@thierrynakoa/fire-flow 10.0.0 → 12.2.0
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.
- package/.claude-plugin/plugin.json +9 -9
- package/ARCHITECTURE-DIAGRAM.md +7 -4
- package/COMMAND-REFERENCE.md +33 -13
- package/DOMINION-FLOW-OVERVIEW.md +581 -421
- package/QUICK-START.md +3 -3
- package/README.md +102 -45
- package/TROUBLESHOOTING.md +264 -264
- package/agents/fire-executor.md +200 -116
- package/agents/fire-fact-checker.md +276 -276
- package/agents/fire-phoenix-analyst.md +394 -0
- package/agents/fire-planner.md +145 -53
- package/agents/fire-project-researcher.md +155 -155
- package/agents/fire-research-synthesizer.md +166 -166
- package/agents/fire-researcher.md +144 -59
- package/agents/fire-roadmapper.md +215 -203
- package/agents/fire-verifier.md +247 -65
- package/agents/fire-vision-architect.md +381 -0
- package/commands/fire-0-orient.md +476 -476
- package/commands/fire-1a-new.md +216 -0
- package/commands/fire-1b-research.md +210 -0
- package/commands/fire-1c-setup.md +254 -0
- package/commands/{fire-1a-discuss.md → fire-1d-discuss.md} +35 -7
- package/commands/fire-3-execute.md +55 -2
- package/commands/fire-4-verify.md +61 -0
- package/commands/fire-5-handoff.md +2 -2
- package/commands/fire-6-resume.md +37 -2
- package/commands/fire-add-new-skill.md +2 -2
- package/commands/fire-autonomous.md +20 -3
- package/commands/fire-brainstorm.md +1 -1
- package/commands/fire-complete-milestone.md +2 -2
- package/commands/fire-cost.md +183 -0
- package/commands/fire-dashboard.md +2 -2
- package/commands/fire-debug.md +663 -663
- package/commands/fire-loop-resume.md +2 -2
- package/commands/fire-loop-stop.md +1 -1
- package/commands/fire-loop.md +1168 -1168
- package/commands/fire-map-codebase.md +3 -3
- package/commands/fire-new-milestone.md +356 -356
- package/commands/fire-phoenix.md +603 -0
- package/commands/fire-reflect.md +235 -235
- package/commands/fire-research.md +246 -246
- package/commands/fire-search.md +1 -1
- package/commands/fire-skills-diff.md +3 -3
- package/commands/fire-skills-history.md +3 -3
- package/commands/fire-skills-rollback.md +7 -7
- package/commands/fire-skills-sync.md +5 -5
- package/commands/fire-test.md +9 -9
- package/commands/fire-todos.md +1 -1
- package/commands/fire-update.md +5 -5
- package/hooks/hooks.json +16 -16
- package/hooks/run-hook.sh +8 -8
- package/hooks/run-session-end.sh +7 -7
- package/hooks/session-end.sh +90 -90
- package/hooks/session-start.sh +1 -1
- package/package.json +2 -2
- package/plugin.json +7 -7
- package/references/metrics-and-trends.md +1 -1
- package/skills-library/SKILLS-INDEX.md +588 -588
- package/skills-library/_general/methodology/AUTONOMOUS_ORCHESTRATION.md +182 -0
- package/skills-library/_general/methodology/BACKWARD_PLANNING_INTERVIEW.md +307 -0
- package/skills-library/_general/methodology/CIRCUIT_BREAKER_INTELLIGENCE.md +163 -0
- package/skills-library/_general/methodology/CONTEXT_ROTATION.md +151 -0
- package/skills-library/_general/methodology/DEAD_ENDS_SHELF.md +188 -0
- package/skills-library/_general/methodology/DESIGN_PHILOSOPHY_ENFORCEMENT.md +152 -0
- package/skills-library/_general/methodology/INTERNAL_CONSISTENCY_AUDIT.md +212 -0
- package/skills-library/_general/methodology/LIVE_BREADCRUMB_PROTOCOL.md +242 -0
- package/skills-library/_general/methodology/PHOENIX_REBUILD_METHODOLOGY.md +251 -0
- package/skills-library/_general/methodology/QUALITY_GATES_AND_VERIFICATION.md +157 -0
- package/skills-library/_general/methodology/RELIABILITY_PREDICTION.md +104 -0
- package/skills-library/_general/methodology/REQUIREMENTS_DECOMPOSITION.md +155 -0
- package/skills-library/_general/methodology/SELF_TESTING_FEEDBACK_LOOP.md +143 -0
- package/skills-library/_general/methodology/STACK_COMPATIBILITY_MATRIX.md +178 -0
- package/skills-library/_general/methodology/TIERED_CONTEXT_ARCHITECTURE.md +118 -0
- package/skills-library/_general/methodology/ZERO_FRICTION_CLI_SETUP.md +312 -0
- package/skills-library/_general/methodology/autonomous-multi-phase-build.md +133 -0
- package/skills-library/_general/methodology/claude-md-archival.md +280 -0
- package/skills-library/_general/methodology/debug-swarm-researcher-escape-hatch.md +240 -240
- package/skills-library/_general/methodology/git-worktrees-parallel.md +232 -0
- package/skills-library/_general/methodology/llm-judge-memory-crud.md +241 -0
- package/skills-library/_general/methodology/multi-project-autonomous-build.md +360 -0
- package/skills-library/_general/methodology/shell-autonomous-loop-fixplan.md +238 -238
- package/skills-library/_general/patterns-standards/GOF_DESIGN_PATTERNS_FOR_AI_AGENTS.md +358 -0
- package/skills-library/methodology/BREATH_BASED_PARALLEL_EXECUTION.md +1 -1
- package/skills-library/methodology/RESEARCH_BACKED_WORKFLOW_UPGRADE.md +1 -1
- package/skills-library/methodology/SABBATH_REST_PATTERN.md +1 -1
- package/templates/ASSUMPTIONS.md +1 -1
- package/templates/BLOCKERS.md +1 -1
- package/templates/DECISION_LOG.md +1 -1
- package/templates/phase-prompt.md +1 -1
- package/templates/phoenix-comparison.md +80 -0
- package/version.json +2 -2
- package/workflows/handoff-session.md +1 -1
- package/workflows/new-project.md +2 -2
- package/commands/fire-1-new.md +0 -281
|
@@ -0,0 +1,216 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Initialize a new project with Dominion Flow (Dominion Flow)
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
# /fire-1a-new
|
|
6
|
+
|
|
7
|
+
> Initialize a new project — scaffold directory, gather requirements, create .planning/ structure
|
|
8
|
+
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
## Purpose
|
|
12
|
+
|
|
13
|
+
Create the project foundation: directory, requirements gathering, and the complete `.planning/` file structure. This is Step 1 of 3 in project initialization.
