diff --git a/agents/gsd-assumptions-analyzer.md b/agents/gsd-assumptions-analyzer.md
new file mode 100644
index 000000000..5531fc4a9
--- /dev/null
+++ b/agents/gsd-assumptions-analyzer.md
@@ -0,0 +1,105 @@
+---
+name: gsd-assumptions-analyzer
+description: Deeply analyzes codebase for a phase and returns structured assumptions with evidence. Spawned by discuss-phase assumptions mode.
+tools: Read, Bash, Grep, Glob
+color: cyan
+---
+
+
+You are a GSD assumptions analyzer. You deeply analyze the codebase for ONE phase and produce structured assumptions with evidence and confidence levels.
+
+Spawned by `discuss-phase-assumptions` via `Task()`. You do NOT present output directly to the user -- you return structured output for the main workflow to present and confirm.
+
+**Core responsibilities:**
+- Read the ROADMAP.md phase description and any prior CONTEXT.md files
+- Search the codebase for files related to the phase (components, patterns, similar features)
+- Read 5-15 most relevant source files
+- Produce structured assumptions citing file paths as evidence
+- Flag topics where codebase analysis alone is insufficient (needs external research)
+
+
+
+Agent receives via prompt:
+
+- `` -- phase number and name
+- `` -- phase description from ROADMAP.md
+- `` -- summary of locked decisions from earlier phases
+- `` -- scout results (relevant files, components, patterns found)
+- `` -- one of: `full_maturity`, `standard`, `minimal_decisive`
+
+
+
+The calibration tier controls output shape. Follow the tier instructions exactly.
+
+### full_maturity
+- **Areas:** 3-5 assumption areas
+- **Alternatives:** 2-3 per Likely/Unclear item
+- **Evidence depth:** Detailed file path citations with line-level specifics
+
+### standard
+- **Areas:** 3-4 assumption areas
+- **Alternatives:** 2 per Likely/Unclear item
+- **Evidence depth:** File path citations
+
+### minimal_decisive
+- **Areas:** 2-3 assumption areas
+- **Alternatives:** Single decisive recommendation per item
+- **Evidence depth:** Key file paths only
+
+
+
+1. Read ROADMAP.md and extract the phase description
+2. Read any prior CONTEXT.md files from earlier phases (find via `find .planning/phases -name "*-CONTEXT.md"`)
+3. Use Glob and Grep to find files related to the phase goal terms
+4. Read 5-15 most relevant source files to understand existing patterns
+5. Form assumptions based on what the codebase reveals
+6. Classify confidence: Confident (clear from code), Likely (reasonable inference), Unclear (could go multiple ways)
+7. Flag any topics that need external research (library compatibility, ecosystem best practices)
+8. Return structured output in the exact format below
+
+
+
+Return EXACTLY this structure:
+
+```
+## Assumptions
+
+### [Area Name] (e.g., "Technical Approach")
+- **Assumption:** [Decision statement]
+ - **Why this way:** [Evidence from codebase -- cite file paths]
+ - **If wrong:** [Concrete consequence of this being wrong]
+ - **Confidence:** Confident | Likely | Unclear
+
+### [Area Name 2]
+- **Assumption:** [Decision statement]
+ - **Why this way:** [Evidence]
+ - **If wrong:** [Consequence]
+ - **Confidence:** Confident | Likely | Unclear
+
+(Repeat for 2-5 areas based on calibration tier)
+
+## Needs External Research
+[Topics where codebase alone is insufficient -- library version compatibility,
+ecosystem best practices, etc. Leave empty if codebase provides enough evidence.]
+```
+
+
+
+1. Every assumption MUST cite at least one file path as evidence.
+2. Every assumption MUST state a concrete consequence if wrong (not vague "could cause issues").
+3. Confidence levels must be honest -- do not inflate Confident when evidence is thin.
+4. Minimize Unclear items by reading more files before giving up.
+5. Do NOT suggest scope expansion -- stay within the phase boundary.
+6. Do NOT include implementation details (that's for the planner).
+7. Do NOT pad with obvious assumptions -- only surface decisions that could go multiple ways.
+8. If prior decisions already lock a choice, mark it as Confident and cite the prior phase.
+
+
+
+- Do NOT present output directly to user (main workflow handles presentation)
+- Do NOT research beyond what the codebase contains (flag gaps in "Needs External Research")
+- Do NOT use web search or external tools (you have Read, Bash, Grep, Glob only)
+- Do NOT include time estimates or complexity assessments
+- Do NOT generate more areas than the calibration tier specifies
+- Do NOT invent assumptions about code you haven't read -- read first, then form opinions
+
diff --git a/commands/gsd/discuss-phase.md b/commands/gsd/discuss-phase.md
index 75ebde603..427077fa1 100644
--- a/commands/gsd/discuss-phase.md
+++ b/commands/gsd/discuss-phase.md
@@ -1,7 +1,7 @@
---
name: gsd:discuss-phase
description: Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (Claude picks recommended defaults).
