wtf-p 0.4.0 → 0.5.0

package/vendors/claude/commands/wtfp/review-section.md

@@ -1,6 +1,6 @@
 ---
 name: wtfp:review-section
-description: Run 3-layer verification on written sections
+description: Review section for citations, coherence, and requirements
 argument-hint: "[section]"
 allowed-tools:
   - Read
@@ -8,377 +8,103 @@ allowed-tools:
   - Write
   - Glob
   - Grep
+  - Task
   - AskUserQuestion
 ---
 
+<execution_context>
+@~/.claude/write-the-f-paper/workflows/review-section.md
+</execution_context>
+
 <objective>
 User acceptance testing of written sections with configurable reviewer personas.
 
+**Orchestrator role:** Validate section exists, select persona, resolve model profile, spawn section-reviewer agent, present results.
+
 Runs 3-layer verification:
 1. Citation Check (Mechanical)
 2. Argument Coherence (Logical)
 3. Rubric Check (Requirements)
-
-**Reviewer Personas** adjust critique intensity and focus:
-- Reviewer #2 (Hostile): Nitpicky, finds every flaw, assumes bad faith
-- Area Chair (Big Picture): Strategic, focuses on contribution significance
-- Camera-Ready Editor (Nitpicky): Formatting, style, polish details
-- Friendly Mentor (Constructive): Balanced, actionable suggestions
-
-Creates ISSUES.md if problems found.
-
-User performs verification; Claude guides and documents.
 </objective>
 
-<execution_context>
-@~/.claude/write-the-f-paper/workflows/review-section.md
-</execution_context>
+<context>
+Section: $ARGUMENTS (section number or path)
+</context>
 
 <process>
 
-<step name="verify">
-**Verify section exists:**
+## 1. Validate Environment and Resolve Model Profile
 
 ```bash
-# Check for written content
 ls paper/*.md 2>/dev/null || echo "No content in paper/ directory"
-
-# Check for SUMMARY indicating writing complete
-ls .planning/sections/*/SUMMARY.md 2>/dev/null | head -5
+ls .planning/ 2>/dev/null
 ```
 
-</step>
-
-<step name="load">
-**Load context for review:**
+**Resolve model profile:**
+```bash
+MODEL_PROFILE=$(cat .planning/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
+```
 
-- Read the written section content (paper/[section].md)
-- Read PROJECT.md for requirements
-- Read argument-map.md for expected claims
-- Read outline.md for structure expectations
-- Read sources/literature.md for citation expectations
-- Read SUMMARY.md for what was intended
-</step>
+| Agent | quality | balanced | budget |
+|-------|---------|----------|--------|
+| section-reviewer | opus | sonnet | haiku |
 
-<step name="select_persona">
-**Select reviewer persona:**
+## 2. Select Reviewer Persona
 