|
|
14
|
+
|
|
15
|
+
**Flow:** `/fire-1a-new` → `/fire-1b-research` → `/fire-1c-setup`
|
|
16
|
+
|
|
17
|
+
---
|
|
18
|
+
|
|
19
|
+
## Arguments
|
|
20
|
+
|
|
21
|
+
```yaml
|
|
22
|
+
arguments: none
|
|
23
|
+
optional_flags:
|
|
24
|
+
--name: "Project name (will prompt if not provided)"
|
|
25
|
+
--path: "Project path (defaults to current directory)"
|
|
26
|
+
--minimal: "Skip adaptive questioning, use defaults"
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
---
|
|
30
|
+
|
|
31
|
+
## EXECUTION ORDER
|
|
32
|
+
|
|
33
|
+
```
|
|
34
|
+
STEP 1: Environment Validation → create NEW project directory
|
|
35
|
+
STEP 2: Gather Requirements → MODE GATE question, backward interview if needed
|
|
36
|
+
STEP 3: Create .planning/ → mkdir + touch ALL files (EXACT names, no renaming)
|
|
37
|
+
FINAL: Chain to next command → tell user to run /fire-1b-research
|
|
38
|
+
```
|
|
39
|
+
|
|
40
|
+
**Complete each step before starting the next. No skipping.**
|
|
41
|
+
|
|
42
|
+
---
|
|
43
|
+
|
|
44
|
+
## Step 1: Environment Validation
|
|
45
|
+
|
|
46
|
+
```
|
|
47
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
48
|
+
DOMINION FLOW > PROJECT INITIALIZATION
|
|
49
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
1. **Create a NEW project directory** — Do NOT initialize inside an existing project. If the current directory has source code, `package.json`, or `.planning/`, create a new directory:
|
|
53
|
+
```bash
|
|
54
|
+
mkdir -p {project-path}/{project-name}
|
|
55
|
+
cd {project-path}/{project-name}
|
|
56
|
+
git init
|
|
57
|
+
```
|
|
58
|
+
Use `--path` flag if provided, otherwise ask the user or derive from project name.
|
|
59
|
+
2. Check if `.planning/` already exists (warn if so — means project was already initialized)
|
|
60
|
+
3. Verify write permissions
|
|
61
|
+
4. Create git repo if not present
|
|
62
|
+
|
|
63
|
+
---
|
|
64
|
+
|
|
65
|
+
## Step 2: Gather Requirements
|
|
66
|
+
|
|
67
|
+
**Core Questions:**
|
|
68
|
+
1. What is this project? (one sentence)
|
|
69
|
+
2. Who is the primary user?
|
|
70
|
+
3. What is the core value it provides?
|
|
71
|
+
4. What are the non-negotiable features (must-haves)?
|
|
72
|
+
|
|
73
|
+
**The MODE GATE Question:**
|
|
74
|
+
|
|
75
|
+
> **"Have you already started building this, or are we starting from scratch?"**
|
|
76
|
+
|
|
77
|
+
This reveals technical level without asking them to self-assess:
|
|
78
|
+
|
|
79
|
+
| Answer | Mode |
|
|
80
|
+
|--------|------|
|
|
81
|
+
| "I already have a React app with Express backend" | **Forward** — validate their stack |
|
|
82
|
+
| "I started something but I'm stuck" | **Forward** — audit what exists |
|
|
83
|
+
| "Starting from scratch, but I want Python" | **Forward** — build around preference |
|
|
84
|
+
| "Starting from scratch" | **Backward** — derive stack from vision |
|
|
85
|
+
| "I have an idea but don't know where to start" | **Backward** — full interview |
|
|
86
|
+
| "I have a WordPress site and want to add features" | **Forward** — WordPress-aware stack |
|
|
87
|
+
|
|
88
|
+
**If Forward Mode** (user has code or stated tech preferences):
|
|
89
|
+
1. Existing codebases to integrate with?
|
|
90
|
+
2. Known technical constraints?
|
|
91
|
+
3. *(Anti-Frankenstein gate validates choices later in /fire-1b-research)*
|
|
92
|
+
|
|
93
|
+
**If Backward Mode** (user described product, not tech):
|
|
94
|
+
Use the interview protocol from `@skills-library/_general/methodology/BACKWARD_PLANNING_INTERVIEW.md`:
|
|
95
|
+
|
|
96
|
+
0. **Visual Input (ALWAYS ask first)** — "Do you have anything visual — screenshot, wireframe, sketch? Drop it here."
