ultra-builder-pro-cli 5.0.1 → 6.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (159) hide show
  1. package/CHANGELOG.md +103 -3
  2. package/README.md +67 -478
  3. package/README.zh-CN.md +49 -422
  4. package/adapters/_shared/frontmatter.cjs +1 -18
  5. package/adapters/_shared/plugin-core.cjs +17 -83
  6. package/adapters/_shared/runtime-assets.cjs +6 -120
  7. package/adapters/claude.js +8 -24
  8. package/adapters/codex.js +13 -32
  9. package/bin/install.js +35 -57
  10. package/docs/PLUGIN-ISOLATION-CONTRACT.md +13 -101
  11. package/docs/examples/drive/claude-reviewer.sh +53 -0
  12. package/docs/examples/drive/claude-writer.sh +43 -0
  13. package/engine/FORMATS.md +1051 -0
  14. package/engine/checks.cjs +139 -0
  15. package/engine/cli.cjs +148 -0
  16. package/engine/completion.cjs +48 -0
  17. package/engine/context.cjs +94 -0
  18. package/engine/drive.cjs +220 -0
  19. package/engine/expect-worker.cjs +5 -0
  20. package/engine/expect.cjs +33 -0
  21. package/engine/formats.cjs +189 -0
  22. package/engine/git-state.cjs +112 -0
  23. package/engine/ledger.cjs +205 -0
  24. package/engine/loading.cjs +28 -0
  25. package/engine/merge.cjs +273 -0
  26. package/engine/milestone.cjs +89 -0
  27. package/engine/plan.cjs +232 -0
  28. package/engine/project.cjs +5 -0
  29. package/engine/signals.cjs +3 -0
  30. package/engine/states.cjs +175 -0
  31. package/hooks/session-start.cjs +54 -0
  32. package/package.json +17 -52
  33. package/skills/ultra/SKILL.md +395 -0
  34. package/.ultra-template/changes/abandoned/.gitkeep +0 -0
  35. package/.ultra-template/changes/active/.gitkeep +0 -1
  36. package/.ultra-template/changes/archive/.gitkeep +0 -1
  37. package/.ultra-template/contexts/TEMPLATE.md +0 -135
  38. package/.ultra-template/decisions/.gitkeep +0 -1
  39. package/.ultra-template/evidence/.gitkeep +0 -1
  40. package/.ultra-template/north-star.md +0 -52
  41. package/.ultra-template/project-brief.md +0 -28
  42. package/.ultra-template/research/.gitkeep +0 -1
  43. package/.ultra-template/specs/architecture.md +0 -81
  44. package/.ultra-template/specs/discovery.md +0 -74
  45. package/.ultra-template/specs/product.md +0 -80
  46. package/.ultra-template/specs/research-distillate.md +0 -57
  47. package/.ultra-template/tasks.json +0 -4
  48. package/.ultra-template/test-report.json +0 -44
  49. package/adapters/_shared/host-profile.cjs +0 -5
  50. package/adapters/grok.js +0 -242
  51. package/adapters/kimi.js +0 -232
  52. package/adapters/opencode.js +0 -408
  53. package/adapters/zcode.js +0 -375
  54. package/bin/delegate-worker.cjs +0 -5
  55. package/bin/delegate.cjs +0 -5
  56. package/docs/ARCHITECTURE.md +0 -274
  57. package/docs/ARTIFACT-AUTHORITY.md +0 -305
  58. package/docs/DECISIONS.md +0 -229
  59. package/docs/PHILOSOPHY.md +0 -261
  60. package/docs/RUNTIME-COMPAT-MATRIX.md +0 -316
  61. package/docs/SKILL-AUTHORING.md +0 -113
  62. package/docs/WORKFLOW-LIFECYCLE.md +0 -350
  63. package/docs/evals/adversarial-review-2026-08-14.md +0 -84
  64. package/docs/evals/ultra-5-0-journey-results.md +0 -62
  65. package/docs/evals/ultra-5-0-live-acp-conformance.md +0 -93
  66. package/docs/evals/ultra-5-0-route-journeys.md +0 -145
  67. package/docs/evals/zcode-automation-2026-08-14.md +0 -103
  68. package/hooks/README.md +0 -52
  69. package/hooks/_common.py +0 -1779
  70. package/hooks/adapters/codex.py +0 -295
  71. package/hooks/adapters/grok.py +0 -134
  72. package/hooks/adapters/kimi.py +0 -156
  73. package/hooks/adapters/zcode.py +0 -227
  74. package/hooks/block_dangerous_commands.py +0 -201
  75. package/hooks/compact_context.py +0 -224
  76. package/hooks/mid_workflow_recall.py +0 -47
  77. package/hooks/post_edit_guard.py +0 -215
  78. package/hooks/session_context.py +0 -741
  79. package/skills/ultra-change/SKILL.md +0 -165
  80. package/skills/ultra-change/references/change-contract.md +0 -199
  81. package/skills/ultra-change/references/execution-grant.md +0 -109
  82. package/skills/ultra-change/references/primary-transfer.md +0 -273
  83. package/skills/ultra-change/scripts/validate_primary_transfer.cjs +0 -1928
  84. package/skills/ultra-delegate/SKILL.md +0 -195
  85. package/skills/ultra-delegate/patches/zcode-acp-0.1.0-zcode-0.16.5.patch +0 -184
  86. package/skills/ultra-delegate/references/delegation-contract.md +0 -138
  87. package/skills/ultra-delegate/scripts/acp-conformance.cjs +0 -287
  88. package/skills/ultra-delegate/scripts/acp-driver.cjs +0 -762
  89. package/skills/ultra-delegate/scripts/agent-execution-driver.cjs +0 -320
  90. package/skills/ultra-delegate/scripts/cli-driver.cjs +0 -61
  91. package/skills/ultra-delegate/scripts/delegate-profiles/kimi-read-only.md +0 -15
  92. package/skills/ultra-delegate/scripts/delegate-profiles/kimi-write.md +0 -17
  93. package/skills/ultra-delegate/scripts/delegate-worker.cjs +0 -328