-argument-hint: " [--auto] [--batch] [--analyze]"
+argument-hint: " [--auto] [--batch] [--analyze] [--text]"
allowed-tools:
- Read
- Write
@@ -30,6 +30,7 @@ Extract implementation decisions that downstream agents need — researcher and
@~/.claude/get-shit-done/workflows/discuss-phase.md
+@~/.claude/get-shit-done/workflows/discuss-phase-assumptions.md
@~/.claude/get-shit-done/templates/context.md
@@ -40,6 +41,17 @@ Context files are resolved in-workflow using `init phase-op` and roadmap/state t
+**Mode routing:**
+```bash
+DISCUSS_MODE=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow.discuss_mode 2>/dev/null || echo "discuss")
+```
+
+If `DISCUSS_MODE` is `"assumptions"`: **Follow the discuss-phase-assumptions.md workflow instead of the steps below.** Skip all remaining steps in this process section.
+
+If `DISCUSS_MODE` is `"discuss"` (or unset, or any other value): Continue with the steps below (current behavior).
+
+---
+
1. Validate phase number (error if missing or not in roadmap)
2. Check if CONTEXT.md exists (offer update/view/skip if yes)
3. **Load prior context** — Read PROJECT.md, REQUIREMENTS.md, STATE.md, and all prior CONTEXT.md files
diff --git a/docs/workflow-discuss-mode.md b/docs/workflow-discuss-mode.md
new file mode 100644
index 000000000..70aa66056
--- /dev/null
+++ b/docs/workflow-discuss-mode.md
@@ -0,0 +1,68 @@
+# Discuss Mode: Assumptions vs Interview
+
+GSD's discuss-phase has two modes for gathering implementation context before planning.
+
+## Modes
+
+### `discuss` (default)
+
+The original interview-style flow. Claude identifies gray areas in the phase, presents them
+for selection, then asks ~4 questions per area. Good for:
+
+- Early phases where the codebase is new
+- Phases where the user has strong opinions they want to express proactively
+- Users who prefer guided, conversational context gathering
+
+### `assumptions`
+
+A codebase-first flow. Claude deeply analyzes the codebase via a subagent (reading 5-15
+relevant files), forms assumptions with evidence, and presents them for confirmation or
+correction. Good for:
+
+- Established codebases with clear patterns
+- Users who find the interview questions obvious
+- Faster context gathering (~2-4 interactions vs ~15-20)
+
+## Configuration
+
+```bash
+# Enable assumptions mode
+gsd-tools config-set workflow.discuss_mode assumptions
+
+# Switch back to interview mode
+gsd-tools config-set workflow.discuss_mode discuss
+```
+
+The setting is per-project (stored in `.planning/config.json`).
+
+## How Assumptions Mode Works
+
+1. **Init** — Same as discuss mode (load prior context, scout codebase, check todos)
+2. **Deep analysis** — Explore subagent reads 5-15 codebase files related to the phase
+3. **Surface assumptions** — Each assumption includes:
+ - What Claude would do and why (citing file paths)
+ - What goes wrong if the assumption is incorrect
+ - Confidence level (Confident / Likely / Unclear)
+4. **Confirm or correct** — User reviews assumptions, selects any that need changing
+5. **Write CONTEXT.md** — Identical output format to discuss mode
+
+## Flag Compatibility
+
+| Flag | `discuss` mode | `assumptions` mode |
+|------|----------------|-------------------|
+| `--auto` | Auto-selects recommended answers | Skips confirm gate, auto-resolves Unclear items |
+| `--batch` | Groups questions in batches | N/A (corrections already batched) |
+| `--text` | Plain-text questions (remote sessions) | Plain-text questions (remote sessions) |
+| `--analyze` | Shows trade-off tables per question | N/A (assumptions include evidence) |
+
+## Output
+
+Both modes produce identical CONTEXT.md with the same 6 sections:
+- `` — Phase boundary
+- `` — Locked implementation decisions
+- `` — Specs/docs downstream agents must read
+- `` — Reusable assets, patterns, integration points
+- `` — User references and preferences
+- `` — Ideas noted for future phases
+
+Downstream agents (researcher, planner, checker) consume this identically regardless of mode.
diff --git a/get-shit-done/templates/config.json b/get-shit-done/templates/config.json
index 6b8b46064..f730fa68b 100644
--- a/get-shit-done/templates/config.json
+++ b/get-shit-done/templates/config.json
@@ -6,7 +6,8 @@
"plan_check": true,
"verifier": true,
"auto_advance": false,
- "nyquist_validation": true
+ "nyquist_validation": true,
+ "discuss_mode": "discuss"
},
"planning": {
"commit_docs": true,
diff --git a/get-shit-done/workflows/discuss-phase-assumptions.md b/get-shit-done/workflows/discuss-phase-assumptions.md
new file mode 100644
index 000000000..26d51a31b
--- /dev/null
+++ b/get-shit-done/workflows/discuss-phase-assumptions.md
@@ -0,0 +1,645 @@
+
+Extract implementation decisions that downstream agents need — using codebase-first analysis
+and assumption surfacing instead of interview-style questioning.
