@opengsd/gsd-core 1.6.1 → 1.7.0-rc.2

package/gsd-core/workflows/autonomous.md

@@ -61,7 +61,7 @@ fi
 
 When `--only` is set, also set `FROM_PHASE` to the same value so existing filter logic applies.
 
-When `--interactive` is set, discuss runs inline with questions. On Codex, where a backgrounded agent can still spawn subagents, plan and execute are dispatched as background agents — keeping the main context lean (only discuss conversations accumulate) and enabling overlap. On every other runtime (Claude Code and all other non-Codex runtimes), backgrounded agents cannot reliably nest subagents, so plan and execute run inline to preserve worktree isolation and independent verification, and phases run sequentially with their work accumulating in the main context. Either way, user input is preserved on all design decisions.
+When `--interactive` is set, discuss stays inline. If `dispatch-should-flatten` returns `false`, dispatch plan and execute as background agents; if it returns `true`, run them inline and keep phases sequential. Preserve user input on all design decisions.
 
 When `PLAN_STRATEGY=converge`, the planning step MUST invoke the plan-review convergence workflow instead of `gsd-plan-phase`. `--cross-ai` is an alias for `--converge`. Forward `CONVERGENCE_ARGS` exactly as parsed so reviewer flags and `--max-cycles N` retain the same meaning as they have on `/gsd:plan-review-convergence`.
 
@@ -114,6 +114,8 @@ If `TO_PHASE` is set, display: `Stopping after phase ${TO_PHASE}`
 If `INTERACTIVE` is set, display: `Mode: Interactive (discuss inline, plan+execute inline — background on Codex only)`
 If `PLAN_STRATEGY` is `converge`, display: `Planning: Plan-review convergence enabled`
 
+**Agent skills (delegated agents self-load):** This workflow delegates plan/execute/review via flat `Skill()` invocations rather than resolving `agent_skills` itself. Each consumer agent (`gsd-planner`, `gsd-executor`, `gsd-plan-checker`, `gsd-verifier`, …) self-loads its configured `.planning/config.json` `agent_skills` in its own mandatory init step per `@~/.claude/gsd-core/references/agent-skills-bootstrap.md`. This is the durable path that works on every runtime — including Cursor, where `Skill()`-delegated workflow bash init does not reliably execute. No per-delegation injection is needed here. See open-gsd/gsd-core#1866.
+
 </step>
 
 <step name="discover_phases">
@@ -125,10 +127,17 @@ Run phase discovery:
 ```bash
 INIT_MANAGER=$(gsd_run query init.manager)
 if [[ "$INIT_MANAGER" == @file:* ]]; then INIT_MANAGER=$(cat "${INIT_MANAGER#@file:}"); fi
+STATE_CONTENT=$(cat .planning/STATE.md 2>/dev/null || true)
 ```
 
 Parse the JSON `phases` array.
 
+Parse the optional `## Deferred Verification` table from `STATE_CONTENT` into a phase-number map:
+- `verification_deferred_human` -> `/gsd:verify-work <phase>`
+- `verification_deferred_gaps` -> `/gsd:plan-phase <phase> --gaps`
+
+**Skip deferred phases on autonomous re-entry:** drop any phase whose number appears in the deferred-phase map from this run's queue; resume it only through the recorded command.
+
 **Filter to incomplete phases:** Keep `phase_complete !== true`, including implemented phases with `verification_status !== "passed"`.
 
 **Apply `--from N`:** If set, filter out phases where `number < FROM_PHASE` (numeric compare; handles "5.1").
@@ -180,6 +189,8 @@ Exit cleanly.
 | 8 | Lifecycle Orchestration | Not Started |
 ```
 
+**If any deferred phases were skipped:** display `## Deferred Verification (Skipped on Re-entry)` with the skipped rows and resume commands, then omit them from this run's queue.
+
 **Fetch details for each phase:**
 
 ```bash
@@ -202,9 +213,7 @@ For the current phase, display the progress banner:
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 ```
 
-Where N = current phase number (from the ROADMAP, e.g., 63), T = total milestone phases (from `phase_count` parsed in initialize step, e.g., 67). **Important:** T must be `phase_count` (the total number of phases in this milestone), NOT the count of remaining/incomplete phases. When phases are numbered 61-67, T=7 and the banner should read `Phase 63/7` (phase 63, 7 total in milestone), not `Phase 63/3` (which would confuse 3 remaining with 3 total). P = percentage of all milestone phases completed so far. Calculate P as: (number of phases with `disk_status` "complete" from the latest `roadmap analyze` / T × 100). Use █ for filled and ░ for empty segments in the progress bar (8 characters wide).
-
-**Alternative display when phase numbers exceed total** (e.g., multi-milestone projects where phases are numbered globally): If N > T (phase number exceeds milestone phase count), use the format `Phase {N} ({position}/{T})` where `position` is the 1-based index of this phase among incomplete phases being processed. This prevents confusing displays like "Phase 63/5".
+Where N is the ROADMAP phase number, T is the milestone `phase_count`, and P = completed milestone phases / T × 100. Use `phase_count`, not remaining phases: phase 63 in a 7-phase milestone is `Phase 63/7`, not `Phase 63/3`. If N > T, render `Phase {N} ({position}/{T})`. Use an 8-character bar with █ and ░.
 
