@accelerationguy/accel 1.0.0

package/modules/drive/src/rules/templates.md

@@ -0,0 +1,51 @@
+---
+paths:
+  - "src/templates/**/*.md"
+---
+
+# Template Rules
+
+Rules for editing files in `src/templates/`.
+
+## File Structure
+
+Templates define the structure for generated documents. Each template file contains:
+
+1. **Header** — `# [NAME].md Template`
+2. **Intro** — Brief description and file naming pattern
+3. **File Template block** — The actual template in a fenced code block
+4. **Field documentation** — Tables explaining frontmatter fields, sections
+5. **Examples/Anti-patterns** — Good vs bad usage
+
+## Placeholder Conventions
+
+**Square brackets** for human-fillable placeholders:
+```
+[Project Name]
+[Description of what this accomplishes]
+[Specific implementation instructions]
+```
+
+**Curly braces** for variable interpolation:
+```
+{phase}-{plan}-PLAN.md
+.drive/phases/{phase-number}-{name}/
+```
+
+## YAML Frontmatter in Template Content
+
+Templates that define output documents show example frontmatter:
+
+```yaml
+---
+phase: XX-name
+plan: NN
+type: execute
+wave: 1
+depends_on: []
+files_modified: []
+autonomous: true
+---
+```
+
+This is content TO BE GENERATED, not frontmatter for the template file itself.

package/modules/drive/src/rules/workflows.md

@@ -0,0 +1,133 @@
+---
+paths:
+  - "src/workflows/**/*.md"
+---
+
+# Workflow Rules
+
+Rules for editing files in `src/workflows/`.
+
+## No Frontmatter
+
+Workflows don't use YAML frontmatter. Content starts immediately with semantic XML.
+
+## Required Sections
+
+Every workflow MUST have:
+
+1. `<purpose>` — What this workflow accomplishes (1-2 sentences)
+2. `<when_to_use>` — Decision criteria for invoking this workflow
+3. `<process>` — Container for execution steps
+
+## Optional Sections
+
+- `<required_reading>` — Files to read before starting
+- `<loop_context>` — Current PLAN/APPLY/UNIFY phase awareness
+- `<references>` — @-references to load conceptual docs when relevant
+
+## Step Elements
+
+When using `<step>` elements within `<process>`:
+
+```xml
+<step name="load_project_state" priority="first">
+  Read .drive/STATE.md to determine current position.
+  Verify loop phase matches expected phase for this workflow.
+</step>
+
+<step name="execute_tasks">
+  For each task in PLAN.md:
+  1. Execute task action
+  2. Run task verification
+  3. Record result
+</step>
+```
+
+- `name` attribute: snake_case (e.g., `name="load_project_state"`)
+- `priority` attribute: Optional ("first", "second") for ordering hints
+- Content: Imperative instructions, can include numbered steps
+
+## Loop Phase Awareness
+
+Workflows should be aware of their position in the Drive loop:
+
+```xml
+<loop_context>
+Expected phase: PLAN
+Prior phase: UNIFY (previous plan) or none (first plan)
+Next phase: APPLY (after plan approval)
+</loop_context>
+```
+
+This helps workflows validate they're being invoked at the right time.
+
+## Conditional Logic
+
+For mode-dependent behavior:
+
+```xml
+<if autonomous="true">
+  Execute all tasks without checkpoints.
+</if>
+
+<if autonomous="false">
+  Pause at each checkpoint:human-verify task.
+</if>
+```
+
+Conditions reference PLAN.md frontmatter or config values.
+
+## Key Principle
+
+Workflows contain detailed execution logic. Commands are thin wrappers that delegate to workflows.
+
+A workflow can be long and detailed. It answers "how to do it" comprehensively.
+
+## Example Workflow Structure
+
+```markdown
+<purpose>
+Execute an approved PLAN by running tasks in order, verifying each, and recording results.
+</purpose>
+
+<when_to_use>
+- User has approved a PLAN.md
+- STATE.md shows loop position at PLAN (ready for APPLY)
+- No blocking checkpoints remain unresolved
+</when_to_use>
+
+<required_reading>
+@.drive/STATE.md
+@.drive/phases/{phase}/{plan}-PLAN.md
+</required_reading>
+
+<loop_context>
+Expected phase: APPLY
+Prior phase: PLAN (approval just received)
+Next phase: UNIFY (after execution completes)
+</loop_context>
+
+<process>
+
+<step name="validate_preconditions" priority="first">
+  1. Read STATE.md, confirm loop position
+  2. Read PLAN.md, confirm autonomous flag
+  3. If autonomous=false and checkpoints exist, warn user
+</step>
+
+<step name="execute_tasks">
+  For each <task> in PLAN.md <tasks> section:
+  1. Log task start
+  2. Execute <action> content
+  3. Run <verify> command
+  4. If verify passes, record in APPLY-LOG
+  5. If verify fails, stop and report
+</step>
+
+<step name="finalize">
+  1. Update STATE.md loop position to UNIFY
+  2. Report completion status
+</step>
+
+</process>
+```

