@zalom/plastic 1.1.0 → 1.1.2

package/PLASTIC.md

@@ -19,7 +19,7 @@ store/
     plan.md               # optional - implementation plan (How deliverable)
     checklist.md          # optional - execution registry (How deliverable)
     outcome.md            # optional - detailed result (Exec deliverable)
-    actions/              # optional - individual work items
+    actions/              # optional - real action files (How deliverable, at least one required)
     resources/            # optional - research, references, screenshots, diagrams
     savepoint.md          # optional - deterministic cycle-step ledger (auto-written)
     revisions.md          # optional - append-only structural-maintenance audit trail
@@ -95,7 +95,7 @@ tags: [plastic, architecture]
 |-------|---------|-------------|--------|
 | **What** | `## Intent` | `{ID}--{slug}.md` | `plastic-intent-creating` |
 | **Why** | `## Context` + Decisions | `spec.md` | `plastic-intent-brainstorming` |
-| **How** | Planning | `plan.md` + `actions/` + `checklist.md` | `plastic-intent-planning` |
+| **How** | Planning | `plan.md` + `actions/ACTION_N.md` (at least one) + `checklist.md` | `plastic-intent-planning` |
 | **Exec** | Execution | `outcome.md` | `plastic-intent-executing` |
 
 `## Insights` is the append-only log of durable discoveries captured throughout ALL stages.
@@ -133,8 +133,9 @@ same-structure invariant holds: same file set, stage order, gates, and savepoint
 every tier and in both modes.
 
 S/M collapse the topology (one thinker agent writes spec.md then plan.md plus
-checklist.md in one context; actions/ only for L; a sonnet executor implements). L keeps
-the full team.
+checklist.md plus at least one real action file in one context, consolidated into a single
+actions/ACTION_1.md at S/M and one file per task at L; a sonnet executor implements). L
+keeps the full team.
 
 Never cut at any tier: the independent reviewer, outcome.md as truth of delivery, the
 delivery lock, worktree isolation, intent creation via skill, INDEX as status truth, the
@@ -167,8 +168,10 @@ and Exec, spins up the team above, and works the dashboard's dispatchable queue.
 `human_only` (intents that need a person); auto mode consumes the former.
 
 **Model contract.** Every agent in `agents/*.md` pins an explicit Claude Code model alias in
-its own frontmatter: `opus`, `sonnet`, or `haiku`. Never `inherit`, never Fable. Aliases track
-"latest per tier" so no Plastic release is required to advance a tier. The tier by role:
+its own frontmatter: `opus`, `sonnet`, or `haiku`. Never `inherit`, never Fable by default,
+unless an explicit `agents.models.<name>` config override names Fable for that role, in which
+case the override is honored as written. Aliases track "latest per tier" so no Plastic release
+is required to advance a tier. The tier by role:
 `plastic-enforcer`, `plastic-brainstorming`, `plastic-planner` are `opus`;
 `plastic-spec-specialist`, `plastic-executor`, `plastic-intent-curator`,
 `plastic-future-intent-researcher`, `plastic-intent-discovery` are `sonnet`.
@@ -423,8 +426,8 @@ purge. See `docs/internals.md` for depth.
 | Transition | Trigger | Gate |
 |---|---|---|
 | What → Why | `spec.md` written | (none) |
-| Why → How | `plan.md` + `actions/` + `checklist.md` | `spec.md` must exist |
-| How → Exec | Checklist has items | Plan triplet must exist |
+| Why → How | `plan.md` + `actions/ACTION_N.md` (at least one) + `checklist.md` | `spec.md` must exist |
+| How → Exec | Checklist has items | plan.md, checklist.md, and at least one real actions/ACTION_N.md must exist |
 | Exec → Done | `outcome.md` written | All checklist items checked |
 