+
+You are a thinking partner, not an interviewer. Analyze the codebase deeply, surface what you
+believe based on evidence, and ask the user only to correct what's wrong.
+
+
+
+**CONTEXT.md feeds into:**
+
+1. **gsd-phase-researcher** — Reads CONTEXT.md to know WHAT to research
+2. **gsd-planner** — Reads CONTEXT.md to know WHAT decisions are locked
+
+**Your job:** Capture decisions clearly enough that downstream agents can act on them
+without asking the user again. Output is identical to discuss mode — same CONTEXT.md format.
+
+
+
+**Assumptions mode philosophy:**
+
+The user is a visionary, not a codebase archaeologist. They need enough context to evaluate
+whether your assumptions match their intent — not to answer questions you could figure out
+by reading the code.
+
+- Read the codebase FIRST, form opinions SECOND, ask ONLY about what's genuinely unclear
+- Every assumption must cite evidence (file paths, patterns found)
+- Every assumption must state consequences if wrong
+- Minimize user interactions: ~2-4 corrections vs ~15-20 questions
+
+
+
+**CRITICAL: No scope creep.**
+
+The phase boundary comes from ROADMAP.md and is FIXED. Discussion clarifies HOW to implement
+what's scoped, never WHETHER to add new capabilities.
+
+When user suggests scope creep:
+"[Feature X] would be a new capability — that's its own phase.
+Want me to note it for the roadmap backlog? For now, let's focus on [phase domain]."
+
+Capture the idea in "Deferred Ideas". Don't lose it, don't act on it.
+
+
+
+**IMPORTANT: Answer validation** — After every AskUserQuestion call, check if the response
+is empty or whitespace-only. If so:
+1. Retry the question once with the same parameters
+2. If still empty, present the options as a plain-text numbered list
+
+**Text mode (`workflow.text_mode: true` in config or `--text` flag):**
+When text mode is active, do not use AskUserQuestion at all. Present every question as a
+plain-text numbered list and ask the user to type their choice number.
+
+
+
+
+
+Phase number from argument (required).
+
+```bash
+INIT=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" init phase-op "${PHASE}")
+if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
+```
+
+Parse JSON for: `commit_docs`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`,
+`phase_slug`, `padded_phase`, `has_research`, `has_context`, `has_plans`, `has_verification`,
+`plan_count`, `roadmap_exists`, `planning_exists`.
+
+**If `phase_found` is false:**
+```
+Phase [X] not found in roadmap.
+
+Use /gsd:progress to see available phases.
+```
+Exit workflow.
+
+**If `phase_found` is true:** Continue to check_existing.
+
+**Auto mode** — If `--auto` is present in ARGUMENTS:
+- In `check_existing`: auto-select "Update it" (if context exists) or continue without prompting
+- In `present_assumptions`: skip confirmation gate, proceed directly to write CONTEXT.md
+- In `correct_assumptions`: auto-select recommended option for each correction
+- Log each auto-selected choice inline
+- After completion, auto-advance to plan-phase
+
+
+
+Check if CONTEXT.md already exists using `has_context` from init.
+
+```bash
+ls ${phase_dir}/*-CONTEXT.md 2>/dev/null
+```
+
+**If exists:**
+
+**If `--auto`:** Auto-select "Update it". Log: `[auto] Context exists — updating with assumption-based analysis.`
+
+**Otherwise:** Use AskUserQuestion:
+- header: "Context"
+- question: "Phase [X] already has context. What do you want to do?"
+- options:
+ - "Update it" — Re-analyze codebase and refresh assumptions
+ - "View it" — Show me what's there
+ - "Skip" — Use existing context as-is
+
+If "Update": Load existing, continue to load_prior_context
+If "View": Display CONTEXT.md, then offer update/skip
+If "Skip": Exit workflow
+
+**If doesn't exist:**
+
+Check `has_plans` and `plan_count` from init. **If `has_plans` is true:**
+
+**If `--auto`:** Auto-select "Continue and replan after". Log: `[auto] Plans exist — continuing with assumption analysis, will replan after.`
+
+**Otherwise:** Use AskUserQuestion:
+- header: "Plans exist"
+- question: "Phase [X] already has {plan_count} plan(s) created without user context. Your decisions here won't affect existing plans unless you replan."
+- options:
+ - "Continue and replan after"
+ - "View existing plans"
+ - "Cancel"
+
+If "Continue and replan after": Continue to load_prior_context.
+If "View existing plans": Display plan files, then offer "Continue" / "Cancel".
+If "Cancel": Exit workflow.
+
+**If `has_plans` is false:** Continue to load_prior_context.
+
+
+
+Read project-level and prior phase context to avoid re-asking decided questions.