 **3a. Smart Discuss**
 
@@ -358,13 +367,13 @@ UI_SPEC_FILE=$(ls "${PHASE_DIR}"/*-UI-SPEC.md 2>/dev/null | head -1)
 
 **3b. Plan**
 
-**If `INTERACTIVE` is set:** Background dispatch is only safe on a runtime where a backgrounded agent can still nest the pipeline's subagents (plan-checker / worktree executors / verifier). Among supported runtimes only **Codex** (`spawn_agent`) can do this; Claude Code's backgrounded agents have no `Agent`/`Task` tool, and every other runtime either prohibits nested subagents or disables them by default. So run **inline** everywhere except Codex, which is dispatched in the background. Resolve the runtime first:
+**If `INTERACTIVE` is set:** Background dispatch is only safe on a runtime where a backgrounded agent can still nest the pipeline's subagents (plan-checker / worktree executors / verifier). This is determined from the documentation-sourced dispatch capability in the registry (#1708); Claude Code's backgrounded agents have no `Agent`/`Task` tool, and every other runtime either prohibits nested subagents or disables them by default. So run **inline** everywhere except where `dispatch-should-flatten` returns `false`. Resolve first:
 
 ```bash
-RUNTIME=$(gsd_run query config-get runtime --default claude --raw 2>/dev/null || echo "claude")
+FLATTEN=$(gsd_run query dispatch-should-flatten --raw 2>/dev/null || echo "true")
 ```
 
-- **If `RUNTIME` is `codex`:** Dispatch plan as a background agent to keep the main context lean. While plan runs, the workflow can immediately start discussing the next phase (see step 4).
+- **If `FLATTEN` is `false`:** Dispatch plan as a background agent to keep the main context lean. While plan runs, the workflow can immediately start discussing the next phase (see step 4).
 
   - If `PLAN_STRATEGY=converge`, print: `◆ Spawning background plan-convergence loop for phase ${PHASE_NUM}... (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)`
 
@@ -388,7 +397,7 @@ RUNTIME=$(gsd_run query config-get runtime --default claude --raw 2>/dev/null ||
 
   Store the agent task_id. After discuss for the next phase completes (or if no next phase), wait for the plan agent to finish before proceeding to execute.
 
-- **Otherwise (Claude Code or any other non-Codex runtime):** Run plan **inline** (do NOT background) so the plan-checker runs. The next phase's discuss does not overlap planning here — correctness over overlap.
+- **Otherwise (`FLATTEN` is `true` — run inline):** Run plan **inline** (do NOT background) so the plan-checker runs. The next phase's discuss does not overlap planning here — correctness over overlap.
 
   - If `PLAN_STRATEGY=converge`:
 
@@ -420,13 +429,13 @@ Verify plan produced output — re-run `init phase-op` and check `has_plans`. If
 
 **3c. Execute**
 
-**If `INTERACTIVE` is set:** Wait for the plan agent to complete (if not already) and verify plans exist. Background dispatch is only safe on a runtime where a backgrounded agent can still nest the pipeline's subagents (plan-checker / worktree executors / verifier). Among supported runtimes only **Codex** (`spawn_agent`) can do this; Claude Code's backgrounded agents have no `Agent`/`Task` tool, and every other runtime either prohibits nested subagents or disables them by default. So run **inline** everywhere except Codex, which is dispatched in the background. Resolve the runtime first:
+**If `INTERACTIVE` is set:** Wait for the plan agent to complete (if not already) and verify plans exist. Background dispatch is only safe on a runtime where a backgrounded agent can still nest the pipeline's subagents (plan-checker / worktree executors / verifier). This is determined from the documentation-sourced dispatch capability in the registry (#1708); Claude Code's backgrounded agents have no `Agent`/`Task` tool, and every other runtime either prohibits nested subagents or disables them by default. So run **inline** everywhere except where `dispatch-should-flatten` returns `false`. Resolve first:
 
 ```bash
-RUNTIME=$(gsd_run query config-get runtime --default claude --raw 2>/dev/null || echo "claude")
+FLATTEN=$(gsd_run query dispatch-should-flatten --raw 2>/dev/null || echo "true")
 ```
 