|
|
97
|
+
- If provided: Extract requirements, save to `.planning/research/VISUAL-ANALYSIS.md`, skip questions already answered
|
|
98
|
+
- If not: Proceed to question 1
|
|
99
|
+
1. **The Walkthrough** — "Walk me through a user's first 60 seconds"
|
|
100
|
+
2. **The Money Screen** — "What's the ONE screen where your app delivers the most value?"
|
|
101
|
+
3. **The Similar App** — "Name 1-2 apps that feel closest to yours"
|
|
102
|
+
4. **The Deal-Breakers** — Yes/no: login, payments, uploads, emails, mobile, real-time
|
|
103
|
+
5. **The MVP Gate** — "If you could only ship THREE features, which three?"
|
|
104
|
+
|
|
105
|
+
**Timeline Questions:**
|
|
106
|
+
1. Target completion date?
|
|
107
|
+
2. Critical milestones?
|
|
108
|
+
|
|
109
|
+
**Save outputs:**
|
|
110
|
+
- `.planning/PROJECT.md` — requirements summary
|
|
111
|
+
- `.planning/REQUIREMENTS.md` — REQ-IDs for traceability
|
|
112
|
+
|
|
113
|
+
---
|
|
114
|
+
|
|
115
|
+
## Step 3: Create .planning/ Structure
|
|
116
|
+
|
|
117
|
+
**Create directories:**
|
|
118
|
+
|
|
119
|
+
```bash
|
|
120
|
+
mkdir -p .planning/breadcrumbs .planning/research .planning/phases
|
|
121
|
+
```
|
|
122
|
+
|
|
123
|
+
**Breadcrumbs are ON-DEMAND — do NOT create empty files.** Agents create breadcrumb files when they have something worth recording. The directory exists; the files don't — until earned.
|
|
124
|
+
|
|
125
|
+
When agents write breadcrumbs, they use these EXACT names:
|
|
126
|
+
- `breadcrumbs/LESSONS.md` — Solutions that worked
|
|
127
|
+
- `breadcrumbs/FAILURES.md` — Approaches that failed
|
|
128
|
+
- `breadcrumbs/PATTERNS.md` — Project conventions
|
|
129
|
+
- `breadcrumbs/DEPENDENCIES.md` — Library gotchas
|
|
130
|
+
|
|
131
|
+
> See `@skills-library/_general/methodology/LIVE_BREADCRUMB_PROTOCOL.md` for the full protocol.
|
|
132
|
+
|
|
133
|
+
**Create CONSCIENCE.md** using template from `@templates/state.md`:
|
|
134
|
+
- Project name and core value
|
|
135
|
+
- Current phase: 1 of N (placeholder until ROADMAP.md exists)
|
|
136
|
+
- Status: Ready to research
|
|
137
|
+
- WARRIOR Integration section
|
|
138
|
+
- Session Continuity section
|
|
139
|
+
|
|
140
|
+
**After Step 3, these files MUST exist:**
|
|
141
|
+
|
|
142
|
+
```
|
|
143
|
+
.planning/
|
|
144
|
+
├── PROJECT.md # Step 2
|
|
145
|
+
├── REQUIREMENTS.md # Step 2
|
|
146
|
+
├── CONSCIENCE.md # Step 3
|
|
147
|
+
├── breadcrumbs/ # Step 3 (empty dir — files created on-demand by agents)
|
|
148
|
+
├── research/ # empty, ready for /fire-1b-research
|
|
149
|
+
└── phases/ # empty, ready for /fire-2-plan
|
|
150
|
+
```
|
|
151
|
+
|
|
152
|
+
**Verify before proceeding:**
|
|
153
|
+
```bash
|
|
154
|
+
test -f .planning/PROJECT.md && test -f .planning/REQUIREMENTS.md && test -f .planning/CONSCIENCE.md && test -d .planning/breadcrumbs && echo "ALL FILES PRESENT" || echo "MISSING FILES — go back"
|
|
155
|
+
```
|
|
156
|
+
|
|
157
|
+
---
|
|
158
|
+
|
|
159
|
+
## Completion
|
|
160
|
+
|
|
161
|
+
```
|
|
162
|
+
+==============================================================================+
|
|
163
|
+
| SCAFFOLD COMPLETE |
|
|
164
|
+
|==============================================================================|
|
|
165
|
+
| |
|
|
166
|
+
| Project: {project_name} |
|
|
167
|
+
| Mode: {forward/backward} |
|
|
168
|
+
| Status: Ready to research |
|
|
169
|
+
| |
|
|
170
|
+
| Created: |
|
|
171
|
+
| [x] .planning/PROJECT.md <- requirements |
|
|
172
|
+
| [x] .planning/REQUIREMENTS.md <- REQ-IDs |
|
|
173
|
+
| [x] .planning/CONSCIENCE.md <- project state |
|
|
174
|
+
| [x] .planning/breadcrumbs/ <- on-demand memory (empty until |
|
|
175
|
+
| agents record learnings) |
|
|
176
|
+
| |
|
|
177
|
+
| Pending (created by next commands): |
|
|
178
|
+
| [ ] research/SYNTHESIS.md <- /fire-1b-research |
|
|
179
|
+
| [ ] VISION.md <- /fire-1b-research |
|
|
180
|
+
| [ ] ROADMAP.md <- /fire-1b-research |
|
|
181
|
+
| [ ] TOOLING-LOG.md <- /fire-1c-setup |
|
|
182
|
+
| [ ] WARRIOR handoff <- /fire-1c-setup |
|
|
183
|
+
| |
|
|
184
|
+
|==============================================================================|
|
|
185
|
+
| NEXT UP |
|
|
186
|
+
|------------------------------------------------------------------------------|
|
|
187
|
+
| |
|
|
188
|
+
| -> Run /fire-1b-research to spawn researchers and select architecture |
|
|
189
|
+
| |
|
|
190
|
+
+==============================================================================+
|
|
191
|
+
```
|
|
192
|
+
|