 Use AskUserQuestion:
 - header: "Reviewer"
 - question: "What type of review do you want?"
 - options:
+  - "Friendly Mentor" — Balanced, constructive, actionable (Recommended)
   - "Reviewer #2 (Hostile)" — Nitpicky, assumes worst, finds every flaw
   - "Area Chair (Big Picture)" — Strategic focus on contribution and impact
   - "Camera-Ready Editor" — Formatting, style, polish, consistency
-  - "Friendly Mentor" — Balanced, constructive, actionable (Recommended)
-
-**Persona behaviors:**
-
-### Reviewer #2 (Hostile)
-- Questions every claim without citation
-- Assumes methodology is flawed until proven
-- Finds ambiguity in clear statements
-- Demands more experiments/evidence
-- Tone: "The authors fail to..." / "It is unclear why..."
-- Severity bias: Escalates minor issues to major
-
-### Area Chair (Big Picture)
-- Focuses on: Is the contribution significant?
-- Asks: Would this paper advance the field?
-- Checks: Is the evaluation convincing for the claims made?
-- Less concerned with minor formatting
-- Tone: "The main contribution..." / "The significance..."
-- Severity bias: Ignores minor, focuses on blockers
-
-### Camera-Ready Editor
-- Formatting consistency (headings, spacing, fonts)
-- Figure/table placement and references
-- Citation style compliance
-- Grammar, typos, awkward phrasing
-- LaTeX/formatting warnings
-- Tone: "Line X has..." / "Figure Y should..."
-- Severity bias: Many minor issues
-
-### Friendly Mentor
-- Balanced critique with encouragement
-- Every criticism paired with suggestion
-- Prioritizes actionable feedback
-- Acknowledges what works well
-- Tone: "Consider..." / "This works well, but could be stronger if..."
-- Severity bias: Realistic assessment
-
-Store selected persona for use in all verification steps.
-
-</step>
-
-<step name="citation_check">
-**Layer 1: Citation Check (Mechanical)**
-
-Adjust intensity based on persona:
-
-**If Reviewer #2 (Hostile):**
-```
-## Citation Check (Hostile Mode)
-
-I'm looking for EVERY missing citation:
-
-- [ ] ALL factual claims have citations (even "obvious" ones)
-- [ ] Claims of novelty properly qualified
-- [ ] No weasel words hiding missing citations ("studies show...", "it is known...")
-- [ ] Self-citation ratio appropriate (not self-promotional)
-- [ ] Recent work cited (nothing newer doing this?)
-- [ ] Foundational work cited (did you read the classics?)
-
-**Potential issues I see:**
-[Claude actively identifies potential issues in hostile mode]
-```
-
-**If Area Chair:**
-```
-## Citation Check (Strategic)
-
-Focus on citation credibility:
-
-- [ ] Key claims backed by strong citations
-- [ ] Methodology citations are appropriate
-- [ ] Comparison baselines properly cited
-- [ ] Not over-citing tangential work
-
-**Big picture:**
-```
-
-**If Camera-Ready Editor:**
-```
-## Citation Check (Formatting)
-
-- [ ] Citation format consistent throughout ([N] vs (Author, Year))
-- [ ] All citations resolve in bibliography
-- [ ] No duplicate entries
-- [ ] Citation style matches venue requirements
-- [ ] Page numbers where required
-```
-
-**If Friendly Mentor:**
-```
-## Citation Check
-
-Let's make sure your citations are solid:
-
-- [ ] Factual claims have citations
-- [ ] Format is consistent
-- [ ] Bibliography is complete
-
-**What's working well:** [note positives]
-**Suggestions:**
-```
-
-Use AskUserQuestion:
-- header: "Citations"
-- question: "Any citation issues found?"
-- options:
-  - "All clear" — Citations look good
-  - "Issues found" — I'll list them
-  - "Skip this check" — Move to next layer
-
-If issues found, prompt for details.
-
-</step>
-
-<step name="coherence_check">
-**Layer 2: Argument Coherence (Logical)**
-
-Adjust intensity based on persona:
-
-**If Reviewer #2 (Hostile):**
-```
-## Argument Coherence (Hostile Mode)
-
-I'm stress-testing your logic:
-
-- [ ] Every claim PROVEN, not just stated
-- [ ] Assumptions explicitly stated and justified
-- [ ] Alternative explanations addressed
-- [ ] Limitations acknowledged (or I'll find them)
-- [ ] No logical leaps ("clearly" / "obviously" hiding weak reasoning)
-- [ ] Statistics interpreted correctly
-- [ ] Causation vs correlation distinguished
-
-**Logical weaknesses I see:**
-[Claude actively identifies logical gaps in hostile mode]
-
-**Questions a hostile reviewer would ask:**
-- "How do you know X causes Y?"
-- "What about alternative explanation Z?"
-- "Your sample size is only N..."
-```
 
-**If Area Chair:**
-```
-## Argument Coherence (Strategic)
-
-Does the argument support a strong contribution?
+## 3. Read Context Files
 