+
+**Step 1: Read project-level files**
+```bash
+cat .planning/PROJECT.md 2>/dev/null
+cat .planning/REQUIREMENTS.md 2>/dev/null
+cat .planning/STATE.md 2>/dev/null
+```
+
+Extract from these:
+- **PROJECT.md** — Vision, principles, non-negotiables, user preferences
+- **REQUIREMENTS.md** — Acceptance criteria, constraints
+- **STATE.md** — Current progress, any flags
+
+**Step 2: Read all prior CONTEXT.md files**
+```bash
+find .planning/phases -name "*-CONTEXT.md" 2>/dev/null | sort
+```
+
+For each CONTEXT.md where phase number < current phase:
+- Read the `` section — these are locked preferences
+- Read `` — particular references or "I want it like X" moments
+- Note patterns (e.g., "user consistently prefers minimal UI")
+
+**Step 3: Build internal `` context**
+
+Structure the extracted information for use in assumption generation.
+
+**If no prior context exists:** Continue without — expected for early phases.
+
+
+
+Check if any pending todos are relevant to this phase's scope.
+
+```bash
+TODO_MATCHES=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" todo match-phase "${PHASE_NUMBER}")
+```
+
+Parse JSON for: `todo_count`, `matches[]`.
+
+**If `todo_count` is 0:** Skip silently.
+
+**If matches found:** Present matched todos, use AskUserQuestion (multiSelect) to fold relevant ones into scope.
+
+**For selected (folded) todos:** Store as `` for CONTEXT.md `` section.
+**For unselected:** Store as `` for CONTEXT.md `` section.
+
+**Auto mode (`--auto`):** Fold all todos with score >= 0.4 automatically. Log the selection.
+
+
+
+Lightweight scan of existing code to inform assumption generation.
+
+**Step 1: Check for existing codebase maps**
+```bash
+ls .planning/codebase/*.md 2>/dev/null
+```
+
+**If codebase maps exist:** Read relevant ones (CONVENTIONS.md, STRUCTURE.md, STACK.md). Extract reusable components, patterns, integration points. Skip to Step 3.
+
+**Step 2: If no codebase maps, do targeted grep**
+
+Extract key terms from phase goal, search for related files.
+
+```bash
+grep -rl "{term1}\|{term2}" src/ app/ --include="*.ts" --include="*.tsx" 2>/dev/null | head -10
+```
+
+Read the 3-5 most relevant files.
+
+**Step 3: Build internal ``**
+
+Identify reusable assets, established patterns, integration points, and creative options. Store internally for use in deep_codebase_analysis.
+
+
+
+Spawn a `gsd-assumptions-analyzer` agent to deeply analyze the codebase for this phase. This
+keeps raw file contents out of the main context window, protecting token budget.
+
+**Resolve calibration tier (if USER-PROFILE.md exists):**
+
+```bash
+PROFILE_PATH="$HOME/.claude/get-shit-done/USER-PROFILE.md"
+```
+
+If file exists at PROFILE_PATH:
+- Priority 1: Read config.json > preferences.vendor_philosophy (project-level override)
+- Priority 2: Read USER-PROFILE.md Vendor Choices/Philosophy rating (global)
+- Priority 3: Default to "standard"
+
+Map to calibration tier:
+- conservative OR thorough-evaluator → full_maturity (more alternatives, detailed evidence)
+- opinionated → minimal_decisive (fewer alternatives, decisive recommendations)
+- pragmatic-fast OR any other value → standard
+
+If no USER-PROFILE.md: calibration_tier = "standard"
+
+**Spawn Explore subagent:**
+
+```
+Task(subagent_type="gsd-assumptions-analyzer", prompt="""
+Analyze the codebase for Phase {PHASE}: {phase_name}.
+
+Phase goal: {roadmap_description}
+Prior decisions: {prior_decisions_summary}
+Codebase scout hints: {codebase_context_summary}
+Calibration: {calibration_tier}
+
+Your job:
+1. Read ROADMAP.md phase {PHASE} description
+2. Read any prior CONTEXT.md files from earlier phases
+3. Glob/Grep for files related to: {phase_relevant_terms}
+4. Read 5-15 most relevant source files
+5. Return structured assumptions
+
+## Output Format
+
+Return EXACTLY this structure:
+
+## Assumptions
+
+### [Area Name] (e.g., "Technical Approach")
+- **Assumption:** [Decision statement]
+ - **Why this way:** [Evidence from codebase — cite file paths]
+ - **If wrong:** [Concrete consequence of this being wrong]
+ - **Confidence:** Confident | Likely | Unclear
+
+(3-5 areas, calibrated by tier:
+- full_maturity: 3-5 areas, 2-3 alternatives per Likely/Unclear item
+- standard: 3-4 areas, 2 alternatives per Likely/Unclear item
+- minimal_decisive: 2-3 areas, decisive single recommendation per item)
+
+## Needs External Research
+[Topics where codebase alone is insufficient — library version compatibility,
+ecosystem best practices, etc. Leave empty if codebase provides enough evidence.]
