maxsimcli 4.15.3 → 4.16.0

package/dist/assets/templates/workflows/execute-plan.md

@@ -7,7 +7,6 @@ Read STATE.md before any operation to load project context.
 Read config.json for planning behavior settings.
 
 @./references/git-integration.md
-@./references/dashboard-bridge.md
 </required_reading>
 
 ## MCP Server Fallback
@@ -52,25 +51,13 @@ mcp_detect_external_edits(issue_number: phase_issue_number)
 
 If external edits detected: warn user and offer to re-read the plan before proceeding.
 
-**Fallback -- no GitHub context:**
+**If no GitHub context is available:**
 
-If no `phase_issue_number` or `plan_comment_body` was passed:
+GitHub Issues is the source of truth for plans. If no `phase_issue_number` or `plan_comment_body` was passed, report the error and exit:
 
-```bash
-# Use plans/summaries from INIT JSON, or list files
-ls .planning/phases/XX-name/*-PLAN.md 2>/dev/null | sort
-ls .planning/phases/XX-name/*-SUMMARY.md 2>/dev/null | sort
 ```
-
-Find first PLAN without matching SUMMARY. Decimal phases supported (`01.1-hotfix/`).
-
-<if mode="yolo">
-Auto-approve: `⚡ Execute {phase}-{plan}-PLAN.md [Plan X of Y for Phase Z]` → parse_segments.
-</if>
-
-<if mode="interactive" OR="custom with gates.execute_next_plan true">
-Present plan identification, wait for confirmation.
-</if>
+Plan content must be provided via GitHub Issue comment. Ensure GitHub integration is configured.
+```
 </step>
 
 <step name="record_start_time">
@@ -145,12 +132,7 @@ Pattern B only (verify-only checkpoints). Skip for A/C.
 
 The plan content IS the execution instructions. Follow exactly. If plan references CONTEXT.md: honor user's vision throughout.
 
-When plan was loaded from a GitHub comment (github_context passed): the plan content is already in memory from the load_plan_from_github step.
-
-When plan is loaded from a local file (fallback):
-```bash
-cat .planning/phases/XX-name/{phase}-{plan}-PLAN.md
-```
+The plan content is already in memory from the load_plan_from_github step (loaded from the GitHub Issue comment passed by the orchestrator).
 </step>
 
 <step name="pre_execution_gates">
@@ -194,7 +176,7 @@ fi
 node ~/.claude/maxsim/bin/maxsim-tools.cjs phases list --type summaries --raw
 # Extract the second-to-last summary from the JSON result
 ```
-If previous phase has unresolved issues (check summary comments on phase issue or local SUMMARY.md "Issues Encountered" / "Next Phase Readiness" blockers): AskUserQuestion(header="Previous Issues", options: "Proceed anyway" | "Address first" | "Review previous").
+If previous phase has unresolved issues (check summary comments on phase issue for "Issues Encountered" / "Next Phase Readiness" blockers): AskUserQuestion(header="Previous Issues", options: "Proceed anyway" | "Address first" | "Review previous").
 </step>
 
 <step name="execute">
@@ -363,11 +345,6 @@ Display: `CHECKPOINT: [Type]` box → Progress {X}/{Y} → Task name → type-sp
 | decision (9%) | Decision needed + context + options with pros/cons | "Select: option-id" |
 | human-action (1%) | What was automated + ONE manual step + verification plan | "done" |
 
-**Dashboard mode:** If `DASHBOARD_ACTIVE` (see @dashboard-bridge), present checkpoint content via `mcp__maxsim-dashboard__ask_question` instead of plain text:
-- human-verify: `options: [{value: "approved", label: "Approved"}, {value: "issues", label: "Report issues"}]`, `allow_free_text: true`
-- decision: one option per decision choice
-- human-action: `options: [{value: "done", label: "Done"}]`, `allow_free_text: true`
-
 After response: verify if specified. Pass → continue. Fail → inform, wait. WAIT for user — do NOT hallucinate completion.
 