  94. package/skills/ultra-delegate/scripts/delegate.cjs +0 -690
  95. package/skills/ultra-delegate/scripts/delegate_wait.py +0 -86
  96. package/skills/ultra-delegate/scripts/host-profile.cjs +0 -267
  97. package/skills/ultra-deliver/SKILL.md +0 -194
  98. package/skills/ultra-deliver/references/baseline-reconciliation.md +0 -41
  99. package/skills/ultra-dev/SKILL.md +0 -265
  100. package/skills/ultra-dev/references/debugging.md +0 -22
  101. package/skills/ultra-domain-modeling/SKILL.md +0 -79
  102. package/skills/ultra-grilling/SKILL.md +0 -121
  103. package/skills/ultra-grilling/references/reframing.md +0 -76
  104. package/skills/ultra-init/SKILL.md +0 -143
  105. package/skills/ultra-init/references/brownfield-adoption.md +0 -32
  106. package/skills/ultra-init/scripts/init_project.cjs +0 -1031
  107. package/skills/ultra-plan/SKILL.md +0 -160
  108. package/skills/ultra-plan/references/task-evidence-v2.md +0 -300
  109. package/skills/ultra-plan/scripts/validate_task_evidence.cjs +0 -859
  110. package/skills/ultra-research/SKILL.md +0 -167
  111. package/skills/ultra-research/references/00-problem-validation.md +0 -36
  112. package/skills/ultra-research/references/01-opportunity-discovery.md +0 -33
  113. package/skills/ultra-research/references/02-market-assessment.md +0 -31
  114. package/skills/ultra-research/references/03-alternatives.md +0 -31
  115. package/skills/ultra-research/references/04-product-strategy.md +0 -41
  116. package/skills/ultra-research/references/05-assumptions-validation.md +0 -31
  117. package/skills/ultra-research/references/10-user-personas.md +0 -30
  118. package/skills/ultra-research/references/11-user-scenarios.md +0 -28
  119. package/skills/ultra-research/references/20-user-stories.md +0 -31
  120. package/skills/ultra-research/references/21-features-scope.md +0 -38
  121. package/skills/ultra-research/references/22-success-metrics.md +0 -33
  122. package/skills/ultra-research/references/30-architecture-context.md +0 -30
  123. package/skills/ultra-research/references/31-solution-strategy.md +0 -28
  124. package/skills/ultra-research/references/32-building-blocks.md +0 -28
  125. package/skills/ultra-research/references/40-deployment.md +0 -29
  126. package/skills/ultra-research/references/41-quality-risks.md +0 -28
  127. package/skills/ultra-research/references/99-synthesis.md +0 -59
  128. package/skills/ultra-research/references/north-star-v2.md +0 -168
  129. package/skills/ultra-research/references/wayfinding.md +0 -50
  130. package/skills/ultra-research/scripts/validate_north_star.cjs +0 -1174
  131. package/skills/ultra-review/SKILL.md +0 -275
  132. package/skills/ultra-review/references/adversarial-evaluation.md +0 -31
  133. package/skills/ultra-review/references/code.md +0 -17
  134. package/skills/ultra-review/references/comments.md +0 -12
  135. package/skills/ultra-review/references/design.md +0 -12
  136. package/skills/ultra-review/references/errors.md +0 -13
  137. package/skills/ultra-review/references/review-modes.md +0 -29
  138. package/skills/ultra-review/references/spec.md +0 -18
  139. package/skills/ultra-review/references/tests.md +0 -12
  140. package/skills/ultra-review/references/unified-schema.md +0 -284
  141. package/skills/ultra-review/references/worker-packet.md +0 -183
  142. package/skills/ultra-review/scripts/review_wait.py +0 -2943
  143. package/skills/ultra-status/SKILL.md +0 -209
  144. package/skills/ultra-status/references/route-contract.md +0 -100
  145. package/skills/ultra-tdd/SKILL.md +0 -91
  146. package/skills/ultra-tdd/references/templates/README.md +0 -20
  147. package/skills/ultra-tdd/references/templates/feature-flag-default-audit.sh +0 -79
  148. package/skills/ultra-tdd/references/templates/persistence-real.ts +0 -78
  149. package/skills/ultra-tdd/references/templates/testcontainer-postgres.py +0 -78
  150. package/skills/ultra-tdd/references/templates/testcontainer-postgres.ts +0 -73
  151. package/skills/ultra-tdd/references/templates/vertical-slice.ts +0 -66
  152. package/skills/ultra-tdd/references/test-execution.md +0 -23
  153. package/skills/ultra-test/SKILL.md +0 -244
  154. package/skills/ultra-test/references/export-syntax.md +0 -18
  155. package/skills/ultra-test/scripts/validate_review_transport.cjs +0 -549
  156. package/skills/ultra-test/scripts/worktree_digest.cjs +0 -576
  157. package/skills/ultra-think/SKILL.md +0 -56
  158. package/skills/ultra-think/references/autonomy-boundary.md +0 -48
  159. package/skills/ultra-think/references/interaction-boundary.md +0 -42
package/README.md CHANGED
@@ -1,485 +1,74 @@
1
- # Ultra Builder Pro
1
+ # Ultra Builder Pro 6
2
2
 
3
- **English** | [简体中文](README.zh-CN.md)
3
+ Intent is source code, the plan is compiled, progress is computed, and a change is a diff.