package/modules/drive/src/templates/CONTEXT.md

@@ -0,0 +1,88 @@
+# CONTEXT.md Template
+
+Template for `.drive/phases/{NN}-{name}/CONTEXT.md` - phase discussion context handoff.
+
+**Purpose:** Captures user's vision, goals, and approach before planning. Created by `/drive:discuss`, consumed by `/drive:plan`.
+
+---
+
+## File Template
+
+```markdown
+# Phase Context
+
+**Phase:** {NN} — {phase_name}
+**Generated:** {date}
+**Status:** Ready for planning | Needs more discussion
+
+## Goals
+
+{user's goals as bullets}
+- Goal 1: [description]
+- Goal 2: [description]
+- Goal 3: [description]
+
+## Approach
+
+{user's approach notes}
+- Pattern/library preferences
+- Technical direction
+- Constraints mentioned
+
+## Constraints
+
+{any limitations or requirements}
+- Constraint 1
+- Constraint 2
+
+## Open Questions
+
+{items still unclear or needing research}
+- Question 1
+- Question 2
+
+## Additional Context
+
+{any other notes from discussion}
+
+---
+
+*This file is temporary. It informs planning but is not required.*
+*Created by /drive:discuss, consumed by /drive:plan.*
+```
+
+---
+
+## Field Descriptions
+
+| Field | Purpose |
+|-------|---------|
+| `Phase` | Phase number and name from ROADMAP.md |
+| `Generated` | Date context was created |
+| `Status` | Whether context is complete or needs more discussion |
+| `Goals` | User's objectives for the phase |
+| `Approach` | Technical direction, patterns, preferences |
+| `Constraints` | Limitations or requirements |
+| `Open Questions` | Items needing research or decisions |
+| `Additional Context` | Other notes from discussion |
+
+---
+
+## Usage Pattern
+
+1. User runs `/drive:discuss <phase>`
+2. Discussion workflow explores goals and approach
+3. CONTEXT.md created in phase directory
+4. `/drive:plan` reads CONTEXT.md to inform planning
+5. CONTEXT.md remains for reference (not deleted)
+
+---
+
+## Relationship to Other Files
+
+| File | Relationship |
+|------|--------------|
+| ROADMAP.md | Source of phase definition |
+| CONTEXT.md | Discussion output (this file) |
+| PLAN.md | Consumes context for planning |
+| RESEARCH.md | May inform context or result from questions |

