@lumenflow/cli 2.8.0 → 2.10.0

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.
@@ -53,6 +53,30 @@ cd /path/to/main && pnpm wu:done --id WU-XXXX
53
53
 
54
54
  ---
55
55
 
56
+ ## When to Use Initiatives
57
+
58
+ Use **Initiatives** for multi-phase work spanning multiple WUs:
59
+
60
+ - **Product visions**: "Build a task management app"
61
+ - **Larger features**: Work requiring multiple WUs across lanes
62
+ - **Complex projects**: Anything that needs phased delivery
63
+
64
+ ```bash
65
+ # Create an initiative for multi-phase work
66
+ pnpm initiative:create --id INIT-001 --title "Feature Name" \
67
+ --description "..." --phase "Phase 1: MVP" --phase "Phase 2: Polish"
68
+
69
+ # Add WUs to the initiative
70
+ pnpm initiative:add-wu --initiative INIT-001 --wu WU-XXX --phase 1
71
+
72
+ # Track progress
73
+ pnpm initiative:status --id INIT-001
74
+ ```
75
+
76
+ **Skip initiatives** for: single-file bug fixes, small docs updates, isolated refactoring.
77
+
78
+ ---
79
+
56
80
  ## Setup Notes (Common First-Run Failures)
57
81
 
58
82
  ### Lane inference (sub-lanes)
@@ -224,6 +224,53 @@ pnpm prettier --write <files> # Safe in worktree
224
224
 
225
225
  ---
226
226
 
227
+ ## Mistake 12: Not Acting on Implied Directives
228
+
229
+ ### Wrong
230
+
231
+ ```text
232
+ Agent: [presents research findings about a bug]
233
+ User: "so update 1348 then?"
234
+ Agent: [no response or asks "should I update it?"]
235
+ ```
236
+
237
+ ### Right
238
+
239
+ ```text
240
+ Agent: [presents research findings about a bug]
241
+ User: "so update 1348 then?"
242
+ Agent: Updating WU-1348 with these findings now.
243
+ [Edits the WU YAML file]
244
+ ```
245
+
246
+ ### How to Update a WU
247
+
248
+ **Option 1: CLI command**
249
+
250
+ ```bash
251
+ pnpm wu:edit --id WU-1348 --notes "Research findings: ..."
252
+ ```
253
+
254
+ **Option 2: Direct file edit**
255
+
256
+ ```bash
257
+ # Edit docs/04-operations/tasks/wu/WU-1348.yaml directly
258
+ ```
259
+
260
+ ### Recognizing Implied Directives
261
+
262
+ Phrases that mean "do this now":
263
+
264
+ - "so do X then?" / "so X then?"
265
+ - "update that" / "add that"
266
+ - "fix it" / "make that change"
267
+ - "go ahead" / "proceed"
268
+ - "sounds good, do it"
269
+
270
+ **Rule:** Information + user confirmation = immediate action. Don't ask "should I proceed?" when user already implied yes.
271
+
272
+ ---
273
+
227
274
  ## Quick Checklist
228
275
 