4
4
 
5
- Ultra Builder Pro is a file-first engineering workflow for Claude Code, Codex,
6
- OpenCode, Kimi Code, Grok Build, and ZCode. It implements the provider-neutral
7
- **Ultra Core Protocol**: owner–agent cognitive alignment, per-fact canonical
8
- authority, explicit session-local or durable work-package grants, exclusive
9
- verified handover between Agents, typed evidence with recovery, and review that
10
- terminates within an owner-visible budget. It keeps product
11
- intent, specifications, task contracts, evidence, decisions, and recovery notes
12
- in the repository, so a different session or host can continue by reading files
13
- and Git.
14
-
15
- The host model remains the engineer. Ultra supplies reusable methods and checkable
16
- artifacts; it does not replace reasoning with a workflow engine. Agent topology —
17
- one Agent or several, which providers — is the owner's choice at every stage; the
18
- default is the current Agent continuing alone, and handing the work package's
19
- writing authority to a different Agent requires an explicit verified transfer
20
- (OFFER → ACK → RESULT over the repository files and Git).
21
-
22
- ## Ultra Builder Pro 5.0
23
-
24
- Version `5.0.1` is the current implementation of Ultra as a cognitive-alignment harness
25
- for real software engineering. It preserves the accepted 3.0 file-first and model-agency
26
- constitution, then makes workflow position, recovery, and cross-Agent execution directly
27
- observable. It is not a decentralized multi-agent platform and it does not prescribe one
28
- Agent topology. Instead, it keeps five promises:
29
-
30
- - establish the owner-accepted North Star before Research becomes a plan or code;
31
- - let the owner choose one Agent or several, and the provider, at every stage;
32
- - carry canonical intent, decisions, tasks, evidence, and recovery through files
33
- under `.ultra/` plus Git so another session or host can resume from the same facts;
34
- - automate mechanically verifiable authority, permissions, external effects,
35
- evidence, physical limits, and recovery while leaving meaning and strategy to the
36
- model and owner; and
37
- - bound Review and repair so delivery converges instead of turning every observation
38
- into another automatic implementation loop.
39
-
40
- 5.0 expresses those promises through one Route Contract, explicit Init/Research/Change/
41
- Plan responsibilities, file-only fresh-session recovery, an installed Skill-local
42
- delegation runtime, and a replaceable `AgentExecutionDriver`. Stable ACP v1 is preferred
43
- only after the exact Host has passed a recorded conformance drill; otherwise the same
44
- result contract uses a reported CLI fallback. The portable protocol and native
45
- installation cover Claude Code, Codex, OpenCode, Kimi Code, Grok Build, and ZCode. All
46
- six profiles expose stable ACP v1 candidates and have their own current real-provider
47
- receipt. Each selects ACP only while its recorded executable and candidate identity
48
- still match; otherwise it returns a typed CLI fallback. ZCode uses an independently
49
- installed, source-pinned bridge and remains `experimental`.
50
-
51
- 5.0 deliberately does not add a daemon, workflow service, semantic state machine, A2A
52
- network, Team Pack, remote marketplace, or shared authority store. Package publication
53
- and real user installation remain independently verifiable effects; a source version
54
- alone never proves either one occurred.
55
-
56
- ## Why it exists
57
-
58
- Long agentic changes tend to fail in four repeatable ways:
59
-
60
- - intent is paraphrased until the delivered product no longer matches the owner;
61
- - a locally green layer is mistaken for a working end-to-end path;
62
- - context loss turns an interrupted task into archaeology;
63
- - safety mechanisms start deciding product meaning and trap the primary workflow.
64
-
65
- Ultra addresses those failures with short owner-readable files, progressive Skills,
66
- real verification evidence, and Git recovery. There is no database, MCP server,
67
- semantic state machine, generated prompt projection, or background daemon.
68
-
69
- ## Product surface
70
-
71
- The package installs exactly fourteen Skills in three roles.
72
-
73
- ### Owner-invoked workflows
74
-
75
- | Skill | Outcome |
76
- |---|---|
77
- | `ultra-init` | Establish the project skeleton and raw Project Brief |
78
- | `ultra-research` | Establish an accepted North Star and evidence-backed baseline |
79
- | `ultra-change` | Reconcile one requested delta against the accepted baseline |
80
- | `ultra-plan` | Write tracer-bullet tasks, contexts, dependencies, and seams |
81
- | `ultra-dev` | Implement one task through red/green development and six evidence dimensions |
82
- | `ultra-test` | Audit whole-system wiring, E2E behavior, performance, and security |
83
- | `ultra-deliver` | Reconcile, review, document, and archive a completed Change |
84
- | `ultra-delegate` | Run bounded task work, Research evidence, or aggregate review through another supported CLI |
85
-
86
- ### Model-invoked disciplines
87
-
88
- | Skill | Reused method |
89
- |---|---|
90
- | `ultra-grilling` | Draw out incomplete owner intent one material question at a time |
91
- | `ultra-domain-modeling` | Maintain precise ubiquitous language in `CONTEXT.md` |
92
- | `ultra-tdd` | Prove one confirmed seam red, then green |
93
- | `ultra-review` | Run six independent review lenses and synthesize findings |
94
- | `ultra-think` | Stress-test consequential decisions and record durable results |
95
-
96
- `ultra-status` is the single router. It infers the current route from project files,
97
- Git, and installation health without mutating the workflow.