-- [ ] Core thesis is clear and significant
-- [ ] Evidence supports the main claims
-- [ ] Contribution is differentiated from prior work
-- [ ] Limitations don't undermine the contribution
-
-**Strategic assessment:**
-```
+```bash
+SECTION_CONTENT=$(cat paper/*.md 2>/dev/null)
+PROJECT_CONTENT=$(cat .planning/PROJECT.md)
+ARGMAP_CONTENT=$(cat .planning/structure/argument-map.md 2>/dev/null)
+OUTLINE_CONTENT=$(cat .planning/structure/outline.md 2>/dev/null)
+SUMMARY_CONTENT=$(cat .planning/sections/*/SUMMARY.md 2>/dev/null | head -200)
 
-**If Camera-Ready Editor:**
+SECTION_DIR=$(ls -d .planning/sections/${SECTION}-* 2>/dev/null | head -1)
+CONTEXT_CONTENT=$(cat "${SECTION_DIR}"/*-CONTEXT.md 2>/dev/null)
 ```
-## Argument Coherence (Light Touch)
 
-Basic logical flow:
+## 4. Spawn wtfp-section-reviewer Agent
 
-- [ ] Paragraphs in logical order
-- [ ] Transitions present
-- [ ] No obvious contradictions
 ```
-
-**If Friendly Mentor:**
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► REVIEWING SECTION
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 ```
-## Argument Coherence
-
-Let's strengthen your argument:
 
-- [ ] Claims follow from evidence
-- [ ] Logic flows naturally
-- [ ] Counter-arguments addressed
-
-**Strengths:** [what's working]
-**Opportunities:** [where to strengthen]
 ```
-
-**Cross-reference with argument-map.md:**
-- [ ] Claim 1 addressed: [yes/no/partial]
-- [ ] Claim 2 addressed: [yes/no/partial]
-- [ ] ...
-
-Use AskUserQuestion:
-- header: "Coherence"
-- question: "Any logical/flow issues found?"
-- options:
-  - "All clear" — Logic flows well
-  - "Issues found" — I'll list them
-  - "Skip this check" — Move to next layer
-
-</step>
-
-<step name="rubric_check">
-**Layer 3: Rubric Check (Requirements)**
-
-Present checklist based on PROJECT.md requirements:
-
+Task(
+  prompt="First, read ~/.claude/agents/wtfp/section-reviewer.md for your role and instructions.\n\n" + filled_review_prompt,
+  subagent_type="general-purpose",
+  model="{reviewer_model}",
+  description="Review Section {X}"
+)
 ```
-## Rubric Check
-
-Review against requirements:
-
-**Structure:**
-- [ ] All required elements present
-- [ ] Follows expected structure (IMRaD, etc.)
-- [ ] Appropriate for target venue
 
-**Length:**
-- [ ] Word count: [current] / [target] ([variance]%)
-- [ ] Within acceptable range
+Review prompt includes: `<section_content>` with written text, `<review_persona>` with selected persona, `<project_context>` with PROJECT + argument-map + outline, `<user_decisions>` with CONTEXT_CONTENT.
 
-**Formatting:**
-- [ ] Heading levels correct
-- [ ] Figure/table references correct
-- [ ] Consistent style throughout
+## 5. Handle Reviewer Return
 
-**Content Requirements:**
-- [ ] [Requirement 1 from PROJECT.md]: [met/not met]
-- [ ] [Requirement 2 from PROJECT.md]: [met/not met]
+**`## REVIEW COMPLETE`:** Present results, route to next action.
 