package/modules/drive/src/templates/DEBUG.md

@@ -0,0 +1,164 @@
+# Debug Template
+
+Template for `.drive/debug/[slug].md` — active debug session tracking.
+
+---
+
+## File Template
+
+```markdown
+---
+status: gathering | investigating | fixing | verifying | resolved
+trigger: "[verbatim user input]"
+created: [ISO timestamp]
+updated: [ISO timestamp]
+---
+
+## Current Focus
+<!-- OVERWRITE on each update - always reflects NOW -->
+
+hypothesis: [current theory being tested]
+test: [how testing it]
+expecting: [what result means if true/false]
+next_action: [immediate next step]
+
+## Symptoms
+<!-- Written during gathering, then immutable -->
+
+expected: [what should happen]
+actual: [what actually happens]
+errors: [error messages if any]
+reproduction: [how to trigger]
+started: [when it broke / always broken]
+
+## Eliminated
+<!-- APPEND only - prevents re-investigating after context reset -->
+
+- hypothesis: [theory that was wrong]
+  evidence: [what disproved it]
+  timestamp: [when eliminated]
+
+## Evidence
+<!-- APPEND only - facts discovered during investigation -->
+
+- timestamp: [when found]
+  checked: [what was examined]
+  found: [what was observed]
+  implication: [what this means]
+
+## Resolution
+<!-- OVERWRITE as understanding evolves -->
+
+root_cause: [empty until found]
+fix: [empty until applied]
+verification: [empty until verified]
+files_changed: []
+```
+
+---
+
+<section_rules>
+
+**Frontmatter (status, trigger, timestamps):**
+- `status`: OVERWRITE - reflects current phase
+- `trigger`: IMMUTABLE - verbatim user input, never changes
+- `created`: IMMUTABLE - set once
+- `updated`: OVERWRITE - update on every change
+
+**Current Focus:**
+- OVERWRITE entirely on each update
+- Always reflects what Claude is doing RIGHT NOW
+- If Claude reads this after context reset, it knows exactly where to resume
+- Fields: hypothesis, test, expecting, next_action
+
+**Symptoms:**
+- Written during initial gathering phase
+- IMMUTABLE after gathering complete
+- Reference point for what we're trying to fix
+- Fields: expected, actual, errors, reproduction, started
+
+**Eliminated:**
+- APPEND only - never remove entries
+- Prevents re-investigating dead ends after context reset
+- Each entry: hypothesis, evidence that disproved it, timestamp
+- Critical for efficiency across session boundaries
+
+**Evidence:**
+- APPEND only - never remove entries
+- Facts discovered during investigation
+- Each entry: timestamp, what checked, what found, implication
+- Builds the case for root cause
+
+**Resolution:**
+- OVERWRITE as understanding evolves
+- May update multiple times as fixes are tried
+- Final state shows confirmed root cause and verified fix
+- Fields: root_cause, fix, verification, files_changed
+
+</section_rules>
+
+<lifecycle>
+
+**Creation:** Immediately when debug workflow is called
+- Create file with trigger from user input
+- Set status to "gathering"
+- Current Focus: next_action = "gather symptoms"
+- Symptoms: empty, to be filled
+
+**During symptom gathering:**
+- Update Symptoms section as user answers questions
+- Update Current Focus with each question
+- When complete: status → "investigating"
+
+**During investigation:**
+- OVERWRITE Current Focus with each hypothesis
+- APPEND to Evidence with each finding
+- APPEND to Eliminated when hypothesis disproved
+- Update timestamp in frontmatter
+
+**During fixing:**
+- status → "fixing"
+- Update Resolution.root_cause when confirmed
+- Update Resolution.fix when applied
+- Update Resolution.files_changed
+
+**During verification:**
+- status → "verifying"
+- Update Resolution.verification with results
+- If verification fails: status → "investigating", try again
+
+**On resolution:**
+- status → "resolved"
+- Move file to .drive/debug/resolved/
+
+**Complex fixes:** If fix requires significant code changes:
+- Create a dedicated PLAN.md for the fix
+- Reference debug file in plan context
+- Debug file stays in "fixing" until plan completes
+
+</lifecycle>
+
+<resume_behavior>
+
+When Claude reads this file after context reset:
+
+1. Parse frontmatter → know status
+2. Read Current Focus → know exactly what was happening
+3. Read Eliminated → know what NOT to retry
+4. Read Evidence → know what's been learned
+5. Continue from next_action
+
+The file IS the debugging brain. Claude should be able to resume perfectly from any interruption point.
+
+</resume_behavior>
+
+<size_constraint>
+
+Keep debug files focused:
+- Evidence entries: 1-2 lines each, just the facts
+- Eliminated: brief - hypothesis + why it failed
+- No narrative prose - structured data only
+
+If evidence grows very large (10+ entries), consider whether you're going in circles. Check Eliminated to ensure you're not re-treading.
+
+</size_constraint>