98
-
99
- Public workflows are explicitly selected by the owner by default. Outside a live,
100
- owner-activated execution grant (session-local, or a durable work-package grant), one public workflow can recommend the
101
- next one but does not launch it. Inside that grant, the host model may select only
102
- the covered change-scoped Research, same-Change reconciliation, Plan, Dev, Test, and
103
- reconcile-only Deliver routes. Init, Change intake/evidence/acceptance/abandonment or
104
- primary transfer, Delegate, Deliver finalization, archive, and every external effect
105
- remain owner-selected; Status also remains owner-selected, read-only, and grants no continuation.
106
- Every public transition first displays the derived `UBP Route Card`; Host invocation
107
- metadata is only coarse discovery, and the loaded Skill revalidates its exact mode and
108
- grant without creating route state.
109
- Model-invoked disciplines remain available to the host model and are not separate user
110
- routes. The model selects one when the active task presents its trigger: incomplete
111
- intent uses grilling, competing terms use domain modeling, an accepted seam uses TDD,
112
- review-ready evidence uses review, and a consequential unresolved decision uses think.
113
- A host with native bounded subagents may parallelize review lenses; another host runs
114
- the same lens assets sequentially.
115
-
116
- Inside `ultra-research`, the first six references are six semantic lenses, not six
117
- extra Skills: problem validation, opportunity discovery, market assessment,
118
- alternatives, product strategy, and assumptions validation. `wayfinding.md` chooses
119
- the smallest dependency-correct path through those and the later evidence lenses.
120
- Grilling still owns how to ask one missing question, Think owns one consequential
121
- trade-off, and Domain Modeling owns vocabulary; Research owns the overall question
122
- map, evidence convergence, owner checkpoints, and baseline promotion.
123
-
124
- ### What happened to the original Agents
125
-
126
- Version 5.0.1 does not install a custom `agents/` projection. The old review workers became the
127
- six focused files under `ultra-review/references/`; review coordination and synthesis
128
- belong to the parent `ultra-review` Skill. The old debugger procedure lives under
129
- `ultra-dev/references/debugging.md`, and test execution lives under
130
- `ultra-tdd/references/test-execution.md`. These are assets of their Skills and therefore
131
- travel to all six hosts. They preserve a bounded role without pretending that every
132
- host exposes the same custom-agent API.
133
-
134
- ## Project authority
135
-
136
- A project after its first accepted Research baseline uses this shape. Immediately after
137
- Init, `CONTEXT.md` does not exist yet and the North Star/specification files are empty
138
- skeletons.
139
-
140
- ```text
141
- CONTEXT.md
142
- .ultra/
143
- ├── .gitignore # ignores only derived Ultra paths
144
- ├── project-brief.md
145
- ├── north-star.md
146
- ├── tasks.json
147
- ├── test-report.json
148
- ├── specs/
149
- │ ├── product.md
150
- │ ├── architecture.md
151
- │ ├── discovery.md
152
- │ └── research-distillate.md
153
- ├── changes/
154
- │ ├── active/<change-id>/{intent.md,delivery.md}
155
- │ ├── archive/<change-id>/{intent.md,delivery.md}
156
- │ └── abandoned/<change-id>/intent.md # includes exact Abandonment closure
157
- ├── contexts/task-<task-id>.md
158
- ├── decisions/<decision-id>.md
159
- ├── evidence/<task-id>/...
160
- └── research/<run-id>/{brief.md,<step-id>.md}
161
- ```
162
-
163
- The optional `brief.md` is derived navigation; the selected step reports are cited
164
- evidence, and promoted semantic facts live in the other canonical files. Git provides
165
- history, comparison, rollback, and archive moves. The following additional paths are
166
- derived:
167
-
168
- ```text
169
- .ultra/.runtime/
170
- .ultra/progress/
171
- .ultra/reviews/
172
- ```
173
-
174
- `.ultra/.runtime/` and `.ultra/progress/` can be deleted or rebuilt from current
175
- authority. Retain the exact current strict review session until both Test and Deliver
176
- have successfully consumed it; only then may that session be garbage-collected. If it
177
- is lost before both consumers finish, run a fresh Review and Test and never reconstruct
178
- the old receipt.
179
-
180
- See [Artifact Authority](docs/ARTIFACT-AUTHORITY.md) for writer, reader, promotion,
181
- staleness, and recovery rules.