-**Issues found:**
-```
-
-Use AskUserQuestion:
-- header: "Requirements"
-- question: "Any requirement issues found?"
-- options:
-  - "All clear" — Requirements met
-  - "Issues found" — I'll list them
-
-</step>
-
-<step name="issues">
-**Create ISSUES.md if problems found:**
-
-```markdown
----
-section: XX-name
-plan: YY
-review_date: [date]
----
+## 6. Present Results
 
-# Review Issues: [Section Name]
-
-## Reviewer Persona: [Selected Persona]
-
-## Citation Issues
-| ID | Issue | Severity | Location |
-|----|-------|----------|----------|
-| CIT-1 | [description] | [Major/Minor] | [line/para] |
-
-## Coherence Issues
-| ID | Issue | Severity | Location |
-|----|-------|----------|----------|
-| COH-1 | [description] | [Major/Minor] | [line/para] |
-
-## Requirement Issues
-| ID | Issue | Severity | Requirement |
-|----|-------|----------|-------------|
-| REQ-1 | [description] | [Major/Minor] | [which req] |
-
-## Summary
-- Total issues: [N]
-- Blockers (must fix): [N]
-- Major (should fix): [N]
-- Minor (nice to fix): [N]
-
----
-*Reviewed: [date]*
-```
-
-</step>
-
-<step name="commit">
-```bash
-git add .planning/sections/XX-name/XX-YY-ISSUES.md
-git commit -m "$(cat <<'EOF'
-review(XX-YY): [section name] verification
-
-Issues found: [N] ([blockers] blockers)
-EOF
-)"
-```
-
-</step>
-
-<step name="done">
-**Present results:**
-
-```
-Review complete:
-
-- Section: [name]
-- Issues: .planning/sections/XX-name/XX-YY-ISSUES.md
-
-## Summary
-- Citation check: [pass/issues]
-- Coherence check: [pass/issues]
-- Rubric check: [pass/issues]
-
-Total: [N] issues ([blockers] blockers, [major] major, [minor] minor)
+</process>
 
----
+<offer_next>
 
-## ▶ Next Up
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► REVIEW COMPLETE
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
 [If issues found:]
 **Plan revisions** — address identified issues
@@ -392,18 +118,14 @@ Total: [N] issues ([blockers] blockers, [major] major, [minor] minor)
 
 <sub>`/clear` first → fresh context window</sub>
 
----
-```
-
-</step>
+───────────────────────────────────────────
 
-</process>
+</offer_next>
 
 <success_criteria>
 - [ ] Reviewer persona selected
-- [ ] All 3 verification layers executed (intensity adjusted to persona)
-- [ ] User guided through each check
-- [ ] Issues documented in ISSUES.md with persona noted
-- [ ] Severity levels assigned (persona-appropriate)
+- [ ] Section-reviewer spawned with full context
+- [ ] All 3 verification layers executed
+- [ ] Issues documented in ISSUES.md
 - [ ] Clear next steps provided
 </success_criteria>