+""")
+```
+
+Parse the subagent's response. Extract:
+- `assumptions[]` — each with area, statement, evidence, consequence, confidence
+- `needs_research[]` — topics requiring external research (may be empty)
+
+**Initialize canonical refs accumulator:**
+- Source 1: Copy `Canonical refs:` from ROADMAP.md for this phase, expand to full paths
+- Source 2: Check REQUIREMENTS.md and PROJECT.md for specs/ADRs referenced
+- Source 3: Add any docs referenced in codebase scout results
+
+
+
+**Skip if:** `needs_research` from deep_codebase_analysis is empty.
+
+If research topics were flagged, spawn a general-purpose research agent:
+
+```
+Task(subagent_type="general-purpose", prompt="""
+Research the following topics for Phase {PHASE}: {phase_name}.
+
+Topics needing research:
+{needs_research_content}
+
+For each topic, return:
+- **Finding:** [What you learned]
+- **Source:** [URL or library docs reference]
+- **Confidence impact:** [Which assumption this resolves and to what confidence level]
+
+Use Context7 (resolve-library-id then query-docs) for library-specific questions.
+Use WebSearch for ecosystem/best-practice questions.
+""")
+```
+
+Merge findings back into assumptions:
+- Update confidence levels where research resolves ambiguity
+- Add source attribution to affected assumptions
+- Store research findings for DISCUSSION-LOG.md
+
+**If no gaps flagged:** Skip entirely. Most phases will skip this step.
+
+
+
+Display all assumptions grouped by area with confidence badges.
+
+**Format for display:**
+
+```
+## Phase {PHASE}: {phase_name} — Assumptions
+
+Based on codebase analysis, here's what I'd go with:
+
+### {Area Name}
+{Confidence badge} **{Assumption statement}**
+↳ Evidence: {file paths cited}
+↳ If wrong: {consequence}
+
+### {Area Name 2}
+...
+
+[If external research was done:]
+### External Research Applied
+- {Topic}: {Finding} (Source: {URL})
+```
+
+**If `--auto`:**
+- If all assumptions are Confident or Likely: log assumptions, skip to write_context.
+ Log: `[auto] All assumptions Confident/Likely — proceeding to context capture.`
+- If any assumptions are Unclear: log a warning, auto-select recommended alternative for
+ each Unclear item. Log: `[auto] {N} Unclear assumptions auto-resolved with recommended defaults.`
+ Proceed to write_context.
+
+**Otherwise:** Use AskUserQuestion:
+- header: "Assumptions"
+- question: "These all look right?"
+- options:
+ - "Yes, proceed" — Write CONTEXT.md with these assumptions as decisions
+ - "Let me correct some" — Select which assumptions to change
+
+**If "Yes, proceed":** Skip to write_context.
+**If "Let me correct some":** Continue to correct_assumptions.
+
+
+
+The assumptions are already displayed above from present_assumptions.
+
+Present a multiSelect where each option's label is the assumption statement and description
+is the "If wrong" consequence:
+
+Use AskUserQuestion (multiSelect):
+- header: "Corrections"
+- question: "Which assumptions need correcting?"
+- options: [one per assumption, label = assumption statement, description = "If wrong: {consequence}"]
+
+For each selected correction, ask ONE focused question:
+
+Use AskUserQuestion:
+- header: "{Area Name}"
+- question: "What should we do instead for: {assumption statement}?"
+- options: [2-3 concrete alternatives describing user-visible outcomes, recommended option first]
+
+Record each correction:
+- Original assumption
+- User's chosen alternative
+- Reason (if provided via "Other" free text)
+
+After all corrections processed, continue to write_context with updated assumptions.
+
+**Auto mode:** Should not reach this step (--auto skips from present_assumptions).
+
+
+
+Create phase directory if needed. Write CONTEXT.md using the standard 6-section format.
+
+**File:** `${phase_dir}/${padded_phase}-CONTEXT.md`
+
+Map assumptions to CONTEXT.md sections:
+- Assumptions → `` (each assumption becomes a locked decision: D-01, D-02, etc.)
+- Corrections → override the original assumption in ``
+- Areas where all assumptions were Confident → marked as locked decisions
+- Areas with corrections → include user's chosen alternative as the decision
+- Folded todos → included in `` under "### Folded Todos"
+
+```markdown
+# Phase {PHASE}: {phase_name} - Context
+
+**Gathered:** {date} (assumptions mode)
+**Status:** Ready for planning
+
+
+## Phase Boundary
+
+{Domain boundary from ROADMAP.md — clear statement of scope anchor}
+
+
+
+## Implementation Decisions
+
+### {Area Name 1}
+- **D-01:** {Decision — from assumption or correction}
+- **D-02:** {Decision}
+
+### {Area Name 2}
+- **D-03:** {Decision}
+
+### Claude's Discretion
+{Any assumptions where the user confirmed "you decide" or left as-is with Likely confidence}
+
+### Folded Todos
+{If any todos were folded into scope}
+
+
+
+## Canonical References
+
+**Downstream agents MUST read these before planning or implementing.**
+
+{Accumulated canonical refs from analyze step — full relative paths}
+
+[If no external specs: "No external specs — requirements fully captured in decisions above"]
+
+
+
+## Existing Code Insights
+
+### Reusable Assets
+{From codebase scout + Explore subagent findings}
+
+### Established Patterns
+{Patterns that constrain/enable this phase}
+
+### Integration Points
+{Where new code connects to existing system}
+
+
+
+## Specific Ideas
+
+{Any particular references from corrections or user input}
+
+[If none: "No specific requirements — open to standard approaches"]
+
+
+
+## Deferred Ideas
+
+{Ideas mentioned during corrections that are out of scope}
+
+### Reviewed Todos (not folded)
+{Todos reviewed but not folded — with reason}
+
+[If none: "None — analysis stayed within phase scope"]
+
+```
+
+Write file.