182
-
183
- ### Which route writes which document
184
-
185
- | Route | Canonical write | Who consumes it next |
186
- |---|---|---|
187
- | `ultra-init` | raw `project-brief.md`, empty North Star and specification skeletons, and empty task/test ledgers | research, status, and the pre-baseline session Hook fallback |
188
- | `ultra-research` | accepted North Star, first domain baseline, selected cited reports, reconciled specifications, and distillate | change, plan, and delivery |
189
- | `ultra-change` | one active `intent.md` with stable `change_id`, Research Disposition, and only the accepted baseline sections touched by that delta; or an exact Abandonment closure before an owner-authorized move | active: research through delivery; abandoned: future Change history and status |
190
- | `ultra-plan` | append-only `tasks.json` rows for the active `change_id`, one context per task, and Planning Posture in the active intent | dev and every resume path |
191
- | `ultra-dev` | source/tests, typed task evidence, ledger-only task status, Completion, Task Review, and Resume Note | review, test, status, delivery |
192
- | `ultra-test` | the one current `test-report.json` bound to Change id, current task ids, intent digest, HEAD, and product-worktree digest | status and delivery |
193
- | `ultra-deliver` | first reconciled specs/docs, then after a fresh Test snapshot one `delivery.md` and the archived Change directory | owner and future Change history |
194
- | `ultra-status` | none | recommends the smallest explicit route from current files |
195
- | `ultra-delegate` | derived runtime receipt plus an isolated worktree diff | primary host inspection and optional integration |
196
-
197
- `ultra-domain-modeling` is the sole focused writer of `CONTEXT.md`; `ultra-think` writes
198
- a durable decision only after owner acceptance. Review packets, Hook progress, compact
199
- snapshots, and delegation receipts are derived evidence, not extra semantic documents.
5
+ UBP gives Claude Code and Codex one `ultra` Skill, a deterministic `ubp` engine, and a
6
+ SessionStart hook. The model owns judgment; the engine computes progress from project files
7
+ and executable checks. Node.js 22 or newer and Git are required.
200
8
 
201
9
  ## Install
202
10
 
203
- Node.js 22 or newer is required.
204
-
205
- ```bash
206
- # Current project, one host
207
- npx ultra-builder-pro-cli@5.0.1 --claude --local
208
- npx ultra-builder-pro-cli@5.0.1 --codex --local
209
-
210
- # Global installation
211
- npx ultra-builder-pro-cli@5.0.1 --opencode --global
212
- npx ultra-builder-pro-cli@5.0.1 --kimi --global
213
- npx ultra-builder-pro-cli@5.0.1 --grok --global
214
- npx ultra-builder-pro-cli@5.0.1 --zcode --global
215
-
216
- # All supported hosts
217
- npx ultra-builder-pro-cli@5.0.1 --all --global
218
- ```
219
-
220
- ZCode ACP delegation additionally requires the independently built bridge and an
221
- installed ZCode Desktop runtime. Ultra ships the small source patch needed by ZCode
222
- CLI 0.16.5, but installs neither dependency and never records provider credentials:
223
-
224
- ```bash
225
- git clone https://github.com/jpalmae/zcode-acp
226
- git -C zcode-acp checkout 42fe149d4b501469343c01f23ba3801832306d53
227
- git -C zcode-acp apply \
228
- /path/to/installed/ultra-delegate/patches/zcode-acp-0.1.0-zcode-0.16.5.patch
229
- cargo test --locked --manifest-path zcode-acp/Cargo.toml
230
- cargo install --locked --path zcode-acp
11
+ ```sh
12
+ npm install -g ultra-builder-pro-cli@6.0.0
13
+ ubp --claude --global
14
+ ubp --codex --global
15
+ # Or install both:
16
+ ubp --all --global
231
17
  ```
232
18
 
233
- The base commit, patch SHA-256
234
- `174dfd0feafe84320556a84b5ae08b10e44c5515fea4992fd1d58af54cee4e3d`, locked tests,
235
- fake E2E, release build, and real ZCode 0.16.5 session were verified for 5.0. Keep the
236
- binary on `PATH`; its `--version` must report
237
- `zcode-acp 0.1.0+ultra.zcode.0.16.5`. Use the platform's installed ZCode CLI path
238
- outside macOS.
239
-
240
- Provider identity is separate from the Host: ZCode Desktop is the runtime, while the
241
- model account may be domestic 智谱 BigModel or international Z.AI. A domestic BigModel
242
- Coding Plan config uses the official Anthropic-compatible endpoint
243
- `https://open.bigmodel.cn/api/anthropic` and a BigModel API key in
244
- `~/.zcode/cli/config.json`; it must not use the Z.AI OAuth login. The live 5.0 drill used
245
- `builtin:bigmodel-coding-plan/GLM-5.2`. See the
246
- [official BigModel Claude API compatibility guide](https://docs.bigmodel.cn/cn/guide/develop/claude/introduction).
247
-
248
- These pinned `npx` commands resolve the immutable registry version after publication.
249
- Source-tree verification uses `node bin/install.js --config-dir <isolated-path>` when
250
- it must not mutate the real user installation; the separate 5.0 release drill also
251
- verified an ownership-safe install, Doctor, ZCode uninstall, and reinstall in all six
252
- real Host homes.
253
-
254
- Use the host's native Skill picker or invocation syntax to select an owner workflow.
255
- Codex exposes namespaced entries such as `$ultra-builder-pro:ultra-init`. The installed
256
- frontmatter and metadata keep user routes explicit and model disciplines implicit.
257
-
258
- ### Diagnose, update, and uninstall
259
-
260
- Installation is managed, atomic, and provenance-checked.
261
-
262
- ```bash
263
- # Re-running install updates the managed artifact
264
- npx ultra-builder-pro-cli@5.0.1 --codex --global
265
-
266
- # Read-only diagnosis
267
- npx ultra-builder-pro-cli@5.0.1 --all --global --doctor --json
268
-
269
- # Remove only managed Ultra assets
270
- npx ultra-builder-pro-cli@5.0.1 --all --global --uninstall
271
- ```
272
-
273
- `--config-dir <path>` isolates both the primary config and host-owned sidecars. It is
274
- the safe choice for tests and does not fall through to the real home directory. When
275
- more than one host is selected, each host receives `<path>/<runtime>` so their native
276
- layouts cannot overwrite one another.