 See ~/.claude/maxsim/references/checkpoints.md for details.
@@ -455,7 +432,7 @@ mcp_post_comment(
 
 Record the comment URL/ID as `SUMMARY_COMMENT_ID` for future reference.
 
-**Fallback (no GitHub integration):** Write `{phase}-{plan}-SUMMARY.md` to `.planning/phases/XX-name/` as before.
+GitHub Issues is the source of truth -- summaries are always posted as GitHub comments.
 </step>
 
 <step name="review_cycle">
@@ -1044,7 +1021,7 @@ mcp_post_comment(
 )
 ```
 
-**Fallback (no GitHub integration):** Write VERIFICATION.md and UAT.md to the phase directory as before.
+GitHub Issues is the source of truth -- verification and UAT results are always posted as GitHub comments.
 </step>
 
 <step name="update_codebase_map">
@@ -1072,12 +1049,6 @@ mcp_list_sub_issues(issue_number: phase_issue_number)
 
 Count open vs closed sub-issues. Map closed count to plans complete.
 
-Fallback (no GitHub):
-```bash
-ls -1 .planning/phases/[current-phase-dir]/*-PLAN.md 2>/dev/null | wc -l
-ls -1 .planning/phases/[current-phase-dir]/*-SUMMARY.md 2>/dev/null | wc -l
-```
-
 | Condition | Route | Action |
 |-----------|-------|--------|
 | open task sub-issues remain | **A: More plans** | Find next incomplete plan (by open sub-issues or missing summary comment). Yolo: auto-continue. Interactive: show next plan, suggest `/maxsim:execute {phase}`. STOP here. |

package/dist/assets/templates/workflows/execute.md

@@ -87,10 +87,13 @@ When GitHub integration is active (`phase_issue_number` is set):
    - `plan_count`: total plan comments found
    - `incomplete_count`: count of incomplete plans
 
-When GitHub integration is NOT active (no `phase_issue_number`), fall back to local file scanning:
-```bash
-PLAN_INDEX=$(node .claude/maxsim/bin/maxsim-tools.cjs phase-plan-index "${PHASE_NUMBER}")
+When GitHub integration is NOT active (no `phase_issue_number`):
+```
+No plans found for Phase {phase_number}. GitHub Issues is the source of truth for plans.
+
+Ensure GitHub integration is configured: run /maxsim:init to set up GitHub Issues.
 ```
+Exit workflow.
 
 ### 2b. Check for External Edits (WIRE-06)
 
@@ -332,11 +335,6 @@ mcp_get_issue_detail(issue_number: phase_issue_number)
 
 Look for the `<!-- maxsim:type=verification -->` comment and parse the `status:` field from its body.
 