+
+
+
+Write audit trail of assumptions and corrections.
+
+**File:** `${phase_dir}/${padded_phase}-DISCUSSION-LOG.md`
+
+```markdown
+# Phase {PHASE}: {phase_name} - Discussion Log (Assumptions Mode)
+
+> **Audit trail only.** Do not use as input to planning, research, or execution agents.
+> Decisions captured in CONTEXT.md — this log preserves the analysis.
+
+**Date:** {ISO date}
+**Phase:** {padded_phase}-{phase_name}
+**Mode:** assumptions
+**Areas analyzed:** {comma-separated area names}
+
+## Assumptions Presented
+
+### {Area Name}
+| Assumption | Confidence | Evidence |
+|------------|-----------|----------|
+| {Statement} | {Confident/Likely/Unclear} | {file paths} |
+
+{Repeat for each area}
+
+## Corrections Made
+
+{If corrections were made:}
+
+### {Area Name}
+- **Original assumption:** {what Claude assumed}
+- **User correction:** {what the user chose instead}
+- **Reason:** {user's rationale, if provided}
+
+{If no corrections: "No corrections — all assumptions confirmed."}
+
+## Auto-Resolved
+
+{If --auto and Unclear items existed:}
+- {Assumption}: auto-selected {recommended option}
+
+{If not applicable: omit this section}
+
+## External Research
+
+{If research was performed:}
+- {Topic}: {Finding} (Source: {URL})
+
+{If no research: omit this section}
+```
+
+Write file.
+
+
+
+Commit phase context and discussion log:
+
+```bash
+node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" commit "docs(${padded_phase}): capture phase context (assumptions mode)" --files "${phase_dir}/${padded_phase}-CONTEXT.md" "${phase_dir}/${padded_phase}-DISCUSSION-LOG.md"
+```
+
+Confirm: "Committed: docs(${padded_phase}): capture phase context (assumptions mode)"
+
+
+
+Update STATE.md with session info:
+
+```bash
+node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" state record-session \
+ --stopped-at "Phase ${PHASE} context gathered (assumptions mode)" \
+ --resume-file "${phase_dir}/${padded_phase}-CONTEXT.md"
+```
+
+Commit STATE.md:
+
+```bash
+node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" commit "docs(state): record phase ${PHASE} context session" --files .planning/STATE.md
+```
+
+
+
+Present summary and next steps:
+
+```
+Created: .planning/phases/${PADDED_PHASE}-${SLUG}/${PADDED_PHASE}-CONTEXT.md
+
+## Decisions Captured (Assumptions Mode)
+
+### {Area Name}
+- {Key decision} (from assumption / corrected)
+
+{Repeat per area}
+
+[If corrections were made:]
+## Corrections Applied
+- {Area}: {original} → {corrected}
+
+[If deferred ideas exist:]
+## Noted for Later
+- {Deferred idea} — future phase
+
+---
+
+## ▶ Next Up
+
+**Phase ${PHASE}: {phase_name}** — {Goal from ROADMAP.md}
+
+`/gsd:plan-phase ${PHASE}`
+
+`/clear` first → fresh context window
+
+---
+
+**Also available:**
+- `/gsd:plan-phase ${PHASE} --skip-research` — plan without research
+- `/gsd:ui-phase ${PHASE}` — generate UI design contract (if frontend work)
+- Review/edit CONTEXT.md before continuing
+
+---
+```
+
+
+
+Check for auto-advance trigger:
+
+1. Parse `--auto` flag from $ARGUMENTS
+2. Sync chain flag:
+ ```bash
+ if [[ ! "$ARGUMENTS" =~ --auto ]]; then
+ node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-set workflow._auto_chain_active false 2>/dev/null
+ fi
+ ```
+3. Read chain flag and user preference:
+ ```bash
+ AUTO_CHAIN=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow._auto_chain_active 2>/dev/null || echo "false")
+ AUTO_CFG=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow.auto_advance 2>/dev/null || echo "false")
+ ```
+
+**If `--auto` flag present AND `AUTO_CHAIN` is not true:**
+```bash
+node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-set workflow._auto_chain_active true
+```
+
+**If `--auto` flag present OR `AUTO_CHAIN` is true OR `AUTO_CFG` is true:**
+
+Display banner:
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► AUTO-ADVANCING TO PLAN
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Context captured (assumptions mode). Launching plan-phase...