277
-
278
- Uninstall removes the managed plugin and prunes only empty config shells that were
279
- absent before the first install. Pre-existing registries, directories, symlinks, and
280
- any path containing owner data are preserved.
281
-
282
- Kimi Code, Grok Build, and ZCode currently expose user-scoped plugins only, so `--local`
283
- rejects them before mutation. Claude Code, Codex, and OpenCode support project-local
284
- installation; all six support managed global installation and isolated
285
- `--config-dir` verification.
286
-
287
- ## Typical workflow
288
-
289
- For day-to-day work on an existing project, a new request starts with `ultra-change`,
290
- not an open-ended Research run. Enter `ultra-research` directly only to establish the
291
- first baseline, or to answer the bounded evidence question recorded by the same active
292
- Change. Every public transition shows a derived Route Card with its current Mode,
293
- Position, observable Exit condition, material checkpoint, and Next route.
294
-
295
- 1. Select `ultra-init` once. It writes the skeleton, preserves the owner's raw one-line
296
- request and broad outline in the Project Brief, initializes Git when needed, and
297
- stops before product research.
298
- 2. Select `ultra-research` to turn that brief into the first accepted North Star,
299
- shared vocabulary, and evidence-backed product and architecture baseline. For an
300
- unclear multi-lens question it first writes a derived Wayfinding brief; for one
301
- bounded evidence gap it skips that extra file.
302
- 3. Select `ultra-change` for a requested delta. It reconciles only the baseline sections
303
- the delta touches before planning; it does not rebuild the project baseline. Its
304
- Research Disposition either cites sufficient evidence or names the bounded question
305
- and exit evidence that must return through Research. A micro edit that makes no
306
- specification sentence false stays outside Ultra; every accepted Change receives the
307
- smallest Plan graph justified by its real seams, evidence, review, and recovery needs.
308
- A profile never fixes task count. While that Change remains active, reconcile its
309
- same stable id; never open a second active Change for a separate request.
310
- 4. Select `ultra-plan` to record public seams and produce resumable tracer-bullet tasks.
311
- Its earliest observable slice must cross a real consumer and real data path and name
312
- the owner-visible observation. The model owns ordinary technical seams; the owner
313
- decides only a seam that changes the public contract or another material trade-off.
314
- 5. Select `ultra-dev` for one task at a time. `.ultra/tasks.json` is the sole task-status
315
- authority. Dev records typed v2 evidence and completes task review while the row is
316
- still `in_progress`; only after blocking findings and affected evidence are resolved
317
- does it write `completed`, add Completion, and rewrite the Resume Note.
318
- 6. Select `ultra-test` once tasks for the active Change are completed with current v2
319
- evidence and retained task-review provenance. Historical ledger rows and legacy
320
- context Status fields do not enter this audit. Local green tests do not substitute
321
- for wiring and E2E proof.
322
- 7. Select `ultra-deliver` to run aggregate review and reconcile documentation. If that
323
- changes product or semantic files, rerun Test; re-enter Deliver on the fresh snapshot
324
- to write delivery metadata and archive the stable Change id. Commit, push, tag,
325
- publication, and deployment remain separately authorized effects.
326
-
327
- For one accepted Change, the owner may activate its exact `Execution Grant` in either
328
- mode. A `session-local` grant lives only in the current conversation: when that
329
- activation is lost — a fresh session, another host, or compaction — the work stops and
330
- waits for a new owner activation. A `durable work-package` grant lets a fresh Agent or
331
- host continue one exact work package, but only after the Agent stably verifies the
332
- recorded grant itself. In both modes the model may select the covered change-scoped
333
- Research, same-Change reconciliation, Plan, Dev, Test, and reconcile-only Deliver
334
- routes until the next semantic stop or declared budget, and neither mode grants
335
- finalization or archive: writing `delivery.md`, version
336
- or package posture, and archiving always require a current explicit owner invocation,
337
- as do commit, push, publication, deployment, installation, and every other external
338
- effect.
339
-
340
- At any point, `ultra-status` can reconstruct the current position. A fresh session
341
- starts from repository root and `HEAD`, resolves exactly one active Change, then reads
342
- `.ultra/tasks.json`, the matching `context_file` and its `## Resume Note`, `CONTEXT.md`,
343
- relevant decisions, specifications, evidence, and the current Git diff. It never reruns
344
- completed Research merely because conversation memory is gone. If active authority is
345
- ambiguous or unreadable, Status switches to read-only recovery, names the unsafe fact,
346
- and gives the cheapest repair, retry, cancel, abandon, or fresh-session path without
347
- choosing an intent or writing semantic files. Archived and abandoned unfinished rows
348
- remain history, not the frontier.
349
-
350
- ## Three independent integration defences
351
-
352
- The workflow does not treat “tests pass” as an end-to-end verdict.
353
-
354
- - `ultra-plan` rejects horizontal feature slicing and confirms observable seams.
355
- - `ultra-dev` records tests, persistence, feature flags, vertical execution, and spec
356
- trace as six separate observations.
357
- - `ultra-test` searches changed exports for real non-test consumers and runs the
358
- smallest primary flow through its boundary.
359
-
360
- Each defence can report a defect independently. The reports are sensors, not semantic
361
- gates; the model and owner decide the response without erasing evidence.