 Hard blocking: hooks exit code 2 on gate failure.
@@ -528,7 +531,7 @@ each station.
 | Start (board) | none (a procedure, not a stage) | `plastic-lock fix` self-heals stale, corrupt, or legacy state; arm acquires `delivery.lock` (O_EXCL, session-keyed), provisions the code worktree, writes the bridge cache | lock-gate denies any write into an active intent dir without this intent's lock; every deny names the resolving command | savepoint confirms the boarding station |
 | What (create) | `<id>--<slug>.md`, born complete | no lock yet; no bridge | create-gate validates the proposed intent content (Write, Edit, and MCP edits) | savepoint `What` line; intent listed in INDEX `## Active` |
 | Why | `spec.md` | owner writes refresh the lease (lock file mtime heartbeat) | gate-check requires the intent file with `## Intent` before spec.md; lock-gate admits only the owner or a delegate | savepoint `Why started`, `Why spec.md created` |
-| How | `plan.md`, `actions/`, `checklist.md` | heartbeat on writes; the code gate stays closed until plan.md plus checklist.md exist | gate-check requires spec.md before plan.md, and plan.md plus actions/ before checklist.md | savepoint `How started`, `How plan.md created`, `How checklist.md created`, `Exec started` |
+| How | `plan.md`, `actions/ACTION_N.md` (at least one), `checklist.md` | heartbeat on writes; the code gate stays closed until plan.md, checklist.md, and a real action file all exist | gate-check requires spec.md before plan.md, and plan.md plus a real actions/ACTION_N.md before checklist.md | savepoint `How started`, `How plan.md created`, `How checklist.md created`, `Exec started` |
 | Exec | code on the intent branch, checklist checked off | heartbeat; code edits confined to the provisioned worktree; delegates write under the owner's lock; bash, interpreter, and MCP writes gated the same way | code-gate, worktree-gate, bash-gate, lock-gate | checklist boxes; savepoint milestones |
 | End (done) | mandatory `outcome.md` (`disposition: delivered\|abandoned`), INDEX moves to Completed or Abandoned | ordered End tail: verify, merge and remove worktrees, disarm clears `delivery.lock`, then the bridge is purge-eligible, and the QMD reindex runs LAST (after purge) | gate-check blocks outcome.md while checklist items are unchecked | savepoint `Done delivered` (or `abandoned`); takeover audits, if any, remain in savepoint.md |
 | Maintenance (any stage) | `revisions.md` move-and-record entries | future `maintenance.lock` (short TTL), mutually exclusive with `delivery.lock` in either direction; 108 ships the schema seam only, the implementation follows intent 93 in a chained intent | acquisition refuses while the other lock type is fresh; a terminal intent with no lock held is read-only | dated, rule-tagged `revisions.md` entry; savepoint untouched |

package/README.md

@@ -136,8 +136,8 @@ Walk this once in
 | Family | Commands |
 | ------ | -------- |
 | Mode | `plastic-tutorial`, `plastic-auto` |
-| Intent | `plastic-intent-creating`, `plastic-intent-starting`, `plastic-intent-brainstorming`, `plastic-intent-grilling`, `plastic-intent-speccing`, `plastic-intent-planning`, `plastic-intent-executing`, `plastic-intent-ending`, `plastic-intent-continuing`, `plastic-intent-researching` |
-| Project and delivery | `plastic-project-creating`, `plastic-roadmap`, `plastic-releasing` |
+| Intent | `plastic-continuing`, `plastic-intent-creating`, `plastic-intent-starting`, `plastic-intent-brainstorming`, `plastic-intent-grilling`, `plastic-intent-speccing`, `plastic-intent-planning`, `plastic-intent-executing`, `plastic-intent-ending`, `plastic-intent-continuing`, `plastic-intent-researching` |
+| Project and delivery | `plastic-project-creating`, `plastic-project-continuing`, `plastic-roadmap`, `plastic-roadmap-continuing`, `plastic-releasing` |
 | Skill | `plastic-skill-creating`, `plastic-skill-evaluating` |
 | Product | `plastic-install`, `plastic-update`, `plastic-uninstall`, `plastic-rollback`, `plastic-doctor`, `plastic-humanizer` |
 
@@ -165,7 +165,7 @@ Plastic is developed through Plastic.
 The roadmap, intent history, plans, decisions, and outcomes
 behind releases are part of the repository, not a hidden process.
 