+```
+
+Launch: `Skill(skill="gsd:plan-phase", args="${PHASE} --auto")`
+
+Handle return: PHASE COMPLETE / PLANNING COMPLETE / INCONCLUSIVE / GAPS FOUND
+(identical handling to discuss-phase.md auto_advance step)
+
+**If neither `--auto` nor config enabled:**
+Route to confirm_creation step.
+
+
+
+
+
+- Phase validated against roadmap
+- Prior context loaded (no re-asking decided questions)
+- Codebase deeply analyzed via Explore subagent (5-15 files read)
+- Assumptions surfaced with evidence and confidence levels
+- User confirmed or corrected assumptions (~2-4 interactions max)
+- Scope creep redirected to deferred ideas
+- CONTEXT.md captures actual decisions (identical format to discuss mode)
+- CONTEXT.md includes canonical_refs with full file paths (MANDATORY)
+- CONTEXT.md includes code_context from codebase analysis
+- DISCUSSION-LOG.md records assumptions and corrections as audit trail
+- STATE.md updated with session info
+- User knows next steps
+
diff --git a/get-shit-done/workflows/plan-phase.md b/get-shit-done/workflows/plan-phase.md
index a8de7b37b..f30140e5a 100644
--- a/get-shit-done/workflows/plan-phase.md
+++ b/get-shit-done/workflows/plan-phase.md
@@ -187,11 +187,19 @@ If `context_path` is not null, display: `Using phase context from: ${context_pat
**If `context_path` is null (no CONTEXT.md exists):**
+Read discuss mode for context gate label:
+```bash
+DISCUSS_MODE=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow.discuss_mode 2>/dev/null || echo "discuss")
+```
+
Use AskUserQuestion:
- header: "No context"
- question: "No CONTEXT.md found for Phase {X}. Plans will use research and requirements only — your design preferences won't be included. Continue or capture context first?"
- options:
- "Continue without context" — Plan using research + requirements only
+ If `DISCUSS_MODE` is `"assumptions"`:
+ - "Gather context (assumptions mode)" — Analyze codebase and surface assumptions before planning
+ If `DISCUSS_MODE` is `"discuss"` (or unset):
- "Run discuss-phase first" — Capture design decisions before planning
If "Continue without context": Proceed to step 5.
diff --git a/get-shit-done/workflows/progress.md b/get-shit-done/workflows/progress.md
index c0ba54a65..58b7a8ca9 100644
--- a/get-shit-done/workflows/progress.md
+++ b/get-shit-done/workflows/progress.md
@@ -18,6 +18,10 @@ if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
Extract from init JSON: `project_exists`, `roadmap_exists`, `state_exists`, `phases`, `current_phase`, `next_phase`, `milestone_version`, `completed_count`, `phase_count`, `paused_at`, `state_path`, `roadmap_path`, `project_path`, `config_path`.
+```bash
+DISCUSS_MODE=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow.discuss_mode 2>/dev/null || echo "discuss")
+```
+
If `project_exists` is false (no `.planning/` directory):
```
@@ -99,6 +103,7 @@ Present:
**Progress:** {PROGRESS_BAR}
**Profile:** [quality/balanced/budget/inherit]
+**Discuss mode:** {DISCUSS_MODE}
## Recent Work
- [Phase X, Plan Y]: [what was accomplished - 1 line from summary-extract]
diff --git a/tests/copilot-install.test.cjs b/tests/copilot-install.test.cjs
index 297a94047..ad8185ea2 100644
--- a/tests/copilot-install.test.cjs
+++ b/tests/copilot-install.test.cjs
@@ -746,10 +746,10 @@ describe('Copilot agent conversion - real files', () => {
assert.ok(toolsLine.includes("'read'"), 'Read mapped');
});
- test('all 17 agents convert without error', () => {
+ test('all 18 agents convert without error', () => {
const agents = fs.readdirSync(agentsSrc)
.filter(f => f.startsWith('gsd-') && f.endsWith('.md'));
- assert.strictEqual(agents.length, 17, `expected 17 agents, got ${agents.length}`);
+ assert.strictEqual(agents.length, 18, `expected 18 agents, got ${agents.length}`);
for (const agentFile of agents) {
const content = fs.readFileSync(path.join(agentsSrc, agentFile), 'utf8');
@@ -1120,7 +1120,7 @@ const crypto = require('crypto');
const INSTALL_PATH = path.join(__dirname, '..', 'bin', 'install.js');
const EXPECTED_SKILLS = 53;
-const EXPECTED_AGENTS = 17;
+const EXPECTED_AGENTS = 18;
function runCopilotInstall(cwd) {
const env = { ...process.env };
@@ -1189,6 +1189,7 @@ describe('E2E: Copilot full install verification', () => {
const gsdAgents = files.filter(f => f.startsWith('gsd-') && f.endsWith('.agent.md')).sort();
const expected = [
'gsd-advisor-researcher.agent.md',
+ 'gsd-assumptions-analyzer.agent.md',
'gsd-codebase-mapper.agent.md',
'gsd-debugger.agent.md',
'gsd-executor.agent.md',
diff --git a/tests/discuss-mode.test.cjs b/tests/discuss-mode.test.cjs
new file mode 100644
index 000000000..97d2e3dec
--- /dev/null
+++ b/tests/discuss-mode.test.cjs
@@ -0,0 +1,101 @@
+/**
+ * Discuss Mode Config Tests
+ *
+ * Validates workflow.discuss_mode config, routing, and assumptions workflow integration.