362
-
363
- ## Hooks
364
-
365
- Five optional hooks accelerate file reading and protect a narrow effect boundary:
366
-
367
- | Hook | Behavior |
368
- |---|---|
369
- | `session_context.py` | Inject the accepted North Star, or the Project Brief fallback before Research, plus current acceptance |
370
- | `mid_workflow_recall.py` | Restate acceptance before relevant source operations |
371
- | `compact_context.py` | Save and restore a disposable Git/file snapshot |
372
- | `post_edit_guard.py` | Record mechanical evidence observations after edits |
373
- | `block_dangerous_commands.py` | Advise on additive protected-branch publication; deny history rewrites and named destructive shell effects until the exact command is authorized |
374
-
375
- All five hooks exit silently when `.ultra/` is absent. Details are in
376
- [Plugin Isolation](docs/PLUGIN-ISOLATION-CONTRACT.md).
377
-
378
- ## Delegation
379
-
380
- Delegation writes an immutable instruction and permission envelope, then selects one
381
- Host-local `AgentExecutionDriver` and starts it in the background. ACP is selected only
382
- for an executable stdio endpoint that negotiates stable v1 and has a passed per-Host
383
- conformance record with evidence; otherwise the same result contract uses `CliDriver`
384
- and reports the exact fallback reason. All six current Host rows have their own passing
385
- real-provider receipt; a missing executable, candidate-identity mismatch, or
386
- stale/missing receipt still returns the typed CLI fallback. An ACP authentication error
387
- detected before `session/prompt` runs the bounded CLI path once and records
388
- `acp_auth_required`; no other ACP failure is retried, so Ultra cannot duplicate a
389
- provider task. Empty
390
- writable roots select native read-only mode;
391
- declared roots select bounded write mode. The model returns one schema-constrained final
392
- response; the launcher extracts it from native structured output, validates the actual
393
- Git diff, and atomically publishes a terminal `finished`, `blocked`, or `failed` result
394
- beside the instruction. The digest-bound packet is embedded in the worker prompt, so a
395
- strict host need not read instruction files outside its isolated worktree.
396
-
397
- ```bash
398
- node <loaded-ultra-delegate-skill-dir>/scripts/delegate.cjs run --to codex \
399
- --instruction .ultra/.runtime/delegations/D-01/instruction.md \
400
- --permission .ultra/.runtime/delegations/D-01/permission.json \
401
- --worktree .ultra/.runtime/worktrees/D-01
402
- ```
403
-
404
- The loaded Skill path is canonical and works after a clean `npx` plugin install without
405
- a global `ubp` or another `npx` lookup for Ultra; the pinned Claude/Codex ACP adapters
406
- may themselves run through `npx`. `ubp delegate` remains a one-release compatibility
407
- wrapper. Use the installed Skill's `scripts/delegate_wait.py` to wait for `result.json`
408
- without loading intermediate worker output into the parent context. Delegation grants no new
409
- authority; writable roots remain inside the worktree, and its permission file must
410
- declare zero external effects without widening the host sandbox.
411
- The immutable instruction names task execution/continuation, scoped Research evidence,
412
- or aggregate Change review/verification. The latter two may be read-only and do not
413
- require a task row, keeping pre-Plan Research and post-task cross-family review
414
- reachable without inventing ledger work.
415
- ZCode resolves only the installed Desktop runtime through the independently installed
416
- `zcode-acp` bridge and remains `experimental`. Its capability, read-only,
417
- permission, cancellation/no-orphan, cwd/diff, result-parity, and redaction drills pass;
418
- promotion still requires an official stability contract for the App-internal runtime.
419
- Doctor reports runner health, ACP capability, candidate identity, selected driver,
420
- fallback reason, and ZCode maturity independently.
421
-
422
- ## Host support
423
-
424
- | Host | Skills | Hooks | Managed lifecycle |
425
- |---|---:|---:|---|
426
- | Claude Code | 14 | 5 direct | install / doctor / update / uninstall |
427
- | Codex | 14 + native metadata | 5 through wire adapter | plugin + personal marketplace |
428
- | OpenCode | 14 | 5 through native JS plugin | bundle + skill directories |
429
- | Kimi Code | 14 | 5 through wire adapter | managed plugin registry |
430
- | Grok Build | 14 | 5 through wire adapter | native plugin registration when available |
431
- | ZCode | 14 | 5 through wire adapter | inline plugin + local marketplace + reversible config registration |
432
-
433
- See [Runtime Compatibility](docs/RUNTIME-COMPAT-MATRIX.md) for exact paths and host
434
- limitations.
435
-
436
- ## Development
437
-
438
- ```bash
439
- # Node contracts, package smoke, host adapters, delegation, and Skills
440
- npm run test:node
441
-
442
- # File-first hook behavior and wire wrappers
443
- npm run test:hooks
444
-
445
- # Complete release gate
446
- npm run verify:release
447
-
448
- # Inspect the exact publish artifact
449
- npm pack --dry-run --json
450
- ```
451
-
452
- Every changed Skill is also validated with the Codex Skill Creator validator. A changed
453
- Codex manifest is validated against the Plugin Creator schema. No release effect is
454
- implied by a green verification run, and validator success establishes structural
455
- conformance rather than semantic acceptance.
456
-
457
- ## Documentation
458
-
459
- - [5.0 design and acceptance contract](docs/ULTRA-BUILDER-PRO-5.0.zh-CN.md) —
460
- Route, Skill ownership, continuation, ACP/CLI execution, migration, and journey
461
- boundaries implemented by 5.0.1.