|
193
|
+
---
|
|
194
|
+
|
|
195
|
+
## Error Handling
|
|
196
|
+
|
|
197
|
+
### .planning/ Already Exists
|
|
198
|
+
|
|
199
|
+
```
|
|
200
|
+
╔══════════════════════════════════════════════════════════════════════════════╗
|
|
201
|
+
║ ⚠ WARNING: Existing Project Detected ║
|
|
202
|
+
╠══════════════════════════════════════════════════════════════════════════════╣
|
|
203
|
+
║ Options: ║
|
|
204
|
+
║ A) Use `/fire-6-resume` to continue existing project ║
|
|
205
|
+
║ B) Delete .planning/ and run `/fire-1a-new` again ║
|
|
206
|
+
║ C) Use `--path [new-directory]` to initialize elsewhere ║
|
|
207
|
+
╚══════════════════════════════════════════════════════════════════════════════╝
|
|
208
|
+
```
|
|
209
|
+
|
|
210
|
+
---
|
|
211
|
+
|
|
212
|
+
## References
|
|
213
|
+
|
|
214
|
+
- **Template:** `@templates/state.md` - CONSCIENCE.md template
|
|
215
|
+
- **Skill:** `@skills-library/_general/methodology/BACKWARD_PLANNING_INTERVIEW.md`
|
|
216
|
+
- **Brand:** `@references/ui-brand.md` - Visual output standards
|
|
@@ -0,0 +1,210 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Research, vision selection, and roadmap generation for a new project (Dominion Flow)
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
# /fire-1b-research
|
|
6
|
+
|
|
7
|
+
> Spawn researchers, select architecture vision, generate roadmap
|
|
8
|
+
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
## Purpose
|
|
12
|
+
|
|
13
|
+
Research the technology landscape, select a coherent architecture, and generate the project roadmap. This is Step 2 of 3 in project initialization.
|
|
14
|
+
|
|
15
|
+
**Flow:** `/fire-1a-new` → **`/fire-1b-research`** → `/fire-1c-setup`
|
|
16
|
+
|
|
17
|
+
**Prerequisite:** `.planning/PROJECT.md` and `.planning/REQUIREMENTS.md` must exist (created by `/fire-1a-new`).
|
|
18
|
+
|
|
19
|
+
---
|
|
20
|
+
|
|
21
|
+
## EXECUTION ORDER
|
|
22
|
+
|
|
23
|
+
```
|
|
24
|
+
STEP 1: Validate prerequisites → PROJECT.md + REQUIREMENTS.md exist
|
|
25
|
+
STEP 2: Research Synthesis → spawn researchers, search GitHub, write SYNTHESIS.md
|
|
26
|
+
STEP 3: Vision Branch Selection → spawn fire-vision-architect, user picks branch, LOCK VISION.md
|
|
27
|
+
STEP 4: Roadmap Generation → spawn fire-roadmapper, write ROADMAP.md
|
|
28
|
+
FINAL: Chain to next command → tell user to run /fire-1c-setup
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
**Complete each step before starting the next. Each step produces a file — verify it exists before proceeding.**
|
|
32
|
+
|
|
33
|
+
---
|
|
34
|
+
|
|
35
|
+
## Step 1: Validate Prerequisites
|
|
36
|
+
|
|
37
|
+
```bash
|
|
38
|
+
test -f .planning/PROJECT.md && test -f .planning/REQUIREMENTS.md && echo "READY" || echo "MISSING — run /fire-1a-new first"
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
If files are missing, stop and tell the user to run `/fire-1a-new` first.
|
|
42
|
+
|
|
43
|
+
Read `.planning/PROJECT.md` to determine mode (forward/backward) for Step 3.
|
|
44
|
+
|
|
45
|
+
---
|
|
46
|
+
|
|
47
|
+
## Step 2: Research Synthesis (MANDATORY)
|
|
48
|
+
|
|
49
|
+
**Spawn 4 parallel researchers** (or sequential if resources are limited):
|
|
50
|
+
|
|
51
|
+
| Researcher | Focus | Output |
|
|
52
|
+
|-----------|-------|--------|
|
|
53
|
+
| STACK | Technology ecosystem, versions, compatibility | `research/STACK.md` |
|
|
54
|
+
| FEATURES | Feature implementation patterns, complexity | `research/FEATURES.md` |
|
|
55
|
+
| ARCHITECTURE | Folder structure, data flow, API design | `research/ARCHITECTURE.md` |
|
|
56
|
+
| PITFALLS | Common mistakes, known issues, anti-patterns | `research/PITFALLS.md` |
|
|
57
|
+
|
|
58
|
+
**Every researcher MUST search GitHub for open source reference projects:**
|
|
59
|
+
|
|
60
|
+
Search for 2-3 real open source projects similar to what the user is building:
|
|
61
|
+
- Repo name, stars, last updated
|
|
62
|
+
- Tech stack used
|
|
63
|
+
- Folder structure patterns
|
|
64
|
+
- Key patterns worth adopting
|
|
65
|
+
- Mistakes visible in their issues/PRs
|
|
66
|
+
|
|
67
|
+
**Search strategy:**
|
|
68
|
+
```
|
|
69
|
+
gh search repos "{project type}" --sort stars --limit 5
|
|
70
|
+
gh search repos "{project type} {framework}" --sort updated --limit 5
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
**Then synthesize:** Merge 4 files → `.planning/research/SYNTHESIS.md`
|
|
74
|
+
|
|
75
|
+
Include a "Reference Projects" section listing the best repos found, what to steal, and what to avoid.