-- **If `RUNTIME` is `codex`:** Dispatch execute as a background agent:
+- **If `FLATTEN` is `false`:** Dispatch execute as a background agent:
 
 ```
 Agent(
@@ -438,7 +447,7 @@ Agent(
 
   Store the agent task_id. The workflow can now start discussing the next phase while this phase executes in the background. Before starting post-execution routing for this phase, wait for the execute agent to complete.
 
-- **Otherwise (Claude Code or any other non-Codex runtime):** Run execute **inline** (do NOT background) so worktree isolation and verification run:
+- **Otherwise (`FLATTEN` is `true` — run inline):** Run execute **inline** (do NOT background) so worktree isolation and verification run:
 
 ```
 Skill(skill="gsd-execute-phase", args="${PHASE_NUM} --no-transition")
@@ -496,13 +505,7 @@ Display `Phase ${PHASE_NUM} ✅ ${PHASE_NAME} — Verification passed`, run `@~/
 
 **If `human_needed`:**
 
-Read `human_verification` items. In text mode (`--text` or init `text_mode=true`), replace AskUserQuestion with a numbered list and typed choice. Otherwise display items and ask:
-- **question:** "Phase ${PHASE_NUM} has items needing manual verification. Validate now or continue to next phase?"
-- **options:** "Validate now" / "Continue without validation"
-
-On **"Validate now"**: Present items, then ask:
-- **question:** "Validation result?"
-- **options:** "All good — continue" / "Found issues"
+Read `human_verification` items. In text mode (`--text` or init `text_mode=true`), replace AskUserQuestion with a plain-text numbered list. Otherwise ask whether to validate now or continue without validation. If validating now, present items, then ask `Validation result?` with `All good — continue` / `Found issues`.
 
 On "All good — continue": set VERIFICATION frontmatter `status: passed`, display `Phase ${PHASE_NUM} ✅ Human validation passed`, run `@~/.claude/gsd-core/workflows/transition.md`, then iterate.
 