229
276
  Before starting any WU:
@@ -0,0 +1,183 @@
1
+ # LUMENFLOW_FORCE Usage Investigation
2
+
3
+ **Last updated:** {{DATE}}
4
+
5
+ This document presents the findings from WU-1220, investigating improper LUMENFLOW_FORCE usage in agent sessions and providing prevention recommendations.
6
+
7
+ ---
8
+
9
+ ## Executive Summary
10
+
11
+ Analysis of `.beacon/force-bypasses.log` reveals that LUMENFLOW_FORCE is used extensively, but almost exclusively by human operators (user "Tom") rather than AI agents. The vast majority of uses are for legitimate infrastructure operations such as:
12
+
13
+ - Release version pushes
14
+ - Micro-worktree recovery operations
15
+ - State synchronization
16
+ - Emergency fixes
17
+
18
+ **Key Finding:** AI agents are NOT the primary concern. The existing safeguards (documentation, audit logging) are working as designed. The force bypass mechanism serves its intended purpose: enabling humans to perform legitimate administrative operations while maintaining an audit trail.
19
+
20
+ ---
21
+
22
+ ## Root Cause Analysis
23
+
24
+ ### Observations from Audit Log
25
+
26
+ Analysis of 347 logged bypass events shows:
27
+
28
+ | Category | Count | Description |
29
+ | --------------------- | ----- | ----------------------------------------------- |
30
+ | Release operations | ~45 | Pushing version tags, npm releases |
31
+ | Infrastructure repair | ~100 | wu:claim auto-repair, micro-worktree recovery |
32
+ | State sync | ~80 | Syncing repair commits, pushing orphan repairs |
33
+ | Emergency fixes | ~30 | P0 fixes, backlog corruption recovery |
34
+ | No reason provided | ~90 | Human operations without LUMENFLOW_FORCE_REASON |
35
+
36
+ ### Log Entry Patterns
37
+
38
+ **Legitimate human operations:**
39
+
40
+ ```
41
+ {{DATE}}T14:08:55.172Z | pre-push | Tom | main | release v1.6.0 | {{PROJECT_ROOT}}
42
+ {{DATE}}T10:41:23.185Z | pre-push | Tom | main | Recovery: wu:done partially completed, merging remaining changes
43
+ ```
44
+
45
+ **Missing reason (human oversight, not agent misuse):**
46
+
47
+ ```
48
+ {{DATE}}T11:52:15.459Z | pre-commit | Tom | main | (no reason provided)
49
+ ```
50
+
51
+ ### Why Agents Are Not The Problem
52
+
53
+ 1. **Agents follow documented rules:** The constraints.md and agent-safety-card.md clearly state that agents MUST NOT use LUMENFLOW_FORCE without explicit user approval.
54
+
55
+ 2. **Hooks block direct commits:** The pre-commit hook blocks WU commits from main, forcing agents through the proper worktree workflow.
56
+
57
+ 3. **Most bypasses are push operations:** The audit log shows ~70% of bypasses are `pre-push` hooks, which are typically administrative operations (releases, repairs) performed by humans.
58
+
59
+ 4. **No evidence of agent abuse:** None of the logged entries indicate an AI agent autonomously using LUMENFLOW_FORCE to skip tests or avoid gates.
60
+
61
+ ---
62
+
63
+ ## Current Safeguards
64
+
65
+ ### Documentation Safeguards
66
+
67
+ 1. **constraints.md** (Section 7): "AI agents MUST NOT use LUMENFLOW_FORCE without explicit user approval"
68
+
69
+ 2. **agent-safety-card.md**: Complete section on "Emergency Override (LUMENFLOW_FORCE)" with:
70
+ - When emergency override is appropriate
71
+ - When NOT to use emergency override
72
+ - Step-by-step escalation process
73
+ - Audit trail requirements
74
+
75
+ 3. **starting-prompt.md** (Rule 5): Explicit guidance on LUMENFLOW_FORCE usage
76
+
77
+ ### Technical Safeguards
78
+
79
+ 1. **Audit logging:** All bypasses logged to `.beacon/force-bypasses.log` with timestamp, hook, user, branch, reason, and working directory.
80
+
81
+ 2. **Warning when no reason:** If LUMENFLOW_FORCE_REASON is not provided, a warning is printed.
82
+
83
+ 3. **Git-tracked audit log:** The `.beacon/force-bypasses.log` file is version controlled, providing historical accountability.
84
+
85