|
|
76
|
+
|
|
77
|
+
> The 4-tier cascade: Skills Library → GitHub/Open Source → Context7 → Web search.
|
|
78
|
+
|
|
79
|
+
**If token-constrained:** Run a single researcher covering all 4 areas into one SYNTHESIS.md.
|
|
80
|
+
|
|
81
|
+
**Gate:** SYNTHESIS.md MUST exist before Step 3.
|
|
82
|
+
|
|
83
|
+
```bash
|
|
84
|
+
test -f .planning/research/SYNTHESIS.md && echo "SYNTHESIS READY" || echo "MISSING — complete research first"
|
|
85
|
+
```
|
|
86
|
+
|
|
87
|
+
---
|
|
88
|
+
|
|
89
|
+
## Step 3: Vision Branch Selection
|
|
90
|
+
|
|
91
|
+
**Spawn `fire-vision-architect`** with:
|
|
92
|
+
- `.planning/research/SYNTHESIS.md`
|
|
93
|
+
- `.planning/PROJECT.md`
|
|
94
|
+
- Any visual input from Step 2 of `/fire-1a-new`
|
|
95
|
+
|
|
96
|
+
**Two modes (auto-detected):**
|
|
97
|
+
|
|
98
|
+
**Forward Mode** — User stated a tech stack → Anti-Frankenstein gate checks compatibility → generate branches.
|
|
99
|
+
|
|
100
|
+
**Backward Planning Mode** — User described the PRODUCT, not tech:
|
|
101
|
+
```
|
|
102
|
+
Visual input → capability extraction
|
|
103
|
+
+ What does the finished product do?
|
|
104
|
+
→ What capabilities does that require?
|
|
105
|
+
→ What proven stacks deliver those? → branches
|
|
106
|
+
```
|
|
107
|
+
|
|
108
|
+
**Process:**
|
|
109
|
+
|
|
110
|
+
1. Mode detection from PROJECT.md
|
|
111
|
+
2. Anti-Frankenstein Gate (forward) or Capability Extraction (backward)
|
|
112
|
+
3. Generate 2-3 vision branches (often 2 in backward mode)
|
|
113
|
+
4. Display via `AskUserQuestion` — one marked "(Recommended)"
|
|
114
|
+
5. User picks one
|
|
115
|
+
6. **Lock selected branch as `.planning/VISION.md`**
|
|
116
|
+
7. **Save rejected branches to `.planning/research/ALTERNATIVES.md`**
|
|
117
|
+
|
|
118
|
+
**Gate:** VISION.md MUST exist and be LOCKED before Step 4.
|
|
119
|
+
|
|
120
|
+
```bash
|
|
121
|
+
test -f .planning/VISION.md && test -f .planning/research/ALTERNATIVES.md && echo "VISION LOCKED" || echo "MISSING — complete vision selection"
|
|
122
|
+
```
|
|
123
|
+
|
|
124
|
+
---
|
|
125
|
+
|
|
126
|
+
## Step 4: Roadmap Generation (MANDATORY)
|
|
127
|
+
|
|
128
|
+
**Spawn `fire-roadmapper`** with locked VISION.md:
|
|
129
|
+
|
|
130
|
+
1. Reads LOCKED `VISION.md` (does NOT make stack decisions)
|
|
131
|
+
2. Reads `REQUIREMENTS.md` for feature list
|
|
132
|
+
3. Groups requirements into phases by dependency order
|
|
133
|
+
4. Derives success criteria goal-backward from each phase objective
|
|
134
|
+
5. Validates 100% requirement coverage (every REQ-ID in a phase)
|
|
135
|
+
6. Writes `.planning/ROADMAP.md`
|
|
136
|
+
|
|
137
|
+
**Gate:** ROADMAP.md MUST exist before completion.
|
|
138
|
+
|
|
139
|
+
```bash
|
|
140
|
+
test -f .planning/ROADMAP.md && echo "ROADMAP READY" || echo "MISSING — complete roadmap generation"
|
|
141
|
+
```
|
|
142
|
+
|
|
143
|
+
> ROADMAP.md is what `/fire-2-plan` reads. Without it, `/fire-2-plan 1` has no Phase 1 definition.