@@ -528,9 +531,7 @@ Read gap score/items from VERIFICATION.md. Display:
 Score: {N}/{M} must-haves verified
 ```
 
-Ask user via AskUserQuestion:
-- **question:** "Gaps found in phase ${PHASE_NUM}. How to proceed?"
-- **options:** "Run gap closure" / "Continue without fixing" / "Stop autonomous mode"
+Ask how to proceed: `Run gap closure` / `Continue without fixing` / `Stop autonomous mode`.
 
 On **"Run gap closure"**: one gap-closure attempt:
 
@@ -554,9 +555,7 @@ If `passed` or `human_needed`: route normally.
 
 If `stale`: handle_blocker: "Stale verification for phase ${PHASE_NUM}."
 
-If still `gaps_found` after this retry: Display "Gaps persist after closure attempt." and ask via AskUserQuestion:
-- **question:** "Gap closure did not fully resolve issues. How to proceed?"
-- **options:** "Continue anyway" / "Stop autonomous mode"
+If still `gaps_found` after this retry, display `Gaps persist after closure attempt.` and ask `Continue anyway` / `Stop autonomous mode`.
 
 On "Continue anyway": record `verification_deferred_gaps` using the table below, display `Phase ${PHASE_NUM} ⏭ verification_deferred_gaps — resume with /gsd:plan-phase ${PHASE_NUM} --gaps`, then handle_blocker: "Verification gaps deferred for phase ${PHASE_NUM}."
 On "Stop autonomous mode": Go to handle_blocker.
@@ -645,13 +644,10 @@ Proceed to lifecycle step (partial completion skips audit/complete/cleanup). Exi
 ```bash
 INIT_MANAGER=$(gsd_run query init.manager)
 if [[ "$INIT_MANAGER" == @file:* ]]; then INIT_MANAGER=$(cat "${INIT_MANAGER#@file:}"); fi
+STATE_CONTENT=$(cat .planning/STATE.md 2>/dev/null || true)
 ```
 
-Re-filter incomplete phases using the same logic as discover_phases:
-- Keep phases where `phase_complete !== true` or `verification_status !== "passed"`
-- Apply `--from N` filter if originally provided
-- Apply `--to N` filter if originally provided
-- Sort by number ascending
+Re-filter incomplete phases using discover_phases logic: keep phases where `phase_complete !== true` or `verification_status !== "passed"`, drop deferred phases from the autonomous queue, re-apply `--from` / `--to`, then sort by number ascending.
 
 Read STATE.md fresh:
 
@@ -663,12 +659,14 @@ Check for blockers in the Blockers/Concerns section. If blockers are found, go t
 
 If incomplete phases remain: proceed to next phase, loop back to execute_phase.
 
-**Interactive mode overlap:** When `INTERACTIVE` is set, the iterate step enables pipeline parallelism **on Codex** (on every other runtime, plan/execute run inline — see 3b/3c — so there is no overlap and phases run sequentially):
+If no runnable phases remain but deferred phases were skipped, display `Autonomous run stopped with deferred verification phases still pending. Resume them with the commands listed in Deferred Verification.` Proceed to lifecycle only if every non-deferred phase is complete; otherwise go to handle_blocker.
+
+**Interactive mode overlap:** When `INTERACTIVE` is set, Codex can overlap discuss for Phase N+1 with background plan+execute for Phase N. Other runtimes keep plan/execute inline, so phases stay sequential:
 1. After discuss completes for Phase N, dispatch plan+execute as background agents
 2. Immediately start discuss for Phase N+1 (the next incomplete phase) while Phase N builds
 3. Before starting plan for Phase N+1, wait for Phase N's execute agent to complete and handle its post-execution routing (verification, gap closure, etc.)
 
-This means the user is always answering discuss questions (lightweight, interactive) while the heavy work (planning, code generation) runs in the background. The main context only accumulates discuss conversations — plan and execute contexts are isolated in their agents. (On Claude Code and all other non-Codex runtimes, plan and execute run inline, so they run sequentially and their work accumulates in the main context.)
+The main context only accumulates discuss conversations; background plan/execute work stays isolated in its agents.
 
 If all phases complete, proceed to lifecycle step.
 

package/gsd-core/workflows/complete-milestone.md

@@ -453,21 +453,17 @@ Extract from result: `version`, `date`, `phases`, `plans`, `tasks`, `accomplishm
 
 Verify: `✅ Milestone archived to .planning/milestones/`
 
-**Phase archival (optional):** After archival completes, ask the user:
+**Phase archival (default-on):** `milestone complete` archives phase directories to `milestones/v[X.Y]-phases/` by default (#1871), so the next `/gsd:new-milestone` never inherits un-archived dirs. No manual `mkdir`/`mv` or `--archive-phases` flag is needed.
 
+If the user explicitly wants to keep phase directories in place as raw execution history, invoke `milestone complete` with `--no-archive-phases`:
 
-**Text mode (`workflow.text_mode: true` in config or `--text` flag):** Set `TEXT_MODE=true` if `--text` is present in `$ARGUMENTS` OR `text_mode` from init JSON is `true`. When TEXT_MODE is active, replace every `AskUserQuestion` call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where `AskUserQuestion` is not available.
-AskUserQuestion(header="Archive Phases", question="Archive phase directories to milestones/?", options: "Yes — move to milestones/v[X.Y]-phases/" | "Skip — keep phases in place")
-
-If "Yes": move phase directories to the milestone archive:
 ```bash
-mkdir -p .planning/milestones/v[X.Y]-phases
-# For each phase directory in .planning/phases/:
-mv .planning/phases/{phase-dir} .planning/milestones/v[X.Y]-phases/
+gsd_run query milestone complete v[X.Y] --no-archive-phases
 ```
-Verify: `✅ Phase directories archived to .planning/milestones/v[X.Y]-phases/`
 
-If "Skip": Phase directories remain in `.planning/phases/` as raw execution history. Use `/gsd:cleanup` later to archive retroactively.
+Verify after a default (archived) completion: `✅ Phase directories archived to .planning/milestones/v[X.Y]-phases/`
+
+**Text mode (`workflow.text_mode: true` in config or `--text` flag):** Set `TEXT_MODE=true` if `--text` is present in `$ARGUMENTS` OR `text_mode` from init JSON is `true`. When TEXT_MODE is active, replace every `AskUserQuestion` call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where `AskUserQuestion` is not available.
 
 After archival, the AI still handles:
 - Reorganizing ROADMAP.md with milestone grouping (requires judgment) — overwrite in place after extracting Backlog section

package/gsd-core/workflows/execute-phase.md

@@ -84,7 +84,7 @@ AGENT_SKILLS=$(gsd_run query agent-skills gsd-executor)
 
 Parse JSON for: `executor_model`, `verifier_model`, `commit_docs`, `parallelization`, `branching_strategy`, `branch_name`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `plans`, `incomplete_plans`, `plan_count`, `incomplete_count`, `state_exists`, `roadmap_exists`, `phase_req_ids`, `response_language`.
 
-**Model resolution:** If `executor_model` is `"inherit"`, omit the `model=` parameter from all `Agent()` calls — do NOT pass `model="inherit"` to Agent. Omitting the `model=` parameter causes Claude Code to inherit the current orchestrator model automatically. Only set `model=` when `executor_model` is an explicit model name (e.g., `"claude-sonnet-4-6"`, `"claude-opus-4-7"`).
+**Model resolution:** If `executor_model` is `"inherit"`, omit the `model=` parameter from all `Agent()` calls — do NOT pass `model="inherit"` to Agent. Omitting the `model=` parameter causes Claude Code to inherit the current orchestrator model automatically. Only set `model=` when `executor_model` is an explicit model name (e.g., `"claude-sonnet-5"`, `"claude-opus-4-8"`).
 
 **If `response_language` is set:** Include `response_language: {value}` in all spawned subagent prompts so any user-facing output stays in the configured language.
 

package/gsd-core/workflows/forensics.md

@@ -273,7 +273,7 @@ gh issue create \
 
