uctm 1.0.0 → 1.0.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +38 -31
  2. package/bin/cli.mjs +1 -1
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -27,6 +27,14 @@ claude
27
27
  > [new-feature] Add a hello world feature
28
28
  ```
29
29
 
30
+ To run without permission prompts (file creation, shell commands, etc.), use bypass mode:
31
+
32
+ ```bash
33
+ claude --dangerously-skip-permissions
34
+ ```
35
+
36
+ > **Warning**: Only use bypass mode in isolated environments or when you trust the pipeline fully. See [Claude Code Permissions](https://code.claude.com/docs/en/permissions) for details.
37
+
30
38
  That's it. The router analyzes your request, plans the work, and executes through isolated subagent pipelines.
31
39
 
32
40
  ---
@@ -85,7 +93,7 @@ Six subagents work across any project and any language, automatically handling *
85
93
  > [bugfix] Fix typo in login error message
86
94
  ```
87
95
 
88
- Router selects `execution-mode: direct` handles entirely in its own session. No subagent spawned. Creates WORK-NN directory + PLAN + result.md + commit.
96
+ Main Claude calls router, which selects `execution-mode: direct` and handles everything in its session. No additional subagent spawned. Creates WORK-NN directory + PLAN + result.md + commit.
89
97
 
90
98
  ### Quick Task (pipeline mode)
91
99
 
@@ -93,7 +101,7 @@ Router selects `execution-mode: direct` → handles entirely in its own session.
93
101
  > [bugfix] Fix the login button not responding on mobile
94
102
  ```
95
103
 
96
- Router selects `execution-mode: pipeline` creates PLAN, delegates to builder → verifier → committer. Router context stays clean.
104
+ Main Claude calls router, which selects `execution-mode: pipeline` and creates PLAN. Then Main Claude calls builder → verifier → committer in sequence.
97
105
 
98
106
  ### Complex Feature (WORK)
99
107
 
@@ -158,7 +166,7 @@ Skip to a specific TASK within a WORK (e.g., retry after a failure):
158
166
  > Run WORK-02: TASK-02
159
167
  ```
160
168
 
161
- The scheduler reads the TASK file directly and dispatches builder → verifier → committer.
169
+ The scheduler returns the next TASK, then Main Claude calls builder → verifier → committer in sequence.
162
170
 
163
171
  #### 7. Force WORK Creation (Skip Complexity Check)
164
172
 
@@ -268,34 +276,26 @@ claude
268
276
 
269
277
  ## Concept: Three Execution Modes
270
278
 
271
- The **router** analyzes every `[]`-tagged request and selects one of three `execution-mode` values:
279
+ Main Claude detects the `[]` tag and calls the **router** subagent, which selects one of three `execution-mode` values:
272
280
 
273
281
  ```
274
- User Request
275
-
276
-
277
- ┌────────┐
278
- │ router │ ── no [] tag ──▶ handle directly (no pipeline)
279
- └───┬────┘
280
- [] tag detected
281
-
282
- Assess complexity → execution-mode
283
- (reads .agent/router_rule_config.json if present)
284
-
282
+ User Request → Main Claude (orchestrator)
283
+
284
+
285
+ ┌────────┐
286
+ │ router │ (called by Main Claude)
287
+ └───┬────┘
288
+
289
+ execution-mode returned
290
+
285
291
  ├─ direct (no build/test required)
286
-
287
- │ Router handles everything — no subagent overhead
288
- │ Creates WORK-NN/PLAN.md + result.md + commit (0 extra sessions)
292
+ → router handles everything — 0 additional subagent calls
289
293
 
290
294
  ├─ pipeline (build/test required, single domain, sequential)
291
-
292
- │ router → builder → verifier → committer
293
- │ Router creates PLAN, dispatches 3 subagents
295
+ → Main Claude calls: builder → verifier → committer (in sequence)
294
296
 
295
297
  └─ full (multi-domain / complex DAG / new module / 5+ tasks)
296
-
297
- router → planner → scheduler → [builder → verifier → committer] × N
298
- (full planning + multi-task pipeline)
298
+ → Main Claude calls: planner → scheduler → [builder → verifier → committer] × N
299
299
  ```
300
300
 