|
|
144
|
+
|
|
145
|
+
---
|
|
146
|
+
|
|
147
|
+
## Agent Spawning Summary
|
|
148
|
+
|
|
149
|
+
| Agent | Input | Output | Step |
|
|
150
|
+
|-------|-------|--------|------|
|
|
151
|
+
| `fire-project-researcher` (x4) | PROJECT.md, REQUIREMENTS.md | research/*.md → SYNTHESIS.md | 2 |
|
|
152
|
+
| `fire-vision-architect` | SYNTHESIS.md, PROJECT.md, visual input | VISION.md, ALTERNATIVES.md | 3 |
|
|
153
|
+
| `fire-roadmapper` | VISION.md (locked), REQUIREMENTS.md | ROADMAP.md | 4 |
|
|
154
|
+
|
|
155
|
+
---
|
|
156
|
+
|
|
157
|
+
## Completion
|
|
158
|
+
|
|
159
|
+
```
|
|
160
|
+
+==============================================================================+
|
|
161
|
+
| RESEARCH & VISION COMPLETE |
|
|
162
|
+
|==============================================================================|
|
|
163
|
+
| |
|
|
164
|
+
| Project: {project_name} |
|
|
165
|
+
| Stack: {locked stack from VISION.md} |
|
|
166
|
+
| Phases: {N} defined in ROADMAP.md |
|
|
167
|
+
| |
|
|
168
|
+
| Created: |
|
|
169
|
+
| [x] .planning/research/SYNTHESIS.md <- merged research + GitHub refs |
|
|
170
|
+
| [x] .planning/VISION.md <- LOCKED architecture |
|
|
171
|
+
| [x] .planning/research/ALTERNATIVES.md <- rejected branches |
|
|
172
|
+
| [x] .planning/ROADMAP.md <- phase breakdown |
|
|
173
|
+
| |
|
|
174
|
+
| Gates Triggered: |
|
|
175
|
+
| [?] Mode Gate -> {forward/backward} |
|
|
176
|
+
| [?] Anti-Frankenstein -> {conflicts found / clean} |
|
|
177
|
+
| [?] Vision Architect -> {N} branches, Branch {X} selected |
|
|
178
|
+
| [?] Vision Lock -> VISION.md marked LOCKED |
|
|
179
|
+
| |
|
|
180
|
+
|==============================================================================|
|
|
181
|
+
| NEXT UP |
|
|
182
|
+
|------------------------------------------------------------------------------|
|
|
183
|
+
| |
|
|
184
|
+
| -> Run /fire-1c-setup to install tooling and finalize initialization |
|
|
185
|
+
| |
|
|
186
|
+
+==============================================================================+
|
|
187
|
+
```
|
|
188
|
+
|
|
189
|
+
---
|
|
190
|
+
|
|
191
|
+
## Error Handling
|
|
192
|
+
|
|
193
|
+
### Missing Prerequisites
|
|
194
|
+
```
|
|
195
|
+
╔══════════════════════════════════════════════════════════════════════════════╗
|
|
196
|
+
║ ✗ ERROR: Run /fire-1a-new first ║
|
|
197
|
+
╠══════════════════════════════════════════════════════════════════════════════╣
|
|
198
|
+
║ Missing: .planning/PROJECT.md or .planning/REQUIREMENTS.md ║
|
|
199
|
+
║ These are created by /fire-1a-new. Run that command first. ║
|
|
200
|
+
╚══════════════════════════════════════════════════════════════════════════════╝
|
|
201
|
+
```
|
|
202
|
+
|
|
203
|
+
---
|
|
204
|
+
|
|
205
|
+
## References
|
|
206
|
+
|
|
207
|
+
- **Agent:** `@agents/fire-project-researcher.md`
|
|
208
|
+
- **Agent:** `@agents/fire-vision-architect.md`
|
|
209
|
+
- **Agent:** `@agents/fire-roadmapper.md`
|
|
210
|
+
- **Skill:** `@skills-library/_general/methodology/STACK_COMPATIBILITY_MATRIX.md`
|
|
@@ -0,0 +1,254 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Install tooling, create handoff, and finalize project initialization (Dominion Flow)
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
# /fire-1c-setup
|
|
6
|
+
|
|
7
|
+
> Install CLI tools, create WARRIOR handoff, verify all files, show completion
|
|
8
|
+
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
## Purpose
|
|
12
|
+
|
|
13
|
+
Finalize project initialization: install all CLI tools the locked stack requires, create the WARRIOR handoff, and verify every file exists. This is Step 3 of 3 in project initialization.
|
|
14
|
+
|
|
15
|
+
**Flow:** `/fire-1a-new` → `/fire-1b-research` → **`/fire-1c-setup`**
|
|
16
|
+
|
|
17
|
+
**Prerequisite:** `.planning/VISION.md` (locked) and `.planning/ROADMAP.md` must exist (created by `/fire-1b-research`).
|
|
18
|
+
|
|
19
|
+
---
|
|
20
|
+
|
|
21
|
+
## EXECUTION ORDER
|
|
22
|
+
|
|
23
|
+
```
|
|
24
|
+
STEP 1: Validate prerequisites → VISION.md + ROADMAP.md exist
|
|
25
|
+
STEP 2: WARRIOR Handoff Init → create handoff file
|
|
26
|
+
STEP 3: Zero-Friction Tooling → install CLIs from VISION.md, write TOOLING-LOG.md
|
|
27
|
+
STEP 4: SKILLS-INDEX.md → create empty tracking file
|
|
28
|
+
STEP 5: Update CONSCIENCE.md → set status to "Ready to plan"
|
|
29
|
+
STEP 6: MANDATORY FILE GATE → verify ALL 16 files exist
|
|
30
|
+
FINAL: Completion Display → show full project summary
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
**Complete each step before starting the next.**
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
## Step 1: Validate Prerequisites
|
|
38
|
+
|
|
39
|
+
```bash
|
|
40
|
+
test -f .planning/VISION.md && test -f .planning/ROADMAP.md && echo "READY" || echo "MISSING — run /fire-1b-research first"
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
If files are missing, stop and tell the user to run `/fire-1b-research` first.
|
|
44
|
+
|
|
45
|
+
---
|
|
46
|
+
|
|
47
|
+
## Step 2: WARRIOR Handoff Init
|
|
48
|
+
|
|
49
|
+
**Create handoff directory if not exists:**
|
|
50
|
+
```bash
|
|
51
|
+
mkdir -p ~/.claude/warrior-handoffs/
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
**Create initial handoff file:**
|
|
55
|
+
```
|
|
56
|
+
~/.claude/warrior-handoffs/{PROJECT_NAME}_YYYY-MM-DD_init.md
|
|
57
|
+
```
|
|
58
|
+
|
|
59
|
+
Include: project name, core value, locked stack, phase count, current status, key decisions made, next steps.
|
|
60
|
+
|
|
61
|
+
---
|
|
62
|
+
|
|
63
|
+
## Step 3: Zero-Friction Tooling (MANDATORY)
|
|
64
|
+
|
|
65
|
+
**Claude auto-installs ALL CLI tools the locked VISION.md stack requires.** The user should never manually install anything.