 ```bash
 _GSD_SHIM_NAME="gsd-tools.cjs"; _GSD_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"; GSD_TOOLS="${_GSD_RUNTIME_ROOT}/gsd-core/bin/${_GSD_SHIM_NAME}"; if [ -f "$GSD_TOOLS" ]; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif command -v gsd-tools >/dev/null 2>&1; then GSD_TOOLS="$(command -v gsd-tools)"; gsd_run() { "$GSD_TOOLS" "$@"; }; elif [ -f "$HOME/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="$HOME/.claude/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd-tools is not on PATH. Run: npx -y @opengsd/gsd-core@latest --claude --local" >&2; exit 1; fi; if [ -n "${CLAUDE_ENV_FILE:-}" ] && [ -n "${GSD_TOOLS:-}" ]; then printf "export PATH='%s':\"\$PATH\"\n" "${GSD_TOOLS%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
-gsd_run query state.record-session "" \
-  "Forensic investigation complete" \
-  ".planning/forensics/report-{timestamp}.md"
+gsd_run query state.record-session \
+  --stopped-at "Forensic investigation complete" \
+  --resume-file ".planning/forensics/report-{timestamp}.md"
 ```

package/gsd-core/workflows/help/modes/full.md

@@ -673,7 +673,7 @@ These six skills exist primarily for the model to perform two-stage hierarchical
 ├── milestones/
 │   ├── v1.0-ROADMAP.md       # Archived roadmap snapshot
 │   ├── v1.0-REQUIREMENTS.md  # Archived requirements
-│   └── v1.0-phases/          # Archived phase dirs (via /gsd:cleanup or --archive-phases)
+│   └── v1.0-phases/          # Archived phase dirs (via /gsd:cleanup or milestone complete, which archives by default)
 │       ├── 01-foundation/
 │       └── 02-core-features/
 ├── codebase/             # Codebase map (brownfield projects)

package/gsd-core/workflows/manager.md

@@ -1,6 +1,6 @@
 <purpose>
 
-Interactive command center for managing a milestone from a single terminal. Shows a dashboard of all phases with visual status, dispatches discuss inline and runs plan/execute inline (backgrounded only on Codex), and loops back to the dashboard after each action. Enables parallel phase work from one terminal.
+Interactive command center for managing a milestone from a single terminal. Shows a dashboard of all phases with visual status, dispatches discuss inline and runs plan/execute inline (backgrounded when dispatch-should-flatten returns false), and loops back to the dashboard after each action. Enables parallel phase work from one terminal.
 
 </purpose>
 
@@ -45,7 +45,7 @@ Display startup banner:
  {milestone_version} — {milestone_name}
  {phase_count} phases · {completed_count} complete
 
- ✓ Discuss → inline    ◆ Plan/Execute → inline (background on Codex)
+ ✓ Discuss → inline    ◆ Plan/Execute → inline (background when FLATTEN=false)
  Dashboard auto-refreshes when background work is active.
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 ```
@@ -222,10 +222,10 @@ Go to exit step.
 
 ### Compound Action (background + inline)
 
-When the user selects a compound option, behavior depends on the runtime — the Plan Phase N / Execute Phase N handlers below resolve it via `gsd_run query config-get runtime`:
+When the user selects a compound option, behavior depends on whether the runtime supports background dispatch of nesting-capable orchestrators — the Plan Phase N / Execute Phase N handlers below resolve it via `gsd_run query dispatch-should-flatten` (#1708):
 
-- **On Codex:** **Spawn all background agents first** (plan/execute) — dispatch them in parallel using the Plan Phase N / Execute Phase N handlers below — then run verification actions, then run the inline discuss; the background agents continue while you verify/discuss.
-- **On Claude Code or any other non-Codex runtime:** run the chosen plan/execute step(s) **inline** via their handlers below (in order), then run verification actions, then run the inline discuss. There is no overlap.
+- **If `FLATTEN` is `false` (the host can background a nesting-capable orchestrator — e.g. codex, cursor):** **Spawn all background agents first** (plan/execute) — dispatch them in parallel using the Plan Phase N / Execute Phase N handlers below — then run verification actions, then run the inline discuss; the background agents continue while you verify/discuss.
+- **Otherwise (`FLATTEN` is `true` — run inline):** run the chosen plan/execute step(s) **inline** via their handlers below (in order), then run verification actions, then run the inline discuss. There is no overlap.
 
 Inline verification:
 
@@ -254,13 +254,13 @@ After discuss completes, loop back to dashboard step.
 
 ### Plan Phase N
 
-Planning runs autonomously. **First resolve the runtime.** Background dispatch is only safe on a runtime where a backgrounded agent can still nest the pipeline's subagents (plan-checker / worktree executors / verifier). Among supported runtimes only **Codex** (`spawn_agent`) can do this; Claude Code's backgrounded agents have no `Agent`/`Task` tool, and every other runtime either prohibits nested subagents or disables them by default. So run **inline** everywhere except Codex, which is dispatched in the background.
+Planning runs autonomously. **First resolve whether background dispatch is safe.** Background dispatch is only safe on a runtime where a backgrounded agent can still nest the pipeline's subagents (plan-checker / worktree executors / verifier). This is determined from the documentation-sourced dispatch capability in the registry (#1708); Claude Code's backgrounded agents have no `Agent`/`Task` tool, and every other runtime either prohibits nested subagents or disables them by default. So run **inline** everywhere except where `dispatch-should-flatten` returns `false`.
 