301
301
  All three modes output to `works/WORK-NN/` and guarantee `result.md` + `COMMITTER DONE` callback.
@@ -312,18 +312,19 @@ WORK (unit of work) A single goal. The unit requested by the user.
312
312
 
313
313
  ### pipeline mode (Single Task, Delegated)
314
314
 
315
- Subagent-delegated path for moderate single tasks. Router stays clean.
315
+ Subagent-delegated path for moderate single tasks. Main Claude calls each agent in sequence. Router stays clean.
316
316
 
317
317
  ```
318
- router → builder(sonnet) → verifier(haiku) → committer(haiku)
318
+ Main Claude → builder(sonnet) → verifier(haiku) → committer(haiku)
319
+ (each called individually by Main Claude)
319
320
  ```
320
321
 
321
322
  ### direct mode (Trivial)
322
323
 
323
- Router handles everything in its own context. No subagent sessions spawned.
324
+ Main Claude calls router, which handles everything in its own session. No additional subagent calls.
324
325
 
325
326
  ```
326
- router: Analyze → Implement → Self-verify → Commit → result.md
327
+ Main Claude → router: Analyze → Implement → Self-verify → Commit → result.md
327
328
  ```
328
329
 
329
330
  ---
@@ -332,7 +333,12 @@ router: Analyze → Implement → Self-verify → Commit → result.md
332
333
 
333
334
  ### WORK Pipeline (Complex)
334
335
 
336
+ > Subagents cannot nest — Main Claude (CLI terminal) orchestrates every call.
337
+
335
338
  ```
339
+ Main Claude (orchestrator)
340
+ ┌──────────┼──────────────────────┐
341
+ │ │ │
336
342
  router planner scheduler builder verifier committer
337
343
  ┌────────┐ ┌─────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐
338
344
  │Request │────▶│Create │────▶│Dependency │────▶│Code │────▶│Build/Test│────▶│Result │
@@ -352,7 +358,8 @@ router: Analyze → Implement → Self-verify → Commit → result.md
352
358
  │PLAN │─────▶│Code │────▶│Build/Test│────▶│Result │
353
359
  │+TASK │ │Implement │ │Verify │ │→ git │
354
360
  └────────┘ └──────────┘ └──────────┘ └──────────┘
355
- (context clean) (sonnet) (haiku) (haiku)
361
+ (sonnet) (haiku) (haiku)
362
+ ← each called by Main Claude →
356
363
  ```
357
364
 
358
365
  ### direct mode (Trivial)
@@ -678,8 +685,8 @@ For a monorepo with strict build requirements:
678
685
  ### Three Execution Modes
679
686
 
680
687
  The router matches effort to complexity via `execution-mode`:
681
- - **direct**: 1-line typo fix — 0 extra sessions, Router handles everything. Committer session overhead (~12,500 tokens) completely eliminated.
682
- - **pipeline**: Moderate fix — delegated to builder → verifier → committer, router context stays clean
688
+ - **direct**: 1-line typo fix — Main Claude calls router, which handles everything. 0 additional subagent sessions.
689
+ - **pipeline**: Moderate fix — Main Claude calls builder → verifier → committer in sequence. Main Claude only orchestrates, minimizing its own context usage
683
690
  - **full**: Complex features — full planning, decomposition, and tracking
684
691
 
685
692
  All three modes output to `works/WORK-NN/` with identical artifact structure (PLAN.md + result.md + COMMITTER DONE callback), ensuring Runner integration works regardless of mode.
package/bin/cli.mjs CHANGED
@@ -1,4 +1,4 @@
1
- #!/usr/bin/env node
1
+ #!/usr/bin/env node
2
2
 
3
3
  import { VERSION } from '../lib/constants.mjs';
4
4
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "uctm",
3
- "version": "1.0.0",
3
+ "version": "1.0.2",
4
4
  "description": "Universal Claude Task Manager — SDD-based task pipeline subagent system for Claude Code CLI",
5
5
  "type": "module",
6
6
  "bin": {