|
|
66
|
+
|
|
67
|
+
**Read VISION.md and install everything the stack needs.**
|
|
68
|
+
|
|
69
|
+
Reference: `@skills-library/_general/methodology/ZERO_FRICTION_CLI_SETUP.md`
|
|
70
|
+
|
|
71
|
+
**Always install (every web project):**
|
|
72
|
+
```bash
|
|
73
|
+
npm install -D @playwright/test
|
|
74
|
+
npx playwright install chromium firefox
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
> Playwright MCP is the primary visual testing tool for verification.
|
|
78
|
+
|
|
79
|
+
**Install based on VISION.md stack:**
|
|
80
|
+
|
|
81
|
+
| Stack Requirement | CLI Command |
|
|
82
|
+
|------------------|-------------|
|
|
83
|
+
| Supabase | `npx supabase init` then `npx supabase start` |
|
|
84
|
+
| Stripe payments | `npm install stripe @stripe/stripe-js` |
|
|
85
|
+
| Next.js | `npx create-next-app@latest` |
|
|
86
|
+
| Prisma ORM | `npx prisma init` then `npx prisma generate` |
|
|
87
|
+
| Drizzle ORM | `npm install drizzle-orm` + `npm install -D drizzle-kit` |
|
|
88
|
+
| Tailwind CSS | `npm install -D tailwindcss @tailwindcss/vite` |
|
|
89
|
+
| shadcn/ui | `npx shadcn@latest init` |
|
|
90
|
+
| better-auth | `npx @better-auth/cli generate` |
|
|
91
|
+
| Firebase | `npx firebase-tools init` |
|
|
92
|
+
| Docker | `docker compose up -d` (if compose.yml exists) |
|
|
93
|
+
| ESLint + Prettier | `npm install -D eslint prettier eslint-config-prettier` |
|
|
94
|
+
| Husky (git hooks) | `npx husky init` |
|
|
95
|
+
|
|
96
|
+
**Process:**
|
|
97
|
+
1. Read locked VISION.md Technology Stack table
|
|
98
|
+
2. Match each technology to its CLI setup command
|
|
99
|
+
3. Run all installations sequentially (dependencies first)
|
|
100
|
+
4. Verify each tool installed correctly (version check)
|
|
101
|
+
5. Log installed tools to `.planning/TOOLING-LOG.md`
|
|
102
|
+
|
|
103
|
+
**Skip conditions:**
|
|
104
|
+
- Backend-only projects skip Playwright and frontend tools
|
|
105
|
+
- User explicitly opts out of a specific tool
|
|
106
|
+
- Tool already installed (check `package.json` or version command)
|
|
107
|
+
|
|
108
|
+
---
|
|
109
|
+
|
|
110
|
+
## Step 4: SKILLS-INDEX.md
|
|
111
|
+
|
|
112
|
+
```markdown
|
|
113
|
+
# Skills Applied to This Project
|
|
114
|
+
|
|
115
|
+
## Summary
|
|
116
|
+
- Total skills applied: 0
|
|
117
|
+
- Categories used: 0
|
|
118
|
+
- Last skill applied: N/A
|
|
119
|
+
|
|
120
|
+
## By Phase
|
|
121
|
+
*No phases executed yet*
|
|
122
|
+
|
|
123
|
+
## By Category
|
|
124
|
+
*Skills will be tracked here as they're applied during execution*
|
|
125
|
+
|
|
126
|
+
## Quick Reference
|
|
127
|
+
Run `/fire-search [query]` to find relevant skills.
|
|
128
|
+
```
|
|
129
|
+
|
|
130
|
+
---
|
|
131
|
+
|
|
132
|
+
## Step 5: Update CONSCIENCE.md
|
|
133
|
+
|
|
134
|
+
Update `.planning/CONSCIENCE.md`:
|
|
135
|
+
- Status: `Ready to plan`
|
|
136
|
+
- Phase count: from ROADMAP.md
|
|
137
|
+
- Last Action: `Project initialized via /fire-1a-new → /fire-1b-research → /fire-1c-setup`
|
|
138
|
+
|
|
139
|
+
---
|
|
140
|
+
|
|
141
|
+
## Step 6: MANDATORY FILE GATE
|
|
142
|
+
|
|
143
|
+
**Before showing completion, verify EVERY file exists. If ANY is missing, go back and create it.**
|
|
144
|
+
|
|
145
|
+
```bash
|
|
146
|
+
echo "=== FILE GATE CHECK ==="
|
|
147
|
+
test -f .planning/PROJECT.md || echo "MISSING: PROJECT.md"
|
|
148
|
+
test -f .planning/REQUIREMENTS.md || echo "MISSING: REQUIREMENTS.md"
|
|
149
|
+
test -f .planning/CONSCIENCE.md || echo "MISSING: CONSCIENCE.md"
|
|
150
|
+
test -f .planning/SKILLS-INDEX.md || echo "MISSING: SKILLS-INDEX.md"
|
|
151
|
+
test -f .planning/research/SYNTHESIS.md || echo "MISSING: SYNTHESIS.md"
|
|
152
|
+
test -f .planning/VISION.md || echo "MISSING: VISION.md"
|
|
153
|
+
test -f .planning/ROADMAP.md || echo "MISSING: ROADMAP.md"
|
|
154
|
+
test -f .planning/research/ALTERNATIVES.md || echo "MISSING: ALTERNATIVES.md"
|
|
155
|
+
test -f .planning/TOOLING-LOG.md || echo "MISSING: TOOLING-LOG.md"
|
|
156
|
+
test -d .planning/breadcrumbs || echo "MISSING: breadcrumbs/"
|
|
157
|
+
test -d .planning/phases || echo "MISSING: phases/"
|
|
158
|
+
echo "=== GATE COMPLETE ==="
|
|
159
|
+
```
|
|
160
|
+
|
|
161
|
+
**If ANY file is missing, DO NOT show completion. Go back to the step that creates it — or tell the user which prior command to re-run.**
|
|
162
|
+
|
|
163
|
+
---
|
|
164
|
+
|
|
165
|
+
## DevTools Guide (Backward Mode Only)
|
|
166
|
+
|
|
167
|
+
For users who were in backward mode (beginners), save a brief DevTools orientation to `.planning/DEVTOOLS-GUIDE.md`:
|
|
168
|
+
|
|
169
|
+
```markdown
|
|
170
|
+
## Quick DevTools Guide
|
|
171
|
+
|
|
172
|
+
**Open DevTools:** F12 or Ctrl+Shift+I (Windows) / Cmd+Option+I (Mac)
|
|
173
|
+
|
|
174
|
+
**3 tabs you'll use:**
|
|
175
|
+
1. **Console** — errors show here (red = error, yellow = warning)
|
|
176
|
+
2. **Network** — API calls (filter by Fetch/XHR)
|
|
177
|
+
3. **Elements** — HTML/CSS inspector (click magnifier icon → click element)