 ```bash
-RUNTIME=$(gsd_run query config-get runtime --default claude --raw 2>/dev/null || echo "claude")
+FLATTEN=$(gsd_run query dispatch-should-flatten --raw 2>/dev/null || echo "true")
 ```
 
-**If `RUNTIME` is `codex`:** Spawn a background agent that delegates to the Skill pipeline with any configured flags:
+**If `FLATTEN` is `false`:** Spawn a background agent that delegates to the Skill pipeline with any configured flags:
 
 ```
 Agent(
@@ -282,7 +282,7 @@ Important: You are running in the background. Do NOT use AskUserQuestion — mak
 )
 ```
 
-> **ORCHESTRATOR RULE — CODEX RUNTIME**: After calling Agent() above with `run_in_background=true`, do NOT do any planning work for this phase independently. Return to the dashboard immediately and wait for the background agent to report back. Only resume planning-related work when the subagent result is available.
+> **ORCHESTRATOR RULE — BACKGROUND DISPATCH**: After calling Agent() above with `run_in_background=true`, do NOT do any planning work for this phase independently. Return to the dashboard immediately and wait for the background agent to report back. Only resume planning-related work when the subagent result is available.
 
 Display:
 
@@ -292,7 +292,7 @@ Display:
 
 Loop back to dashboard step.
 
-**Otherwise (Claude Code or any other non-Codex runtime):** Run plan inline so the plan-checker and quality gates actually run — do NOT wrap it in `Agent(run_in_background=true, …)`:
+**Otherwise (`FLATTEN` is `true` — run inline):** Run plan inline so the plan-checker and quality gates actually run — do NOT wrap it in `Agent(run_in_background=true, …)`:
 
 ```
 Skill(skill="gsd-plan-phase", args="{N} --auto {manager_flags.plan}")
@@ -308,13 +308,13 @@ Then loop back to dashboard step.
 
 ### Execute Phase N
 
-Execution runs autonomously. **First resolve the runtime.** Background dispatch is only safe on a runtime where a backgrounded agent can still nest the pipeline's subagents (plan-checker / worktree executors / verifier). Among supported runtimes only **Codex** (`spawn_agent`) can do this; Claude Code's backgrounded agents have no `Agent`/`Task` tool, and every other runtime either prohibits nested subagents or disables them by default. So run **inline** everywhere except Codex, which is dispatched in the background.
+Execution runs autonomously. **First resolve whether background dispatch is safe.** Background dispatch is only safe on a runtime where a backgrounded agent can still nest the pipeline's subagents (plan-checker / worktree executors / verifier). This is determined from the documentation-sourced dispatch capability in the registry (#1708); Claude Code's backgrounded agents have no `Agent`/`Task` tool, and every other runtime either prohibits nested subagents or disables them by default. So run **inline** everywhere except where `dispatch-should-flatten` returns `false`.
 
 ```bash
-RUNTIME=$(gsd_run query config-get runtime --default claude --raw 2>/dev/null || echo "claude")
+FLATTEN=$(gsd_run query dispatch-should-flatten --raw 2>/dev/null || echo "true")
 ```
 
-**If `RUNTIME` is `codex`:** Spawn a background agent that delegates to the Skill pipeline with any configured flags:
+**If `FLATTEN` is `false`:** Spawn a background agent that delegates to the Skill pipeline with any configured flags:
 
 ```
 Agent(
@@ -336,7 +336,7 @@ Important: You are running in the background. Do NOT use AskUserQuestion — mak
 )
 ```
 
-> **ORCHESTRATOR RULE — CODEX RUNTIME**: After calling Agent() above with `run_in_background=true`, do NOT do any execution work for this phase independently. Return to the dashboard immediately and wait for the background agent to report back. Only resume execution-related work when the subagent result is available.
+> **ORCHESTRATOR RULE — BACKGROUND DISPATCH**: After calling Agent() above with `run_in_background=true`, do NOT do any execution work for this phase independently. Return to the dashboard immediately and wait for the background agent to report back. Only resume execution-related work when the subagent result is available.
 
 Display:
 
@@ -346,7 +346,7 @@ Display:
 
 Loop back to dashboard step.
 