-Also fall back to reading locally:
-```bash
-grep "^status:" "$PHASE_DIR"/*-VERIFICATION.md | cut -d: -f2 | tr -d ' '
-```
-
 **If `passed`:** Show verification gate and proceed to completion.
 
 ```
@@ -510,7 +508,7 @@ Display final results:
 
 <success_criteria>
 - [ ] Phase validated against roadmap
-- [ ] Plan inventory loaded from GitHub issue comments (falling back to local files if no GitHub integration)
+- [ ] Plan inventory loaded from GitHub issue comments (GitHub Issues is the source of truth)
 - [ ] External edit detection warns user if phase issue was modified externally
 - [ ] Current state correctly detected from task sub-issue closure and summary comments
 - [ ] Re-entry flow works for already-executed phases

package/dist/assets/templates/workflows/go.md

@@ -160,13 +160,13 @@ Rule 5: Phase "To Do" on GitHub board (not yet started)?
   -> Action: /maxsim:plan {N}
   -> Reasoning: "Phase {N} ({name}) needs planning."
 
-  Sub-check: Does local CONTEXT.md exist?
+  Sub-check: Does a context comment exist on the phase GitHub Issue?
   -> If yes: "Discussion complete, ready for research + planning."
   -> If no: "Starting from discussion stage."
 
 Rule 6: Current phase "In Review" on GitHub board?
   -> Check: mcp_get_all_progress returns a phase with status="In Review"
-  -> Action: /maxsim:verify {N}
+  -> Action: /maxsim:execute {N}
   -> Reasoning: "Phase {N} ({name}) is awaiting verification."
 
 Rule 7: All phases "Done" on GitHub board?
@@ -233,7 +233,7 @@ Or describe what you'd like to do:
 - If no phases exist on board: show `/maxsim:plan` prominently
 - Always include `/maxsim:quick` as it is always relevant
 - Always include an open-ended fallback ("Or describe what you'd like to do")
-- If GitHub not available (mcp calls fail): fall back to local ROADMAP analysis and note degraded mode
+- If GitHub not available (mcp calls fail): note degraded mode, recommend resolving GitHub connectivity
 
 Wait for user selection, then dispatch the chosen command.
 </step>
@@ -245,7 +245,7 @@ Wait for user selection, then dispatch the chosen command.
 - Always surface problems BEFORE suggesting actions
 - All problems block — no severity tiers, no "warnings"
 - No arguments accepted — this is pure auto-detection
-- No mention of old commands (plan-phase, execute-phase, etc.)
+- No mention of old commands (plan, execute-phase, etc.)
 - Keep initial feedback fast — show "Analyzing..." before heavy operations
 - Primary source for phase state: live GitHub (mcp_get_all_progress, mcp_detect_interrupted)
 - Local reads: STATE.md for blockers/decisions, ROADMAP.md for phase ordering only

package/dist/assets/templates/workflows/help.md

@@ -106,7 +106,7 @@ Systematic debugging with persistent state across context resets.
 
 - Scientific method: gather symptoms, hypothesize, test, verify
 - Persistent debug sessions in `.planning/debug/` -- survives `/clear`
-- Spawns isolated debugger agent (fresh 200K context per investigation)
+- Spawns isolated verifier agent (fresh 200K context per investigation)
 - Run with no args to resume an active session
 
 Usage: `/maxsim:debug login form returns 500` or `/maxsim:debug` (resume)

package/dist/assets/templates/workflows/init-existing.md

@@ -6,15 +6,10 @@ Output: `.planning/` directory with config.json, PROJECT.md, REQUIREMENTS.md, RO
 
 <required_reading>
 Read all files referenced by the invoking prompt's execution_context before starting.
-@./references/dashboard-bridge.md
 @./references/thinking-partner.md
 @./references/questioning.md
 </required_reading>
 
-<tool_mandate>
-**Question routing:** At workflow start, probe for the dashboard (see @dashboard-bridge). If `DASHBOARD_ACTIVE = true`, route ALL `AskUserQuestion` calls through `mcp__maxsim-dashboard__ask_question` using the schema translation rules from @dashboard-bridge. If `DASHBOARD_ACTIVE = false`, use `AskUserQuestion` as normal.
-</tool_mandate>
-
 <auto_mode>
 ## Auto Mode Detection
 

package/dist/assets/templates/workflows/new-milestone.md

@@ -7,14 +7,9 @@ Start a new milestone cycle for an existing project. Loads project context, gath
 <required_reading>
 
 Read all files referenced by the invoking prompt's execution_context before starting.
-@./references/dashboard-bridge.md
 
 </required_reading>
 
-<tool_mandate>
-**Question routing:** At workflow start, probe for the dashboard (see @dashboard-bridge). If `DASHBOARD_ACTIVE = true`, route ALL `AskUserQuestion` calls through `mcp__maxsim-dashboard__ask_question` using the schema translation rules from @dashboard-bridge. If `DASHBOARD_ACTIVE = false`, use `AskUserQuestion` as normal.
-</tool_mandate>
-
 <process>
 
 ## 1. Load Context
@@ -22,12 +17,12 @@ Read all files referenced by the invoking prompt's execution_context before star
 - Read PROJECT.md (existing project, validated requirements, decisions)
 - Read MILESTONES.md (what shipped previously)
 - Read STATE.md (pending todos, blockers)
-- Check for MILESTONE-CONTEXT.md (from /maxsim:discuss-milestone)
+- Check for MILESTONE-CONTEXT.md (from /maxsim:plan)
 
 ## 2. Gather Milestone Goals
 
 **If MILESTONE-CONTEXT.md exists:**
-- Use features and scope from discuss-milestone
+- Use features and scope from plan
 - Present summary for confirmation
 
 **If no context file:**

package/dist/assets/templates/workflows/new-project.md

@@ -4,15 +4,10 @@ Initialize a new project through unified flow: questioning, research (optional),
 
 <required_reading>
 Read all files referenced by the invoking prompt's execution_context before starting.
-@./references/dashboard-bridge.md
 @./references/thinking-partner.md
 @./references/questioning.md
 </required_reading>
 
-<tool_mandate>
-**Question routing:** At workflow start, probe for the dashboard (see @dashboard-bridge). If `DASHBOARD_ACTIVE = true`, route ALL `AskUserQuestion` calls through `mcp__maxsim-dashboard__ask_question` using the schema translation rules from @dashboard-bridge. If `DASHBOARD_ACTIVE = false`, use `AskUserQuestion` as normal.
-</tool_mandate>
-
 <auto_mode>
 ## Auto Mode Detection
 

package/dist/assets/templates/workflows/progress.md

@@ -85,10 +85,9 @@ Call `mcp_query_board` with the project number (from init context / config). Gro
 | Done        | 3     | #9, #10, #11 |
 ```
 
