
414
+ rig specs show <name-or-id> [--json]
415
+ rig specs preview <name-or-id> [--json]
416
+ rig specs add <path> [--json]
417
+ rig specs sync [--json]
418
+ rig specs remove <name-or-id> [--json]
419
+ rig specs rename <name-or-id> <new-name> [--json]
420
+ ```
421
+
422
+ ## MCP
423
+
424
+ ```bash
425
+ rig mcp serve [--port <port>]
426
+ ```
427
+
428
+ Current shipped MCP tools:
429
+ - `rig_up`
430
+ - `rig_down`
431
+ - `rig_ps`
432
+ - `rig_status`
433
+ - `rig_snapshot_create`
434
+ - `rig_snapshot_list`
435
+ - `rig_restore`
436
+ - `rig_discover`
437
+ - `rig_bind`
438
+ - `rig_bundle_inspect`
439
+ - `rig_agent_validate`
440
+ - `rig_rig_validate`
441
+ - `rig_rig_nodes`
442
+ - `rig_send`
443
+ - `rig_capture`
444
+ - `rig_chatroom_send`
445
+ - `rig_chatroom_watch`
446
+
447
+ ## JSON and Error Posture
448
+
449
+ Design assumptions that hold in the shipped CLI:
450
+ - many operator commands support `--json`
451
+ - error messages are intended to say what happened, why it matters, and what to do next
452
+ - daemon-backed commands fail loudly when the daemon is stopped or unhealthy
453
+ - restore failure is not something you should silently reinterpret as success
454
+
455
+ ## After-Compaction Recovery Checklist
456
+
457
+ 1. `rig whoami --json`
458
+ 2. `rig transcript <your-session> --tail 100`
459
+ 3. `rig ps --nodes --json`
460
+ 4. `rig chatroom history <rig> --limit 50`
461
+
462
+ ## Commands That Do Not Exist
463
+
464
+ Do not assume these exist unless the shipped help starts listing them:
465
+ - `rig claim`
466
+ - `rig env`
467
+ - `rig blame`
468
+ - `rig replay`