-**Otherwise (Claude Code or any other non-Codex runtime):** Run execute inline so worktree isolation and the verifier actually run — do NOT wrap it in `Agent(run_in_background=true, …)`:
+**Otherwise (`FLATTEN` is `true` — run inline):** Run execute inline so worktree isolation and the verifier actually run — do NOT wrap it in `Agent(run_in_background=true, …)`:
 
 ```
 Skill(skill="gsd-execute-phase", args="{N} {manager_flags.execute}")

package/gsd-core/workflows/milestone-summary.md

@@ -218,7 +218,7 @@ If the user is done:
 ## Step 9: Update STATE.md
 
 ```bash
-gsd_run query state.record-session "" \
-  "Milestone v${VERSION} summary generated" \
-  ".planning/reports/MILESTONE_SUMMARY-v${VERSION}.md"
+gsd_run query state.record-session \
+  --stopped-at "Milestone v${VERSION} summary generated" \
+  --resume-file ".planning/reports/MILESTONE_SUMMARY-v${VERSION}.md"
 ```

package/gsd-core/workflows/new-milestone.md

@@ -212,6 +212,12 @@ Clear leftover phase directories from the previous milestone:
 gsd_run query phases.clear --confirm
 ```
 
+Stage the phase archive move + source removal so they land in the same commit as the milestone start (atomic — no orphaned uncommitted deletions, no un-archived dirs carried forward). `phases.clear` archives each non-999 dir to `milestones/<version>-phases/`; staging both dirs captures the new archive and the removals together (#1871).
+
+```bash
+git add .planning/milestones/ .planning/phases/ 2>/dev/null || true
+```
+
 ```bash
 gsd_run query commit "docs: start milestone v[X.Y] [Name]" --files .planning/PROJECT.md .planning/STATE.md
 ```

package/gsd-core/workflows/plan-phase/steps/closed-phase-gate.md

@@ -0,0 +1,42 @@
+# Closed-Phase Gate (#3569)
+
+The init JSON includes `phase_status` — one of `Pending | Planned | In Progress | Executed | Complete | Needs Review`. `Complete` means the phase has all summaries AND a `VERIFICATION.md` with `status: passed`. Replanning a closed phase silently rewrites plan docs that no longer match the shipped code, so the workflow must hard-stop here unless the operator explicitly overrides.
+
+Parse `phase_status` from the init JSON, then:
+
+```bash
+FORCE_REPLAN=false
+if [[ "$ARGUMENTS" =~ (^|[[:space:]])--force([[:space:]]|$) ]]; then
+  FORCE_REPLAN=true
+fi
+
+if [ "${phase_status}" = "Complete" ]; then
+  if [[ "$ARGUMENTS" =~ (^|[[:space:]])--reviews([[:space:]]|$) ]]; then
+    # --reviews on a closed phase is never legitimate — concerns belong in a
+    # new phase or issue against the closed phase's commits.
+    cat <<EOF >&2
+Phase ${phase_number} (${phase_name}) is already CLOSED (VERIFICATION status: passed).
+/gsd:plan-phase --reviews cannot replan a closed phase. If the review surfaced
+real concerns, open a follow-up phase or file an issue against the closed
+phase's commits. There is no --force override for --reviews on a closed phase.
+EOF
+    exit 1
+  fi
+  if [ "$FORCE_REPLAN" != "true" ]; then
+    cat <<EOF >&2
+Phase ${phase_number} (${phase_name}) is already CLOSED (VERIFICATION status: passed).
+Replanning a closed phase will overwrite plan docs that no longer match the
+shipped code. If you intentionally want to replan over closed work, re-run
+with: /gsd:plan-phase ${phase_number} --force
+
+Otherwise, to view what shipped, see: ${verification_path}
+EOF
+    exit 1
+  fi
+  # FORCE_REPLAN=true: continue, but emit a banner so the operator sees the
+  # decision in the transcript and in any committed plan docs.
+  echo "WARNING: Replanning CLOSED phase ${phase_number} under --force. Verify the closeout was wrong before committing new plan docs." >&2
+fi
+```
+
+The gate fires only on `Complete`. `Executed` and `Needs Review` are not gated — those states mean planning was finished but verification did not pass, and replanning is a legitimate next step.