+ 4. **Hook enforcement:** Pre-commit, commit-msg, pre-push, and prepare-commit-msg hooks all check for LUMENFLOW_FORCE before allowing bypass.
86
+
87
+ ---
88
+
89
+ ## Investigation Conclusion
90
+
91
+ **The original concern ("agent used LUMENFLOW_FORCE to commit directly to main instead of using proper worktree workflow") appears to be unfounded based on audit log analysis.**
92
+
93
+ The audit log shows:
94
+
95
+ - All 347 bypass events were attributed to "Tom" (human operator)
96
+ - No entries indicate AI agent autonomous bypass
97
+ - Legitimate use cases: releases, repairs, emergency fixes, state sync
98
+
99
+ If an agent did use LUMENFLOW_FORCE improperly, it would have been:
100
+
101
+ 1. Logged with the agent's session context
102
+ 2. Visible as a pattern of non-administrative bypasses
103
+ 3. Associated with test skipping or gate avoidance
104
+
105
+ None of these patterns appear in the audit log.
106
+
107
+ ---
108
+
109
+ ## Prevention Recommendations
110
+
111
+ Despite the finding that this is not currently a problem, the following recommendations strengthen the existing safeguards:
112
+
113
+ ### 1. Enhanced Audit Log Format (Low Effort)
114
+
115
+ Add agent/session identification to bypass log entries:
116
+
117
+ ```
118
+ # Current format:
119
+ TIMESTAMP | HOOK | USER | BRANCH | REASON | CWD
120
+
121
+ # Enhanced format:
122
+ TIMESTAMP | HOOK | USER | BRANCH | REASON | CWD | SESSION_TYPE | SESSION_ID
123
+ ```
124
+
125
+ Where `SESSION_TYPE` could be: `human`, `claude-code`, `cursor`, `windsurf`, `unknown`
126
+
127
+ ### 2. Periodic Audit Review (Process)
128
+
129
+ Establish a monthly review of `.beacon/force-bypasses.log` to identify:
130
+
131
+ - High volume of "no reason provided" entries
132
+ - Unexpected patterns in bypass usage
133
+ - Any entries that don't match expected administrative operations
134
+
135
+ ### 3. Agent Context Marker (Technical)
136
+
137
+ When an agent uses LUMENFLOW_FORCE with approval, require the reason to include an agent marker:
138
+
139
+ ```bash
140
+ # Require format for agent-initiated bypasses
141
+ LUMENFLOW_FORCE_REASON="agent-approved: <reason>" LUMENFLOW_FORCE=1 git ...
142
+ ```
143
+
144
+ This allows filtering agent bypasses from human bypasses in audit analysis.
145
+
146
+ ### 4. Real-Time Alert (Optional, Higher Effort)
147
+
148
+ Add optional webhook/notification when LUMENFLOW_FORCE is used without a reason containing "release", "repair", "recovery", or "sync":
149
+
150
+ ```yaml
151
+ # .lumenflow.config.yaml
152
+ force_bypass:
153
+ alert_webhook: https://...
154
+ exempt_patterns:
155
+ - release
156
+ - repair
157
+ - recovery
158
+ - sync
159
+ - tag
160
+ ```
161
+
162
+ ---
163
+
164
+ ## Summary
165
+
166
+ | Finding | Status |
167
+ | ---------------------------------- | ------------------------------ |
168
+ | AI agents misusing LUMENFLOW_FORCE | **Not observed** |
169
+ | Human administrative use | Working as designed |
170
+ | Audit trail completeness | Good, but ~26% missing reasons |
171
+ | Documentation coverage | Comprehensive |
172
+ | Technical enforcement | Effective |
173
+
174
+ **Conclusion:** The existing LUMENFLOW_FORCE mechanism and its safeguards are functioning correctly. The concern that prompted this investigation was not validated by audit log evidence. The recommendations above are incremental improvements, not urgent fixes.
175
+
176
+ ---
177
+
178
+ ## Related Documents
179
+
180
+ - [.lumenflow/constraints.md](../../../../../../.lumenflow/constraints.md) - Section 7: Agent LUMENFLOW_FORCE Usage Policy
181
+ - [agent-safety-card.md](agent-safety-card.md) - Emergency Override section
182
+ - [starting-prompt.md](starting-prompt.md) - Rule 5: Know When to Use LUMENFLOW_FORCE
183
+ - [WU-1070](../../../../tasks/wu/WU-1070.yaml) - Original WU for LUMENFLOW_FORCE policy
@@ -4,32 +4,15 @@
4
4
 