+ */
+
+const { test, describe } = require('node:test');
+const assert = require('node:assert');
+const fs = require('fs');
+const path = require('path');
+
+describe('workflow.discuss_mode config', () => {
+ test('config template includes discuss_mode default', () => {
+ const template = JSON.parse(
+ fs.readFileSync(path.join(__dirname, '..', 'get-shit-done', 'templates', 'config.json'), 'utf8')
+ );
+ assert.strictEqual(template.workflow.discuss_mode, 'discuss');
+ });
+
+ test('discuss-phase command references both workflow files', () => {
+ const command = fs.readFileSync(
+ path.join(__dirname, '..', 'commands', 'gsd', 'discuss-phase.md'), 'utf8'
+ );
+ assert.ok(command.includes('discuss-phase-assumptions.md'), 'should reference assumptions workflow');
+ assert.ok(command.includes('discuss-phase.md'), 'should reference discuss workflow');
+ assert.ok(command.includes('workflow.discuss_mode'), 'should reference config key');
+ });
+
+ test('discuss-phase command argument-hint includes --text', () => {
+ const command = fs.readFileSync(
+ path.join(__dirname, '..', 'commands', 'gsd', 'discuss-phase.md'), 'utf8'
+ );
+ assert.ok(command.includes('--text'), 'argument-hint should include --text');
+ });
+
+ test('assumptions workflow file exists and has required steps', () => {
+ const workflow = fs.readFileSync(
+ path.join(__dirname, '..', 'get-shit-done', 'workflows', 'discuss-phase-assumptions.md'), 'utf8'
+ );
+ const requiredSteps = [
+ 'initialize', 'check_existing', 'load_prior_context',
+ 'deep_codebase_analysis', 'present_assumptions', 'correct_assumptions',
+ 'write_context', 'write_discussion_log', 'auto_advance'
+ ];
+ for (const step of requiredSteps) {
+ assert.ok(workflow.includes(` {
+ const workflow = fs.readFileSync(
+ path.join(__dirname, '..', 'get-shit-done', 'workflows', 'discuss-phase-assumptions.md'), 'utf8'
+ );
+ const sections = ['', '', '', '', '', ''];
+ for (const section of sections) {
+ assert.ok(workflow.includes(section), `missing CONTEXT.md section: ${section}`);
+ }
+ });
+
+ test('plan-phase gate references discuss_mode config', () => {
+ const planPhase = fs.readFileSync(
+ path.join(__dirname, '..', 'get-shit-done', 'workflows', 'plan-phase.md'), 'utf8'
+ );
+ assert.ok(planPhase.includes('workflow.discuss_mode'), 'should reference config key');
+ assert.ok(planPhase.includes('assumptions mode'), 'should mention assumptions mode');
+ });
+
+ test('assumptions workflow handles --auto flag', () => {
+ const workflow = fs.readFileSync(
+ path.join(__dirname, '..', 'get-shit-done', 'workflows', 'discuss-phase-assumptions.md'), 'utf8'
+ );
+ assert.ok(workflow.includes('--auto'), 'should handle --auto');
+ assert.ok(workflow.includes('auto-select'), 'should auto-select in --auto mode');
+ assert.ok(workflow.includes('auto_advance'), 'should support auto_advance');
+ });
+
+ test('assumptions workflow handles --text flag', () => {
+ const workflow = fs.readFileSync(
+ path.join(__dirname, '..', 'get-shit-done', 'workflows', 'discuss-phase-assumptions.md'), 'utf8'
+ );
+ assert.ok(workflow.includes('text_mode'), 'should reference text_mode config');
+ assert.ok(workflow.includes('--text'), 'should handle --text flag');
+ });
+
+ test('progress workflow references discuss_mode', () => {
+ const progress = fs.readFileSync(
+ path.join(__dirname, '..', 'get-shit-done', 'workflows', 'progress.md'), 'utf8'
+ );
+ assert.ok(progress.includes('workflow.discuss_mode'), 'should read discuss_mode config');
+ assert.ok(progress.includes('Discuss mode'), 'should display discuss mode');
+ });
+
+ test('documentation file exists', () => {
+ const docPath = path.join(__dirname, '..', 'docs', 'workflow-discuss-mode.md');
+ assert.ok(fs.existsSync(docPath), 'docs/workflow-discuss-mode.md should exist');
+ const doc = fs.readFileSync(docPath, 'utf8');
+ assert.ok(doc.includes('assumptions'), 'doc should mention assumptions');
+ assert.ok(doc.includes('discuss'), 'doc should mention discuss');
+ assert.ok(doc.includes('config-set'), 'doc should show how to configure');
+ });
+});