package/modules/drive/src/templates/DISCOVERY.md

@@ -0,0 +1,148 @@
+# DISCOVERY.md Template
+
+Template for `.drive/phases/{phase-number}-{name}/DISCOVERY.md` — technical discovery documentation.
+
+**Purpose:** Document technical research, options comparison, and recommendations before planning.
+
+---
+
+## File Template
+
+```markdown
+---
+phase: XX-name
+topic: [what was discovered]
+depth: [quick | standard | deep]
+confidence: [HIGH | MEDIUM | LOW]
+created: YYYY-MM-DD
+---
+
+# Discovery: [Topic]
+
+**Recommendation:** [One-liner recommendation]
+
+**Confidence:** [HIGH/MEDIUM/LOW] — [Brief justification]
+
+## Objective
+
+What we needed to learn before planning:
+- [Question 1]
+- [Question 2]
+- [Question 3]
+
+## Scope
+
+**Include:**
+- [What was researched]
+
+**Exclude:**
+- [What was explicitly out of scope]
+
+## Findings
+
+### Option A: [Name]
+
+**Source:** [URL or documentation reference]
+
+**Summary:** [Brief description]
+
+**Pros:**
+- [Advantage 1]
+- [Advantage 2]
+
+**Cons:**
+- [Disadvantage 1]
+- [Disadvantage 2]
+
+**For our use case:** [Fit assessment]
+
+### Option B: [Name]
+
+**Source:** [URL or documentation reference]
+
+**Summary:** [Brief description]
+
+**Pros:**
+- [Advantage 1]
+- [Advantage 2]
+
+**Cons:**
+- [Disadvantage 1]
+- [Disadvantage 2]
+
+**For our use case:** [Fit assessment]
+
+## Comparison
+
+| Criteria | Option A | Option B |
+|----------|----------|----------|
+| [Criterion 1] | [Rating] | [Rating] |
+| [Criterion 2] | [Rating] | [Rating] |
+| [Criterion 3] | [Rating] | [Rating] |
+
+## Recommendation
+
+**Choose: [Option]**
+
+**Rationale:**
+[Why this option is best for our specific use case]
+
+**Caveats:**
+- [Any limitations or concerns to watch for]
+
+## Open Questions
+
+[Questions that remain after discovery - may affect implementation]
+
+- [Question 1] — Impact: [low/medium/high]
+- [Question 2] — Impact: [low/medium/high]
+
+Or: "None — discovery answered all questions."
+
+## Quality Report
+
+**Sources consulted:**
+- [Source 1 with date]
+- [Source 2 with date]
+
+**Verification:**
+- [Claim 1]: Verified via [source]
+- [Claim 2]: Verified via [source]
+
+**Assumptions (not verified):**
+- [Assumption 1]
+
+---
+*Discovery completed: [date]*
+*Confidence: [level]*
+*Ready for: /drive:plan [phase]*
+```
+
+---
+
+## Section Specifications
+
+### Frontmatter
+
+| Field | Required | Purpose |
+|-------|----------|---------|
+| `phase` | Yes | Phase this discovery informs |
+| `topic` | Yes | What was discovered |
+| `depth` | Yes | quick, standard, or deep |
+| `confidence` | Yes | HIGH, MEDIUM, or LOW |
+| `created` | Yes | Discovery date |
+
+### Confidence Levels
+
+| Level | Meaning | Evidence Required |
+|-------|---------|-------------------|
+| HIGH | Verified, low risk | Multiple authoritative sources, tested |
+| MEDIUM | Likely accurate | Official docs OR multiple sources |
+| LOW | Uncertain | Single source, assumptions, gaps |
+
+### Quality Report
+
+Required for Level 2-3 discovery:
+- List all sources with dates
+- Verify each key claim
+- Document assumptions explicitly

package/modules/drive/src/templates/HANDOFF.md

@@ -0,0 +1,77 @@
+# Drive Handoff
+
+**Date:** {{timestamp}}
+**Session:** {{session_id}}
+**Status:** {{status}}
+
+---
+
+## READ THIS FIRST
+
+You have no prior context. This document tells you everything.
+
+**Project:** {{project_name}}
+**Core value:** {{core_value}}
+
+---
+
+## Current State
+
+**Version:** {{version}}
+**Phase:** {{phase_number}} of {{total_phases}} — {{phase_name}}
+**Plan:** {{plan_id}} — {{plan_status}}
+
+**Loop Position:**
+```
+PLAN ──▶ APPLY ──▶ UNIFY
+  {{plan_mark}}        {{apply_mark}}        {{unify_mark}}
+```
+
+---
+
+## What Was Done
+
+{{accomplished_list}}
+
+---
+
+## What's In Progress
+
+{{in_progress_list}}
+
+---
+
+## What's Next
+
+**Immediate:** {{next_action}}
+
+**After that:** {{following_action}}
+
+---
+
+## Key Files
+
+| File | Purpose |
+|------|---------|
+| `.drive/STATE.md` | Live project state |
+| `.drive/ROADMAP.md` | Phase overview |
+| {{current_plan_path}} | {{plan_purpose}} |
+
+---
+
+## Resume Instructions
+
+1. Read `.drive/STATE.md` for latest position
+2. Check if PLAN exists for current phase
+3. Based on loop position:
+   - `○○○` (fresh) → Run `/drive:plan`
+   - `✓○○` (planned) → Review plan, then `/drive:apply`
+   - `✓✓○` (applied) → Run `/drive:unify`
+   - `✓✓✓` (complete) → Ready for next phase
+
+**Or simply run:** `/drive:resume`
+
+---
+
+*Handoff created: {{timestamp}}*
+*This file is the single entry point for fresh sessions*