5
5
  Complete reference for all CLI commands. Organized by category for quick discovery.
6
6
 
7
- ---
8
-
9
- ## Quick Start (Essential Commands)
10
-
11
- Most common workflow in 4 commands:
12
-
13
- ```bash
14
- # 1. Claim WU and create isolated workspace
15
- pnpm wu:claim --id WU-XXX --lane "Lane Name"
16
- cd worktrees/<lane>-wu-xxx
17
-
18
- # 2. Work in worktree, then run gates
19
- pnpm gates # For code changes
20
- pnpm gates --docs-only # For documentation only
21
-
22
- # 3. Prepare for completion (from worktree)
23
- pnpm wu:prep --id WU-XXX
24
-
25
- # 4. Complete (from main - copy command from wu:prep output)
26
- cd /path/to/main && pnpm wu:done --id WU-XXX
27
- ```
28
-
29
- **Key rules:**
30
- - Always work in worktrees, never on main
31
- - Always run `wu:done` to complete (not just documenting it)
32
- - Use `wu:prep` first (runs gates), then `wu:done` (merges)
7
+ > **Tip (WU-1358):** For complete option lists, always run `<package_manager> <command> --help`.
8
+ > This shows all available flags including inline options that may not appear in generated docs.
9
+ >
10
+ > ```bash
11
+ > # Examples
12
+ > pnpm wu:edit --help # See all wu:edit options
13
+ > npm run wu:claim -- --help
14
+ > yarn wu:create --help
15
+ > ```
33
16
 
34
17
  ---
35
18
 
@@ -37,19 +20,21 @@ cd /path/to/main && pnpm wu:done --id WU-XXX
37
20
 
38
21
  **For this monorepo (development):**
39
22
 
40
- | Command | Description |
41
- | ------------------------ | --------------------------------------- |
42
- | `pnpm setup` | Install deps and build CLI (first time) |
43
- | `pnpm build` | Build all packages |
44
- | `pnpm build:dist` | Build distribution packages |
45
- | `pnpm dev` | Start development mode |
46
- | `pnpm clean` | Clean build artifacts and caches |
47
- | `pnpm pack:all` | Pack all packages for distribution |
48
- | `pnpm lumenflow:init` | Scaffold LumenFlow in a project |
49
- | `pnpm docs:sync` | Sync agent docs (for upgrades) |
50
- | `pnpm sync:templates` | Sync templates to project |
51
- | `pnpm lumenflow:upgrade` | Upgrade LumenFlow packages |
52
- | `pnpm lumenflow:doctor` | Diagnose LumenFlow configuration |
23
+ | Command | Description |
24
+ | -------------------------- | --------------------------------------- |
25
+ | `pnpm setup` | Install deps and build CLI (first time) |
26
+ | `pnpm build` | Build all packages |
27
+ | `pnpm build:dist` | Build distribution packages |
28
+ | `pnpm dev` | Start development mode |
29
+ | `pnpm clean` | Clean build artifacts and caches |
30
+ | `pnpm pack:all` | Pack all packages for distribution |
31
+ | `pnpm lumenflow:init` | Scaffold LumenFlow in a project |
32
+ | `pnpm docs:sync` | Sync agent docs (for upgrades) |
33
+ | `pnpm sync:templates` | Sync templates to project |
34
+ | `pnpm lumenflow:upgrade` | Upgrade LumenFlow packages |
35
+ | `pnpm lumenflow:doctor` | Diagnose LumenFlow configuration |
36
+ | `pnpm lumenflow:integrate` | Generate enforcement hooks for client |
37
+ | `pnpm lumenflow commands` | List all available CLI commands |
53
38
 