|
|
178
|
+
|
|
179
|
+
**Pro tip:** When something breaks, open Console, reproduce the error, screenshot the red text, share with Claude.
|
|
180
|
+
```
|
|
181
|
+
|
|
182
|
+
---
|
|
183
|
+
|
|
184
|
+
## Completion Display
|
|
185
|
+
|
|
186
|
+
**Show ONLY after file gate passes with zero missing files:**
|
|
187
|
+
|
|
188
|
+
```
|
|
189
|
+
+==============================================================================+
|
|
190
|
+
| PROJECT INITIALIZED |
|
|
191
|
+
|==============================================================================|
|
|
192
|
+
| |
|
|
193
|
+
| Project: {project_name} |
|
|
194
|
+
| Stack: {locked stack from VISION.md} |
|
|
195
|
+
| Phases: {phase_count} defined in ROADMAP.md |
|
|
196
|
+
| Status: Ready to plan |
|
|
197
|
+
| |
|
|
198
|
+
| Core Files: |
|
|
199
|
+
| [x] .planning/PROJECT.md <- requirements |
|
|
200
|
+
| [x] .planning/REQUIREMENTS.md <- REQ-IDs |
|
|
201
|
+
| [x] .planning/VISION.md <- LOCKED |
|
|
202
|
+
| [x] .planning/ROADMAP.md <- phase breakdown |
|
|
203
|
+
| [x] .planning/CONSCIENCE.md <- project state |
|
|
204
|
+
| |
|
|
205
|
+
| Research: |
|
|
206
|
+
| [x] .planning/research/SYNTHESIS.md <- merged research + GitHub refs |
|
|
207
|
+
| [x] .planning/research/ALTERNATIVES.md <- rejected branches |
|
|
208
|
+
| |
|
|
209
|
+
| Memory: |
|
|
210
|
+
| [x] .planning/breadcrumbs/ <- on-demand (agents create files |
|
|
211
|
+
| when they record learnings) |
|
|
212
|
+
| |
|
|
213
|
+
| Tooling: |
|
|
214
|
+
| [x] .planning/TOOLING-LOG.md <- installed CLIs |
|
|
215
|
+
| [x] WARRIOR handoff <- session continuity |
|
|
216
|
+
| |
|
|
217
|
+
| Gates Triggered: |
|
|
218
|
+
| [?] Mode Gate -> {forward/backward} |
|
|
219
|
+
| [?] Anti-Frankenstein -> {conflicts found / clean} |
|
|
220
|
+
| [?] Vision Architect -> {N} branches, Branch {X} selected |
|
|
221
|
+
| [?] Vision Lock -> VISION.md marked LOCKED |
|
|
222
|
+
| |
|
|
223
|
+
|==============================================================================|
|
|
224
|
+
| NEXT UP |
|
|
225
|
+
|------------------------------------------------------------------------------|
|
|
226
|
+
| |
|
|
227
|
+
| -> Run /fire-2-plan 1 to create plans for Phase 1 |
|
|
228
|
+
| -> Or run /fire-dashboard to view project status |
|
|
229
|
+
| |
|
|
230
|
+
+==============================================================================+
|
|
231
|
+
```
|
|
232
|
+
|
|
233
|
+
---
|
|
234
|
+
|
|
235
|
+
## Error Handling
|
|
236
|
+
|
|
237
|
+
### Missing Prerequisites
|
|
238
|
+
```
|
|
239
|
+
╔══════════════════════════════════════════════════════════════════════════════╗
|
|
240
|
+
║ ✗ ERROR: Run /fire-1b-research first ║
|
|
241
|
+
╠══════════════════════════════════════════════════════════════════════════════╣
|
|
242
|
+
║ Missing: .planning/VISION.md or .planning/ROADMAP.md ║
|
|
243
|
+
║ These are created by /fire-1b-research. Run that command first. ║
|
|
244
|
+
╚══════════════════════════════════════════════════════════════════════════════╝
|
|
245
|
+
```
|
|
246
|
+
|
|
247
|
+
---
|
|
248
|
+
|
|
249
|
+
## References
|
|
250
|
+
|
|
251
|
+
- **Skill:** `@skills-library/_general/methodology/ZERO_FRICTION_CLI_SETUP.md`
|
|
252
|
+
- **Protocol:** `@references/honesty-protocols.md` - WARRIOR honesty foundation
|
|
253
|
+
- **Template:** `@templates/state.md` - CONSCIENCE.md template
|
|
254
|
+
- **Template:** `@templates/skills-index.md` - Skills tracking template
|