462
- - [5.0 journey results](docs/evals/ultra-5-0-journey-results.md) — observable source,
463
- isolated-runtime, real-provider, real-HOME, and cross-platform outcomes plus the
464
- deliberately excluded service-deployment boundary.
465
- - [Current authority](.ultra/north-star.md) — this repository's accepted
466
- North Star, revision `north-star-v2-r3`, is the canonical current authority;
467
- `.ultra/tasks.json` and the stable Change under `.ultra/changes/active/` or
468
- `.ultra/changes/archive/` record the current or delivered work frontier.
469
- - Frozen design history (immutable accepted records, not live status):
470
- [3.0 North Star R3](docs/ULTRA-BUILDER-PRO-3.0-NORTH-STAR-R3.zh-CN.md) —
471
- the hash-bound accepted r3 design — and
472
- [3.0 design](docs/ULTRA-BUILDER-PRO-3.0.zh-CN.md), superseded by r3.
473
- - [Philosophy](docs/PHILOSOPHY.md)
474
- - [Architecture](docs/ARCHITECTURE.md)
475
- - [Artifact Authority](docs/ARTIFACT-AUTHORITY.md)
476
- - [Workflow Lifecycle](docs/WORKFLOW-LIFECYCLE.md)
477
- - [Skill Authoring](docs/SKILL-AUTHORING.md)
478
- - [Plugin Isolation](docs/PLUGIN-ISOLATION-CONTRACT.md)
479
- - [Runtime Compatibility](docs/RUNTIME-COMPAT-MATRIX.md)
480
- - [Adversarial Review Evaluation](docs/evals/adversarial-review-2026-08-14.md)
481
- - [ZCode Automation Evaluation](docs/evals/zcode-automation-2026-08-14.md)
482
-
483
- ## License
484
-
485
- [MIT](LICENSE)
19
+ Use `--config-dir <dir>` for an isolated installation; `--all` gives each host a separate
20
+ subdirectory. Only Claude Code supports `--local`. Codex installs are user-scope only:
21
+ `--codex` defaults to user scope; `--codex --local` is rejected unless `--config-dir` isolates the
22
+ install.
23
+ Inspect an installation with `ubp --all --global --doctor --json`. Remove managed assets
24
+ with `ubp --all --global --uninstall`.
25
+
26
+ Each installed plugin carries the engine. Its Skill includes the absolute Node command to
27
+ use for every engine command, regardless of any `ubp` on PATH. No Python runtime is needed.
28
+
29
+ ## First session
30
+
31
+ Open the project in Claude Code and invoke `/ultra` (full name `/ultra-builder-pro:ultra`);
32
+ in Codex invoke `$ultra-builder-pro:ultra`. Run `ubp status` to see the current state.
33
+ A project without `.ultra/spec.md` starts with an interview, then a specification, checks and a
34
+ milestone plan.
35
+
36
+ The SessionStart hook prints progress and a reminder to use `ultra` only when
37
+ `.ultra/spec.md` exists, and stays silent inside a drive's writer or reviewer (`UBP_DRIVE`). It does not start work or write project files.
38
+
39
+ Codex users review and trust the plugin hook once with `/hooks`; it is skipped until then.
40
+ Changed hook definitions need renewed trust. Without hook trust, the Skill's first step,
41
+ `ubp status`, still shows the progress line.
42
+ See [Codex hook trust](https://learn.chatgpt.com/docs/hooks).
43
+
44
+ ## Commands
45
+
46
+ | Command | Purpose |
47
+ | --- | --- |
48
+ | `ubp status` | Compute progress and the next step |
49
+ | `ubp gate` | Validate the plan and record its baseline |
50
+ | `ubp check [ids]` | Run checks and record evidence |
51
+ | `ubp node done <id>` | Complete a node with green requirements |
52
+ | `ubp context <id>` | Compile a node brief |
53
+ | `ubp milestone close <id> --owner "words" --review <file>` | Close a reviewed milestone |
54
+ | `ubp approve <items> --owner "words"` | Record approval of reductions |
55
+ | `ubp retro` | Show repeated failure classes |
56
+ | `ubp merge <branch> --expect-head <sha>` | Verify and merge a worker branch |
57
+ | `ubp drive --writer <cmd> [--reviewer <cmd>]` | Run nodes unattended until the next Owner touch |
58
+
59
+ Engine commands accept `--root <dir>` and `--json`.
60
+ See [file formats and exit codes](engine/FORMATS.md)
61
+ and the [method](skills/ultra/SKILL.md) for required evidence and approval boundaries.
62
+
63
+ ## Coming from 5.x
64
+
65
+ Version 6 replaces the fourteen `ultra-*` Skills with one method and replaces the five
66
+ Python hooks with one advisory Node hook. OpenCode, Kimi, Grok and ZCode adapters,
67
+ `run`, `delegate`, ACP/Pi execution, durable grants, wake-up machinery and the old project
68
+ template are removed. These mechanisms competed for the next step; v6 derives it from the
69
+ engine's state. Existing 5.x project records are not automatically migrated.
70
+
71
+ Keep 5.0.1, the last published 5.x, in a separate configuration directory if you still
72
+ need those workflows (5.0.2 was never published).
73
+ The old source remains in Git history. See [changes](CHANGELOG.md) and the
74
+ [plugin boundary](docs/PLUGIN-ISOLATION-CONTRACT.md).