package/gsd-core/workflows/plan-phase/steps/prd-express-path.md

@@ -0,0 +1,102 @@
+# PRD Express Path — generate CONTEXT.md from a PRD
+
+Runs when `--prd <filepath>` is provided (§3.5 of `plan-phase.md`).
+
+1. Read the PRD file:
+```bash
+PRD_CONTENT=$(cat "$PRD_FILE" 2>/dev/null)
+if [ -z "$PRD_CONTENT" ]; then
+  echo "Error: PRD file not found: $PRD_FILE"
+  exit 1
+fi
+```
+
+2. Display banner:
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► PRD EXPRESS PATH
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Using PRD: {PRD_FILE}
+Generating CONTEXT.md from requirements...
+```
+
+3. Parse the PRD content and generate CONTEXT.md. The orchestrator should:
+   - Extract all requirements, user stories, acceptance criteria, and constraints from the PRD
+   - Map each to a locked decision (everything in the PRD is treated as a locked decision)
+   - Identify any areas the PRD doesn't cover and mark as "Claude's Discretion"
+   - **Extract canonical refs** from ROADMAP.md for this phase, plus any specs/ADRs referenced in the PRD — expand to full file paths (MANDATORY)
+   - Create CONTEXT.md in the phase directory
+
+4. Write CONTEXT.md:
+```markdown
+# Phase [X]: [Name] - Context
+
+**Gathered:** [date]
+**Status:** Ready for planning
+**Source:** PRD Express Path ({PRD_FILE})
+
+<domain>
+## Phase Boundary
+
+[Extracted from PRD — what this phase delivers]
+
+</domain>
+
+<decisions>
+## Implementation Decisions
+
+{For each requirement/story/criterion in the PRD:}
+### [Category derived from content]
+- [Requirement as locked decision]
+
+### Claude's Discretion
+[Areas not covered by PRD — implementation details, technical choices]
+
+</decisions>
+
+<canonical_refs>
+## Canonical References
+
+**Downstream agents MUST read these before planning or implementing.**
+
+[MANDATORY. Extract from ROADMAP.md and any docs referenced in the PRD.
+Use full relative paths. Group by topic area.]
+
+### [Topic area]
+- `path/to/spec-or-adr.md` — [What it decides/defines]
+
+[If no external specs: "No external specs — requirements fully captured in decisions above"]
+
+</canonical_refs>
+
+<specifics>
+## Specific Ideas
+
+[Any specific references, examples, or concrete requirements from PRD]
+
+</specifics>
+
+<deferred>
+## Deferred Ideas
+
+[Items in PRD explicitly marked as future/v2/out-of-scope]
+[If none: "None — PRD covers phase scope"]
+
+</deferred>
+
+---
+
+*Phase: XX-name*
+*Context gathered: [date] via PRD Express Path*
+```
+
+5. Commit:
+```bash
+_GSD_SHIM_NAME="gsd-tools.cjs"; _GSD_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"; GSD_TOOLS="${_GSD_RUNTIME_ROOT}/gsd-core/bin/${_GSD_SHIM_NAME}"; if [ -f "$GSD_TOOLS" ]; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif command -v gsd-tools >/dev/null 2>&1; then GSD_TOOLS="$(command -v gsd-tools)"; gsd_run() { "$GSD_TOOLS" "$@"; }; elif [ -f "$HOME/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="$HOME/.claude/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd-tools is not on PATH. Run: npx -y @opengsd/gsd-core@latest --claude --local" >&2; exit 1; fi; if [ -n "${CLAUDE_ENV_FILE:-}" ] && [ -n "${GSD_TOOLS:-}" ]; then printf "export PATH='%s':\"\$PATH\"\n" "${GSD_TOOLS%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
+gsd_run query commit "docs(${padded_phase}): generate context from PRD" --files "${phase_dir}/${padded_phase}-CONTEXT.md"
+```
+
+6. Set `context_content` to the generated CONTEXT.md content and continue to step 5 (Handle Research).
+
+**Effect:** This completely bypasses step 4 (Load CONTEXT.md) since we just created it. The rest of the workflow (research, planning, verification) proceeds normally with the PRD-derived context.

package/gsd-core/workflows/plan-phase/steps/windows-troubleshooting.md

@@ -0,0 +1,23 @@
+# Windows Troubleshooting
+
+**Windows users:** If plan-phase freezes during agent spawning (common on Windows due to
+stdio deadlocks with MCP servers — see Claude Code issue anthropics/claude-code#28126):
+
+1. **Force-kill:** Close the terminal (Ctrl+C may not work)
+2. **Clean up orphaned processes:**
+   ```powershell
+   # Kill orphaned node processes from stale MCP servers
+   Get-Process node -ErrorAction SilentlyContinue | Where-Object {$_.StartTime -lt (Get-Date).AddHours(-1)} | Stop-Process -Force
+   ```
+3. **Clean up stale task directories:**
+   ```powershell
+   # Remove stale subagent task dirs (Claude Code never cleans these on crash)
+   Remove-Item -Recurse -Force "$env:USERPROFILE\.claude\tasks\*" -ErrorAction SilentlyContinue
+   ```
+4. **Reduce MCP server count:** Temporarily disable non-essential MCP servers in settings.json
+5. **Retry:** Restart Claude Code and run `/gsd:plan-phase` again
+
+If freezes persist, try `--skip-research` to reduce the agent chain from 3 to 2 agents:
+```
+/gsd:plan-phase N --skip-research
+```