54
39
  **For external projects (end users):**
55
40
 
@@ -120,22 +105,23 @@ pnpm exec lumenflow --client all # All clients
120
105
 
121
106
  ## Memory & Sessions
122
107
 
123
- | Command | Description |
124
- | ----------------------------------- | ---------------------------------- |
125
- | `pnpm mem:init --wu WU-XXX` | Initialize memory for WU |
126
- | `pnpm mem:start --wu WU-XXX` | Start a memory session |
127
- | `pnpm mem:checkpoint --wu WU-XXX` | Save progress checkpoint |
128
- | `pnpm mem:ready --wu WU-XXX` | Check pending nodes |
129
- | `pnpm mem:export --wu WU-XXX` | Export memory as markdown |
130
- | `pnpm mem:create "msg" --wu WU-XXX` | Create memory node (bug discovery) |
131
- | `pnpm mem:signal "msg" --wu WU-XXX` | Broadcast coordination signal |
132
- | `pnpm mem:inbox --wu WU-XXX` | Check coordination signals |
133
- | `pnpm mem:summarize --wu WU-XXX` | Summarize memory context |
134
- | `pnpm mem:triage --wu WU-XXX` | Triage discovered bugs |
135
- | `pnpm mem:context --wu WU-XXX` | Get context for current lane/WU |
136
- | `pnpm mem:context ... --lane <L>` | Filter context by lane (WU-1292) |
137
- | `pnpm mem:delete --id <node-id>` | Delete/archive a memory node |
138
- | `pnpm mem:cleanup` | Clean up stale memory data |
108
+ | Command | Description |
109
+ | ----------------------------------- | ----------------------------------- |
110
+ | `pnpm mem:init --wu WU-XXX` | Initialize memory for WU |
111
+ | `pnpm mem:start --wu WU-XXX` | Start a memory session |
112
+ | `pnpm mem:checkpoint --wu WU-XXX` | Save progress checkpoint |
113
+ | `pnpm mem:recover --wu WU-XXX` | Generate recovery context (WU-1390) |
114
+ | `pnpm mem:ready --wu WU-XXX` | Check pending nodes |
115
+ | `pnpm mem:export --wu WU-XXX` | Export memory as markdown |
116
+ | `pnpm mem:create "msg" --wu WU-XXX` | Create memory node (bug discovery) |
117
+ | `pnpm mem:signal "msg" --wu WU-XXX` | Broadcast coordination signal |
118
+ | `pnpm mem:inbox --wu WU-XXX` | Check coordination signals |
119
+ | `pnpm mem:summarize --wu WU-XXX` | Summarize memory context |
120
+ | `pnpm mem:triage --wu WU-XXX` | Triage discovered bugs |
121
+ | `pnpm mem:context --wu WU-XXX` | Get context for current lane/WU |
122
+ | `pnpm mem:context ... --lane <L>` | Filter context by lane (WU-1292) |
123
+ | `pnpm mem:delete --id <node-id>` | Delete/archive a memory node |
124
+ | `pnpm mem:cleanup` | Clean up stale memory data |
139
125
 