-See the current [roadmap](ROADMAP.md) and [changelog](CHANGELOG.md).
+[changelog](CHANGELOG.md).
 
 ## Documentation
 

package/agents/plastic-enforcer.md

@@ -12,7 +12,9 @@ You are the Plastic Enforcer. You ARE the auto orchestrator, spanning the whole
 orchestrating main session on the best available thinking model (Fable, Opus, or whatever
 supersedes them) for the sharpest gating and synthesis. This is advice only: it changes no
 behavior and blocks nothing if ignored. It concerns the human's MAIN session; dispatched
-subagents keep their pinned tier and never resolve to Fable.
+subagents keep their pinned tier and never resolve to Fable, unless an explicit
+`agents.models.<name>` config override names Fable for that role, in which case the override
+is honored as written.
 
 ## Your Responsibilities
 
@@ -29,8 +31,9 @@ subagents keep their pinned tier and never resolve to Fable.
 4. **Sequence the team** — dispatch specialists per the chosen topology with a constructed
    context bundle:
    - S/M: ONE thinker agent, one boot, two stations — it writes spec.md, then plan.md +
-     checklist.md, in a single context. Sections may be one line each; plan.md carries the
-     checklist rationale inline; `actions/` files appear only for L. S may skip the QMD
+     checklist.md + at least one real action file, in a single context. Sections may be one
+     line each; the thinker writes one consolidated `actions/ACTION_1.md` (never an empty
+     `actions/`), while L writes one `actions/ACTION_N.md` per task. S may skip the QMD
      discovery deposit when chain and sources are both empty. A sonnet executor implements.
    - L: today's full team, one specialist per stage (brainstorming, spec-specialist, planner,
      executor), each in a fresh context.
@@ -42,7 +45,8 @@ dispatch also resolve the target agent's model through the config chain (`read-c
 agents.models.<basename> --project <repo>`: project override, then global, then the shipped
 tier default) and pass it explicitly as the dispatch call's model parameter, alongside the
 spawn-preamble live-state injection. Never rely on the dispatched role's frontmatter alone. A
-resolved subagent model is never Fable.
+resolved subagent model is never Fable, unless an explicit `agents.models.<name>` config
+override names Fable for that role, in which case the override is honored as written.
 5. **Gate each handoff** — check each stage deliverable against its exit criteria before handing to the next stage
 6. **Run the final review** — at the final gate, dispatch an INDEPENDENT reviewer subagent (not a sixth standing role)
 

package/agents/plastic-executor.md

@@ -19,11 +19,11 @@ When dispatched in auto mode you receive the standard Plastic spawn preamble (fr
 
 ## How You Work
 
-1. Receive (input handoff): `plan.md` and `checklist.md` from the planner (plus
-   `ACTION_N.md` files inside `actions/` at L; at S/M the `actions/` directory exists but
-   stays empty, so read the tier fork from the inline plan-as-checklist in plan.md
-   instead). For S/M intents you run on the sonnet default, the collapsed topology's
-   implementer; behavior is otherwise unchanged.
+1. Receive (input handoff): `plan.md`, `checklist.md`, and at least one real `ACTION_N.md`
+   inside `actions/` from the planner (S/M hand you one consolidated `actions/ACTION_1.md`;
+   L hands you one `actions/ACTION_N.md` per task). Execute the action files in order. For
+   S/M intents you run on the sonnet default, the collapsed topology's implementer; behavior
+   is otherwise unchanged.
 2. Work one action at a time, preferring safe, non-destructive routes
 3. Edit project code (the gate is open now that plan and checklist exist)
 4. Run the full suite, iterate to zero failures and zero errors

package/agents/plastic-future-intent-researcher.md

@@ -31,4 +31,4 @@ You are the Plastic Future Intent Researcher. Your role is to pick up parked fut
 - You never modify `## Insights` or `## Outcome` sections — those belong to the worker
 - You use Read, WebSearch, WebFetch, and Bash (read-only grep/find) for research
 - You never change status fields — status is convention-derived from INDEX.md placement
-- When dispatching any sub-agent, resolve its model via `read-config agents.models.<basename> --project <repo>` and pass it explicitly at dispatch, never relying on inherited frontmatter; a resolved subagent model is never Fable
+- When dispatching any sub-agent, resolve its model via `read-config agents.models.<basename> --project <repo>` and pass it explicitly at dispatch, never relying on inherited frontmatter; a resolved subagent model is never Fable, unless an explicit `agents.models.<name>` config override names Fable for that role, in which case the override is honored as written

package/agents/plastic-planner.md

@@ -14,14 +14,17 @@ When dispatched in auto mode you receive the standard Plastic spawn preamble (fr
 