-**Cross-validate with local ROADMAP.md:**
-- Run `ROADMAP=$(node ~/.claude/maxsim/bin/maxsim-tools.cjs roadmap analyze)` to get local phase data
-- Compare local completion status against GitHub board status
-- Highlight any discrepancies between local and GitHub state in the Issues Detected section
+**Cross-reference with local ROADMAP.md (for phase ordering only -- GitHub is authoritative for status):**
+- Run `ROADMAP=$(node ~/.claude/maxsim/bin/maxsim-tools.cjs roadmap analyze)` to get local phase ordering data
+- If local ROADMAP phase list differs from GitHub Issues, note in Issues Detected section (GitHub is the source of truth)
 </step>
 
 <step name="live_github_detail">
@@ -217,9 +216,9 @@ Identify the in-progress or interrupted phase (from `mcp_get_all_progress` or `m
 
 **Route B: Phase needs planning**
 
-Check if `{phase_num}-CONTEXT.md` exists in phase directory.
+Check if a `<!-- maxsim:type=context -->` comment exists on the phase GitHub Issue.
 
-**If CONTEXT.md exists:**
+**If context comment exists:**
 
 ```
 ---
@@ -236,7 +235,7 @@ Check if `{phase_num}-CONTEXT.md` exists in phase directory.
 ---
 ```
 