package/vendors/claude/commands/wtfp/settings.md

@@ -0,0 +1,197 @@
+---
+name: wtfp:settings
+description: View and edit project settings interactively
+allowed-tools:
+  - Read
+  - Bash
+  - Write
+  - AskUserQuestion
+---
+
+<objective>
+Interactive config editor for .planning/config.json.
+
+Reads current config, presents categories, allows edits, shows diff of changes before applying.
+
+No subagents needed - orchestrator handles all interaction directly.
+</objective>
+
+<context>
+No arguments. Requires .planning/config.json to exist.
+</context>
+
+<process>
+
+## 1. Validate Environment
+
+```bash
+[ ! -f .planning/config.json ] && echo "ERROR: No config. Run /wtfp:new-paper" && exit 1
+```
+
+Read current config:
+```bash
+CONFIG_CONTENT=$(cat .planning/config.json)
+```
+
+Store original for diff comparison later.
+
+## 2. Display Current Settings
+
+Present settings organized by category (matching planning-config.md structure):
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► SETTINGS
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+## General
+  mode: interactive
+  depth: standard
+  document_type: paper
+  output_format: markdown
+  model_profile: balanced
+  venue_template: (none)
+
+## Gates
+  confirm_outline: true
+  confirm_plan: true
+  confirm_write: true
+  confirm_review: true
+  execute_next_section: true
+  issues_review: true
+  confirm_transition: true
+  confirm_submission: true
+
+## Writing
+  claude_mode: co-author
+  citation_style: apa
+  verify_on_complete: true
+
+## Workflow
+  research: true
+  plan_check: true
+  verifier: true
+
+## Verification
+  citation_check: true
+  coherence_check: true
+  rubric_check: true
+
+## Planning
+  commit_docs: true
+  search_gitignored: false
+
+## Parallelization
+  enabled: false
+  plan_level: true
+  task_level: false
+  skip_checkpoints: true
+  max_concurrent_agents: 3
+  min_plans_for_parallel: 2
+
+## Safety
+  always_confirm_destructive: true
+  always_confirm_external_services: true
+  backup_before_major_edits: true
+
+## Git
+  branching_strategy: none
+  section_branch_template: wtfp/section-{section}-{slug}
+  submission_branch_template: wtfp/{milestone}-{slug}
+  squash_on_merge: false
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+## 3. Category Selection
+
+Use AskUserQuestion:
+- header: "Edit Settings"
+- question: "Which category to modify?"
+- options: "General" | "Gates" | "Writing" | "Workflow" | "Verification" | "Planning" | "Parallelization" | "Safety" | "Git" | "Done"
+
+**If "Done":** Skip to Step 6.
+
+## 4. Edit Keys in Category
+
+For chosen category, present each key with current value and ask for new value.
+
+**For boolean keys:** Use AskUserQuestion:
+- options: "true" | "false" | "Keep current"
+
+**For string keys with known options:**
+- `mode`: "interactive" | "yolo" | "Keep current"
+- `depth`: "quick" | "standard" | "thorough" | "Keep current"
+- `document_type`: "paper" | "thesis" | "proposal" | "report" | "Keep current"
+- `output_format`: "markdown" | "latex" | "Keep current"
+- `model_profile`: "quality" | "balanced" | "budget" | "Keep current"
+- `claude_mode`: "co-author" | "scaffold" | "reviewer" | "Keep current"
+- `citation_style`: "apa" | "ieee" | "chicago" | "mla" | "vancouver" | "Keep current"
+- `branching_strategy`: "none" | "section" | "submission" | "Keep current"
+
+**For numeric keys:** Use AskUserQuestion with text input.
+- `max_concurrent_agents`: Accept integer value
+- `min_plans_for_parallel`: Accept integer value
+
+**For string template keys:** Use AskUserQuestion with text input.
+- `section_branch_template`: Accept string value
+- `submission_branch_template`: Accept string value
+- `venue_template`: Accept string value or "none"
+
+Track all changes made.
+
+## 5. Compute and Show Diff
+
+If any changes were made, show diff before applying:
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► SETTINGS CHANGED
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Changes:
+  mode: interactive -> yolo
+  gates.confirm_plan: true -> false
+
+Apply changes?
+```
+
+Use AskUserQuestion:
+- header: "Confirm Changes"
+- question: "Apply these changes?"
+- options: "Yes, apply" | "No, discard" | "Edit more"
+
+**If "Yes, apply":** Write updated config.json.
+
+**If "No, discard":** Discard changes, return to category selection.
+
+**If "Edit more":** Return to Step 3.
+
+## 6. Exit
+
+If no changes or after applying changes, show final banner:
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► SETTINGS SAVED
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+Or if no changes:
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ WTF-P ► SETTINGS UNCHANGED
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+No git commit for settings changes (config.json is a working file).
+
+</process>
+
+<success_criteria>
+- [ ] Current config displayed by category
+- [ ] User can select category and edit keys
+- [ ] Diff shown before applying
+- [ ] config.json updated if changes confirmed
+</success_criteria>