 1. **Decompose the spec** — break the approach into ordered, independent actions
 2. **Write the plan** — produce `plan.md` with numbered tasks and verification
-3. **Write self-contained actions, tier-forked**:
-   - S/M: `plan.md` carries the checklist rationale INLINE; do NOT write
-     `actions/ACTION_N.md` files. Sections may be one line each.
-   - L: keep today's shape — one self-contained `actions/ACTION_N.md` per task.
+3. **Write at least one real action file at every tier, tier-forked**:
+   - S/M: write ONE self-contained `actions/ACTION_1.md` that consolidates the whole
+     ordered delivery (the steps plus the exact changes). You MAY split into a few files
+     when that reads cleaner, but one real action file is the floor.
+   - L: one self-contained `actions/ACTION_N.md` per task. A `.gitkeep` never counts as an
+     action, and an empty `actions/` fails the How gate.
 4. **Write the checklist** — `checklist.md` as the execution registry covering every action.
-   `checklist.md` exists at every tier: the file set does not change by tier, only depth
-   (inline vs action files) and agent topology do. plan.md + checklist.md are the two files
-   that open the code gate at every tier.
+   `checklist.md` and at least one real action file exist at every tier: the file set does not
+   change by tier, only action DEPTH (one consolidated action for S/M vs one-per-task for L)
+   and agent topology do. plan.md, checklist.md, AND a real `actions/ACTION_N.md` are what open
+   the code gate at every tier.
 
 ## How You Work
 
@@ -38,7 +41,7 @@ END your turn with a structured completion report as your final message, per the
 - The ordered actions, one line each: what the action does and how it is verified
 - Decomposition rationale: why this order, and why the actions are independent
 - Checklist coverage: the item count, and that every action plus suite-green is covered
-- Which tier shape was produced: inline plan-as-checklist (S/M) or full `actions/` (L)
+- Which tier shape was produced: one consolidated `actions/ACTION_1.md` (S/M) or one `actions/ACTION_N.md` per task (L)
 
 The plan is an argument; the orchestrator gates on whether that argument is sound before any code is written, so make the report make that case.
 
@@ -46,7 +49,8 @@ The plan is an argument; the orchestrator gates on whether that argument is soun
 
 - You are dispatched by the plastic-enforcer and your deliverable is gated before Exec begins
 - You write only intent-store files (`plan.md`, `actions/`, `checklist.md`); no project code
-- The code gate stays closed until `plan.md` and `checklist.md` exist, so produce both
+- The code gate stays closed until `plan.md`, `checklist.md`, and at least one real `actions/ACTION_N.md` exist, so produce all three
 - Keep each action self-contained so the executor can run them one at a time
-- The `actions/` empty-directory git-tracking edge (present only within one same-session
-  local delivery) is out of scope; do not add a `.gitkeep` or a guard for it here
+- Write real `actions/ACTION_N.md` files, never a `.gitkeep`: keeping a freshly-scaffolded
+  empty `actions/` under git is `scripts/new-intent`'s job at intent birth, not the planner's,
+  and a `.gitkeep` never counts as an action

package/hooks/check-update

@@ -5,7 +5,7 @@
 # upgrade target instead of blindly trusting the `latest` tag.
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-PLASTIC_HOME="$HOME/.plastic"
+PLASTIC_HOME="${PLASTIC_HOME:-$HOME/.plastic}"
 CACHE_DIR="$PLASTIC_HOME/.cache"
 CACHE_FILE="$CACHE_DIR/update-check.json"
 VERSION_FILE="$PLASTIC_HOME/VERSION"