140
126
  ---
141
127
 
@@ -444,3 +430,30 @@ pnpm mem:inbox --since 30m # Check for signals (NOT TaskOutput)
444
430
  # Capture bug, don't fix out-of-scope
445
431
  pnpm mem:create 'Bug: description' --type discovery --tags bug --wu WU-XXX
446
432
  ```
433
+
434
+ ### Enforcement Hooks (WU-1367)
435
+
436
+ Configure hooks that enforce workflow compliance for Claude Code:
437
+
438
+ ```yaml
439
+ # In .lumenflow.config.yaml
440
+ agents:
441
+ clients:
442
+ claude-code:
443
+ enforcement:
444
+ hooks: true
445
+ block_outside_worktree: true
446
+ require_wu_for_edits: true
447
+ warn_on_stop_without_wu_done: true
448
+ ```
449
+
450
+ ```bash
451
+ # Generate hooks after configuration
452
+ pnpm lumenflow:integrate --client claude-code
453
+ ```
454
+
455
+ Hooks provide automatic enforcement at the tool level:
456
+
457
+ - **block_outside_worktree**: Blocks Write/Edit to main when worktrees exist
458
+ - **require_wu_for_edits**: Requires a claimed WU for Write/Edit operations
459
+ - **warn_on_stop_without_wu_done**: Warns when session ends with active worktrees
@@ -30,10 +30,11 @@ pnpm release --release-version 1.3.0
30
30
 
31
31
  1. Validates semver version format
32
32
  2. Ensures clean working directory on main branch
33
- 3. Bumps all `@lumenflow/*` package versions using micro-worktree isolation
34
- 4. Builds all packages
35
- 5. Creates and pushes git tag `vX.Y.Z`
36
- 6. Publishes to npm
33
+ 3. Syncs templates with source docs (`pnpm sync:templates`)
34
+ 4. Bumps all `@lumenflow/*` package versions using micro-worktree isolation
35
+ 5. Builds all packages
36
+ 6. Creates and pushes git tag `vX.Y.Z`
37
+ 7. Publishes to npm
37
38
 
38
39
  ### Options
39
40
 
@@ -73,6 +74,58 @@ Get a token at: https://www.npmjs.com/settings/tokens
73
74
 
74
75
  ---
75
76
 
77
+ ## Template Synchronization (WU-1353)
78
+
79
+ CLI templates (`packages/@lumenflow/cli/templates/`) are synced from source docs to ensure new projects get up-to-date onboarding content.
80
+
81
+ ### Sync Templates
82
+
83
+ ```bash
84
+ # Sync source docs to CLI templates
85
+ pnpm sync:templates
86
+
87
+ # Preview without writing files
88
+ pnpm sync:templates --dry-run
89
+ ```
90
+
91
+ ### Check for Drift (CI)
92
+
93
+ ```bash
94
+ # Check if templates are out of sync with source
95
+ pnpm sync:templates --check-drift
96
+ ```
97
+
98
+ The `--check-drift` flag compares templates with their source files. If drift is detected:
99
+
100
+ - Exit code 1 (fails CI)
101
+ - Lists drifting files
102
+ - Suggests running `pnpm sync:templates`
103
+
104
+ ### What Gets Synced
105
+
106
+ | Source | Template |
107
+ | -------------------------------- | ------------------------------------------------------------- |
108
+ | `.lumenflow/constraints.md` | `templates/core/.lumenflow/constraints.md.template` |
109
+ | `LUMENFLOW.md` | `templates/core/LUMENFLOW.md.template` |
110
+ | `docs/.../agent/onboarding/*.md` | `templates/core/ai/onboarding/*.md.template` |
111
+ | `.claude/skills/*/SKILL.md` | `templates/vendors/claude/.claude/skills/*/SKILL.md.template` |
112
+
113
+ ### Template Variables
114
+
115
+ During sync, content is transformed:
116
+
117
+ - `YYYY-MM-DD` dates become `{{DATE}}`
118
+ - Absolute paths become `{{PROJECT_ROOT}}` (when applicable)
119
+
120
+ ### When to Sync
121
+
122
+ - Before every release (included in release checklist)
123
+ - After updating source onboarding docs
124
+ - After modifying constraints or workflow rules
125
+ - CI drift check runs on every push to main
126
+
127
+ ---
128
+
76
129
  ## Version Bumping (Manual)
77
130
 
78
131
  If you need to bump versions manually without the release command:
@@ -241,6 +294,7 @@ The `apps/github-app/package.json` must have `"private": true` to prevent npm pu
241
294
  - [ ] All acceptance criteria met
242
295
  - [ ] Gates pass (`pnpm gates`)
243
296
  - [ ] Pre-release checks pass (`pnpm pre-release:check`)
297
+ - [ ] Templates synced (`pnpm sync:templates` - ensures CLI templates match source docs)
244
298
  - [ ] CHANGELOG updated (if maintained)
245
299
 
246
300
  ### Release Steps (Automated)
@@ -6,11 +6,56 @@ This is the complete onboarding document for AI agents working with LumenFlow. R
6
6
 
7
7
  ---
8
8
 
9
+ ## When Starting From Product Vision
10
+
11
+ If you are starting a new project or feature from a product vision (e.g., "Build a task management app"), **do NOT create standalone WUs immediately**. Instead, follow the initiative-first workflow:
12
+
13
+ ### 4-Step Initiative Workflow
14
+
15
+ 1. **Create an Initiative**: Capture the vision as an initiative
16
+
17
+ ```bash
18
+ pnpm initiative:create --id INIT-001 --title "Task Management App" \
19
+ --description "Build a task management application with..." \
20
+ --phase "Phase 1: Core MVP" --phase "Phase 2: Collaboration"
21
+ ```
22
+
23
+ 2. **Define Phases**: Break the vision into logical phases (MVP, iteration, polish)
24
+
25
+ 3. **Create WUs under the Initiative**: Each WU belongs to a phase
26
+
27
+ ```bash
28
+ pnpm wu:create --lane "Core: Platform" --title "Add task model" \
29
+ --description "..." --acceptance "..." --code-paths "..." \
30
+ && pnpm initiative:add-wu --initiative INIT-001 --wu WU-XXX --phase 1
31
+ ```
32
+
33
+ 4. **Track Progress**: Use `pnpm initiative:status --id INIT-001` to see overall progress
34
+
35
+ ### Why Initiatives Matter
36
+
37
+ - **Avoid orphan WUs**: Without initiative structure, agents create disconnected WUs that lack coherent scope
38
+ - **Better coordination**: Phases enable parallel work across lanes
39
+ - **Clear completion criteria**: The initiative tracks when all phases are done
40
+ - **Visibility**: Stakeholders can see multi-phase progress
41
+
42
+ ### When to Skip Initiatives
43
+
44
+ Only skip initiatives for:
45
+
46
+ - Single-file bug fixes
47
+ - Small documentation updates
48
+ - Isolated refactoring tasks
49
+
50
+ If work spans multiple WUs or multiple days, create an initiative first.
51
+
52
+ ---
53
+
9
54
  ## Quick Start (Copy This)
10
55
 
11
56
  ```bash
12
57
  # 1. Check your assigned WU
13
- cat {{DOCS_TASKS_PATH}}/wu/WU-XXXX.yaml
58
+ cat docs/04-operations/tasks/wu/WU-XXXX.yaml
14
59
 