-**If CONTEXT.md does NOT exist:**
+**If no context comment exists:**
 
 ```
 ---
@@ -244,7 +243,7 @@ Check if `{phase_num}-CONTEXT.md` exists in phase directory.
 ## ▶ Next Up
 
 **Phase {N}: {Name}** — {Goal from ROADMAP.md}
-<sub>No context yet — /maxsim:plan will start with discussion</sub>
+<sub>No context comment yet — /maxsim:plan will start with discussion</sub>
 
 `/maxsim:plan {phase}`
 
@@ -335,8 +334,8 @@ Ready to plan the next milestone.
 - All work complete → offer milestone completion via `/maxsim:init`
 - Blockers present → highlight before offering to continue
 - External edits detected → surface in Issues Detected section before routing
-- Discrepancy between local ROADMAP and GitHub board → surface in Issues Detected, ask user to reconcile
-- GitHub not available (mcp calls fail) → fall back to local ROADMAP analysis and note degraded mode
+- Discrepancy between local ROADMAP and GitHub board → surface in Issues Detected (GitHub is authoritative)
+- GitHub not available (mcp calls fail) → note degraded mode, recommend resolving GitHub connectivity
   </step>
 
 </process>
@@ -348,7 +347,7 @@ Ready to plan the next milestone.
 - [ ] Board column view shown via mcp_query_board
 - [ ] Per-phase task detail available via mcp_get_phase_progress and mcp_list_sub_issues
 - [ ] External edit detection via mcp_detect_external_edits
-- [ ] Cross-validation between local ROADMAP.md and GitHub board status
+- [ ] Cross-reference local ROADMAP.md for phase ordering (GitHub is authoritative for status)
 - [ ] Phase gaps and discrepancies detected and surfaced in Issues Detected section
 - [ ] Current position clear with visual progress
 - [ ] What's next clearly explained

package/dist/assets/templates/workflows/quick.md

@@ -16,7 +16,6 @@ With `--todo` flag (or trigger words): enters Todo Mode for listing, capturing,
 
 <required_reading>
 Read all files referenced by the invoking prompt's execution_context before starting.
-@./references/dashboard-bridge.md
 </required_reading>
 
 <process>

package/dist/assets/templates/workflows/sdd.md

@@ -14,8 +14,6 @@ Fresh context per task. No context bleeding between tasks. Review is mandatory,
 
 <required_reading>
 Read STATE.md before any operation to load project context.
-
-@./references/dashboard-bridge.md
 </required_reading>
 
 <process>
@@ -34,15 +32,16 @@ Parse JSON for: `executor_model`, `verifier_model`, `commit_docs`, `phase_found`
 </step>
 
 <step name="discover_plans">
-Find incomplete plans — skip any plan that already has a matching SUMMARY.md:
+Find incomplete plans by querying GitHub Issues (the source of truth for plans and completion status):
 
-```bash
-PLAN_INDEX=$(node ~/.claude/maxsim/bin/maxsim-tools.cjs phase-plan-index "${PHASE_NUMBER}")
+```
+mcp_get_issue_detail(issue_number: phase_issue_number)
+mcp_list_sub_issues(issue_number: phase_issue_number)
 ```
 
-Parse JSON for: `plans[]` (each with `id`, `objective`, `files_modified`, `task_count`, `has_summary`), `incomplete`.
+Parse plan comments (`<!-- maxsim:type=plan -->`) from the phase issue. A plan is complete when all its task sub-issues are closed.
 
-**Filtering:** Skip plans where `has_summary: true`. If all plans complete: "All plans in phase already have summaries" — exit.
+**Filtering:** Skip plans where all task sub-issues are closed. If all plans complete: "All plans in phase are already complete" — exit.
 