package/hooks/continue

@@ -23,7 +23,7 @@ if echo "$MESSAGE" | grep -iq '\bcontinue\b'; then
 {
   "hookSpecificOutput": {
     "hookEventName": "UserPromptSubmit",
-    "additionalContext": "PLASTIC CONTINUE — The user wants to resume previous work.\n\nRead ~/.plastic/INDEX.md and follow the continuing skill workflow."
+    "additionalContext": "PLASTIC CONTINUE: The user wants to resume previous work.\n\nRead ~/.plastic/INDEX.md and follow the plastic-continuing skill workflow."
   }
 }
 HOOKJSON

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zalom/plastic",
-  "version": "1.1.0",
+  "version": "1.1.2",
   "description": "Intent-driven idea development system for AI coding agents",
   "type": "module",
   "bin": {

package/scripts/dashboard.rb

@@ -33,7 +33,7 @@ def today
 end
 
 # A generic "about a month" threshold, not tuned to any one store's item count.
-# Deliberately independent from plastic-intent-continuing's separate stale_threshold_days
+# Deliberately independent from plastic-project-continuing's separate stale_threshold_days
 # config: that one is a proactive boot-time triage nudge, this is a board annotation.
 # Unifying the two is a follow-up, not this intent.
 STALE_DAYS = 30
@@ -355,10 +355,7 @@ LIFECYCLE_GLYPH = { "what" => "○", "why" => "◔", "how" => "◑", "exec" => "
 DISPOSITION_GLYPH = { "drive" => "▸", "defer" => "⇢", "research" => "⊙", "triage" => "⚑" }.freeze
 LEGEND = "legend  ○ What ◔ Why ◑ How ◕ Exec ● Done │ ▸drive ⇢defer ⊙research ⚑triage │ ⇡unblocked"
 
-# Markdown board glyphs (intent 37). Quadrant signatures + per-line bullets.
-QUADRANT_BULLET = {
-  "quick_win" => "⚡", "next_big" => "★", "defer" => "→", "triage" => "⚑",
-}.freeze
+# Markdown board glyphs (intent 37). Status signature for the project active/future lists.
 STATUS_GLYPH = { "active" => "◑", "completed" => "●", "future" => "○" }.freeze
 
 # ---------------------------------------------------------------------------
@@ -375,10 +372,10 @@ end
 CELL_CAP = 6
 
 # Markdown-board caps (Task 5, D6/D7): the ASCII renderer already caps via CELL_CAP/
-# cap_cell, but the Markdown board's matrix_data quadrants and the project board's
+# cap_cell, but the Markdown board's next_work list and the project board's
 # active/future lists had no cap and no per-line truncation, so a large store printed
 # hundreds of full-length lines. These two constants fix that on the Markdown side only.
-MATRIX_DATA_CAP = 8
+NEXT_WORK_CAP = 8
 INTENT_LINE_MAX_CHARS = 120
 
 def matrix(records, scope_tag: false)
@@ -584,31 +581,39 @@ def intent_line(rec, bullet)
     scope: rec[:scope], line: "#{bullet} #{rec[:id]} #{text}#{note}".rstrip }
 end
 
-# Cap a raw record list to MATRIX_DATA_CAP entries, then map to intent_line-shaped
+# Cap a raw record list to NEXT_WORK_CAP entries, then map to intent_line-shaped
 # hashes, appending a plain "+N more" line (no id, not a real record) when truncated.
 # Caps the record list first so the "+N more" entry never goes through intent_line.
 def cap_lines(list, bullet)
-  capped = list.first(MATRIX_DATA_CAP)
+  capped = list.first(NEXT_WORK_CAP)
   lines = capped.map { |r| intent_line(r, bullet) }
-  if list.size > MATRIX_DATA_CAP
+  if list.size > NEXT_WORK_CAP
     lines << { id: "", intent: "", created: "", bullet: bullet, scope: "",
-               line: "#{bullet} +#{list.size - MATRIX_DATA_CAP} more" }
+               line: "#{bullet} +#{list.size - NEXT_WORK_CAP} more" }
   end
   lines
 end
 