15
60
  # 2. Claim the WU (creates isolated worktree)
16
61
  pnpm wu:claim --id WU-XXXX --lane "Lane Name"
@@ -160,7 +205,7 @@ git add . && git commit -m "your message"
160
205
  **Fix:** Regenerate the backlog or manually add the missing WU:
161
206
 
162
207
  ```bash
163
- # In worktree, edit {{DOCS_TASKS_PATH}}/backlog.md
208
+ # In worktree, edit docs/04-operations/tasks/backlog.md
164
209
  # Add the missing WU reference in the appropriate section
165
210
  ```
166
211
 
@@ -254,6 +299,7 @@ pnpm wu:spawn --id WU-XXXX --client <client-type>
254
299
  | ----------------------------------------- | --------------------------------- | --------------------- |
255
300
  | `pnpm wu:status --id WU-XXX` | Show WU state and valid commands | Check current state |
256
301
  | `pnpm wu:claim --id WU-XXX --lane "Lane"` | Claim WU and create worktree | Start working |
302
+ | `pnpm wu:edit --id WU-XXX --field value` | Edit WU spec fields | Update notes/desc |
257
303
  | `pnpm wu:spawn --id WU-XXX --client X` | Spawn sub-agent for parallel work | Complex WUs |
258
304
  | `pnpm gates` | Run quality gates | Before wu:done |
259
305
  | `pnpm gates --docs-only` | Run docs-only gates | For documentation WUs |
@@ -266,7 +312,7 @@ pnpm wu:spawn --id WU-XXXX --client <client-type>
266
312
 
267
313
  ```
268
314
  /path/to/repo/
269
- ├── {{DOCS_TASKS_PATH}}/
315
+ ├── docs/04-operations/tasks/
270
316
  │ ├── backlog.md # All WUs listed here
271
317
  │ └── wu/WU-XXXX.yaml # Individual WU specs
272
318
  ├── worktrees/
@@ -310,6 +356,24 @@ Before reporting a WU complete, verify:
310
356
  2. **Read error messages:** They usually include fix commands
311
357
  3. **Check gate logs:** `.logs/gates-*.log` in worktree
312
358
  4. **Recovery command:** `pnpm wu:recover --id WU-XXX`
359
+ 5. **Use --help for full options:** `<package_manager> <command> --help`
360
+
361
+ ### Rule: Always Check --help for Full Options (WU-1358)
362
+
363
+ CLI documentation may not include all available options. Before using a command, **always run `--help`** to see the complete list:
364
+
365
+ ```bash
366
+ # Examples (substitute your package manager)
367
+ pnpm wu:edit --help
368
+ npm run wu:claim -- --help
369
+ yarn wu:create --help
370
+ ```
371
+
372
+ This ensures you see:
373
+
374
+ - All available flags (including inline options not in generated docs)
375
+ - Required vs optional parameters
376
+ - Default values and descriptions
313
377
 
314
378
  ---
315
379