 Report:
 ```
@@ -60,11 +59,7 @@ Report:
 </step>
 
 <step name="load_plan">
-For each incomplete plan, read the plan file and extract the ordered task list:
-
-```bash
-cat ${PHASE_DIR}/${PLAN_FILE}
-```
+For each incomplete plan, read the plan content from the GitHub Issue comment (loaded in discover_plans) and extract the ordered task list.
 
 Extract for each task:
 - **Task number** (sequential order in plan)
@@ -327,14 +322,7 @@ Display task completion:
 </step>
 
 <step name="create_summary">
-After all tasks in a plan complete, create SUMMARY.md:
-
-```bash
-# Get the summary template
-cat ~/.claude/maxsim/templates/summary.md
-```
-
-Create `{phase}-{plan}-SUMMARY.md` in the phase directory. Include:
+After all tasks in a plan complete, build the summary content in memory and post it as a GitHub comment on the phase issue. Include:
 
 **Frontmatter:** phase, plan, subsystem, tags, requires/provides/affects, tech-stack, key-files.created/modified, key-decisions, requirements-completed (copy from PLAN.md frontmatter), duration, completed date.
 
@@ -358,12 +346,19 @@ Create `{phase}-{plan}-SUMMARY.md` in the phase directory. Include:
 - Deviations (if any)
 - Issues encountered
 
-Use `node ~/.claude/maxsim/bin/maxsim-tools.cjs` for template operations as needed.
+Post summary to GitHub:
+```
+mcp_post_comment(
+  issue_number: phase_issue_number,
+  type: "summary",
+  body: {summary_content}
+)
+```
 
 Self-check:
 - Verify first 2 files from `key-files.created` exist on disk
 - Check `git log --oneline --all --grep="{phase}-{plan}"` returns commits
-- Append `## Self-Check: PASSED` or `## Self-Check: FAILED`
+- Append `## Self-Check: PASSED` or `## Self-Check: FAILED` to summary content before posting
 </step>
 
 <step name="update_state">
@@ -398,23 +393,27 @@ node ~/.claude/maxsim/bin/maxsim-tools.cjs requirements mark-complete ${REQ_IDS}
 Task code already committed per-task. Commit planning artifacts:
 
 ```bash
-node ~/.claude/maxsim/bin/maxsim-tools.cjs commit "docs({phase}-{plan}): complete SDD execution" --files .planning/phases/${PHASE_DIR_NAME}/${PHASE}-${PLAN}-SUMMARY.md .planning/STATE.md .planning/ROADMAP.md .planning/REQUIREMENTS.md
+node ~/.claude/maxsim/bin/maxsim-tools.cjs commit "docs({phase}-{plan}): complete SDD execution" --files .planning/STATE.md .planning/ROADMAP.md .planning/REQUIREMENTS.md
 ```
+
+Note: No local SUMMARY.md is committed -- summary was posted to GitHub as a comment.
 </step>
 
 <step name="offer_next">
 After all plans in the phase are processed:
 
-```bash
-ls -1 .planning/phases/${PHASE_DIR_NAME}/*-PLAN.md 2>/dev/null | wc -l
-ls -1 .planning/phases/${PHASE_DIR_NAME}/*-SUMMARY.md 2>/dev/null | wc -l
+Check completion by querying the phase issue's task sub-issues:
 ```
+mcp_list_sub_issues(issue_number: phase_issue_number)
+```
+
+Count open vs closed sub-issues to determine completion.
 
 | Condition | Route | Action |
 |-----------|-------|--------|
-| summaries < plans | **A: More plans** | Find next incomplete plan. Show next plan, suggest `/maxsim:execute {phase}` (SDD mode) to continue. |
-| summaries = plans, more phases exist | **B: Phase done** | Show completion, suggest `/maxsim:execute {phase}` (verification) then `/maxsim:plan {next}`. |
-| summaries = plans, last phase | **C: Milestone done** | Show banner, suggest `/maxsim:progress` (milestone completion) + `/maxsim:execute` (verification). |
+| open sub-issues remain | **A: More plans** | Find next incomplete plan (by open sub-issues). Show next plan, suggest `/maxsim:execute {phase}` (SDD mode) to continue. |
+| all sub-issues closed, more phases exist | **B: Phase done** | Show completion, suggest `/maxsim:execute {phase}` (verification) then `/maxsim:plan {next}`. |
+| all sub-issues closed, last phase | **C: Milestone done** | Show banner, suggest `/maxsim:progress` (milestone completion) + `/maxsim:execute` (verification). |
 
 All routes: recommend `/clear` first for fresh context.
 </step>
@@ -430,5 +429,5 @@ All routes: recommend `/clear` first for fresh context.
 </failure_handling>
 
 <resumption>
-Re-run `/maxsim:execute {phase}` (SDD mode) — discover_plans finds completed SUMMARYs, skips them, resumes from first incomplete plan. Within a plan, completed tasks (those with commits matching the plan pattern) can be detected and skipped.
+Re-run `/maxsim:execute {phase}` (SDD mode) — discover_plans queries GitHub for task sub-issue status, skips plans with all sub-issues closed, resumes from first incomplete plan. Within a plan, completed tasks (those with commits matching the plan pattern) can be detected and skipped.
 </resumption>

package/dist/assets/templates/workflows/settings.md

@@ -4,13 +4,8 @@ Interactive configuration of MAXSIM workflow agents (research, plan_checker, ver
 
 <required_reading>
 Read all files referenced by the invoking prompt's execution_context before starting.
-@./references/dashboard-bridge.md
 </required_reading>
 
-<tool_mandate>
-**Question routing:** At workflow start, probe for the dashboard (see @dashboard-bridge). If `DASHBOARD_ACTIVE = true`, route ALL `AskUserQuestion` calls through `mcp__maxsim-dashboard__ask_question` using the schema translation rules from @dashboard-bridge. If `DASHBOARD_ACTIVE = false`, use `AskUserQuestion` as normal.
-</tool_mandate>
-
 <process>
 
 <step name="ensure_and_load_config">
@@ -33,7 +28,7 @@ Parse current values (default to `true` if not present):
 - `workflow.research` — spawn researcher during /maxsim:plan
 - `workflow.plan_checker` — spawn plan checker during /maxsim:plan
 - `workflow.verifier` — spawn verifier during /maxsim:execute
-- `workflow.nyquist_validation` — validation architecture research during plan-phase
+- `workflow.nyquist_validation` — validation architecture research during planning
 - `model_profile` — which model each agent uses (default: `balanced`)
 - `git.branching_strategy` — branching approach (default: `"none"`)
 </step>
@@ -94,7 +89,7 @@ AskUserQuestion([
     header: "Nyquist",
     multiSelect: false,
     options: [
-      { label: "Yes (Recommended)", description: "Research automated test coverage during plan-phase. Adds validation requirements to plans. Blocks approval if tasks lack automated verify." },
+      { label: "Yes (Recommended)", description: "Research automated test coverage during planning. Adds validation requirements to plans. Blocks approval if tasks lack automated verify." },
       { label: "No", description: "Skip validation research. Good for rapid prototyping or no-test phases." }
     ]
   },

package/dist/assets/templates/workflows/verify-work.md

@@ -15,7 +15,6 @@ No Pass/Fail buttons. No severity questions. Just: "Here's what should happen. D
 </philosophy>
 
 <required_reading>
-@./references/dashboard-bridge.md
 </required_reading>
 
 <template>
@@ -178,20 +177,7 @@ Proceed to `present_test`.
 
 Read Current Test section from UAT file.
 
-**If `DASHBOARD_ACTIVE`** (see @dashboard-bridge): present test via MCP tool:
-```
-mcp__maxsim-dashboard__ask_question(
-  question: "**Test {number}: {name}**\n\n{expected}\n\n---\nSelect result or describe what's wrong:",
-  options: [
-    { value: "pass", label: "Pass" },
-    { value: "skip", label: "Skip" }
-  ],
-  allow_free_text: true
-)
-```
-Map response: "pass"/"skip" → handle as pass/skip. Any other text → logged as issue.
-
-**If `DASHBOARD_ACTIVE = false`**: display using checkpoint box format:
+Display using checkpoint box format:
 
 ```
 ╔══════════════════════════════════════════════════════════════╗
@@ -253,7 +239,7 @@ reported: "{verbatim user response}"
 severity: {inferred}
 ```
 
-Append to Gaps section (structured YAML for plan-phase --gaps):
+Append to Gaps section (structured YAML for plan --gaps):
 ```yaml
 - truth: "{expected behavior from test}"
   status: failed