-def matrix_data(records)
-  cells = { "quick_win" => [], "next_big" => [], "defer" => [], "triage" => [] }
-  research = []
-  records.each do |r|
-    if %w[research exploration].include?(r[:type]) then research << r
-    else cells[r[:quadrant]] << r end
+# Flat, rank-ordered "most-valuable next work" list (intent 149). Replaces the
+# quadrant-keyed matrix_data with a single list ranked by the same rank_key every
+# other ordering uses, capped at NEXT_WORK_CAP with a trailing "+N more" marker
+# when the pool overflows. No grid glyph on the line; the prose surface supplies
+# its own bullet.
+def next_work(records)
+  ranked = records.sort_by { |r| rank_key(r) }
+  capped = ranked.first(NEXT_WORK_CAP)
+  lines = capped.map do |r|
+    text = r[:intent].to_s
+    text = "#{text[0, INTENT_LINE_MAX_CHARS]}…" if text.length > INTENT_LINE_MAX_CHARS
+    { id: r[:id], intent: r[:intent], scope: r[:scope], lifecycle: r[:lifecycle],
+      value: r[:value].to_s, disposition: r[:disposition], flags: r[:flags],
+      line: "#{r[:id]} #{text}" }
   end
-  by_created_desc = ->(list) { list.sort_by { |r| invert_ts(r[:created]) } }
-  out = {}
-  cells.each { |q, list| out[q] = cap_lines(by_created_desc.call(list), QUADRANT_BULLET[q]) }
-  out["research"] = cap_lines(by_created_desc.call(research), "🔬")
-  out
+  if ranked.size > NEXT_WORK_CAP
+    lines << { id: "", intent: "", scope: "", lifecycle: "", value: "", disposition: "",
+               flags: [], line: "+#{ranked.size - NEXT_WORK_CAP} more" }
+  end
+  lines
 end
 
 def short_description(scope)
@@ -654,7 +659,7 @@ def render_data_global(records)
   { mode: "global", date: today.to_s,
     store_health: store_health(:global),
     recently_worked: recently_worked(records),
-    matrix: matrix_data(matrix_pool),
+    next_work: next_work(matrix_pool),
     counts: counts_of(global),
     projects: projs,
     project_totals: {
@@ -671,7 +676,7 @@ def render_data_project(records, slug)
     store_health: store_health(slug),
     description: short_description(scope),
     recently_worked: recently_worked(records, project_scope: scope),
-    matrix: matrix_data(matrix_pool),
+    next_work: next_work(matrix_pool),
     counts: counts_of(scoped),
     active: cap_lines(scoped.select { |r| r[:status] == "active" }
                             .sort_by { |r| invert_ts(r[:last_accessed_at]) }, STATUS_GLYPH["active"]),

package/scripts/doctor.rb

@@ -23,6 +23,9 @@ require_relative "lib/links_section"
 require_relative "lib/hook_registry"
 require_relative "lib/lock"
 require_relative "lib/bridge"
+require_relative "lib/agent_models"
+require_relative "lib/legacy_bookend_amnesty"
+require_relative "lib/skill_lint"
 
 # Diagnostic engine, instantiable with an injected store/agent map so tests can
 # run it hermetically (no eval, no global-constant rewriting).
@@ -41,6 +44,11 @@ class Doctor
   # (intent 60). Alias it here so the two can never drift.
   REQUIRED_FRONTMATTER_FIELDS = IntentValidator::REQUIRED_FIELDS
 
+  # Single source of truth for the pre-161 legacy Done-bookend amnesty list
+  # lives in LegacyBookendAmnesty (intent 170a). Alias it here so the two can
+  # never drift.
+  LEGACY_BOOKEND_AMNESTY = LegacyBookendAmnesty::LIST
+
   CLAUDE_HOOK_SCRIPTS = %w[
     plastic-session-start
     plastic-check-update
@@ -66,9 +74,11 @@ class Doctor
 
   attr_reader :plastic_home, :agents
 
-  def initialize(plastic_home: DEFAULT_PLASTIC_HOME, agents: DEFAULT_AGENTS)
+  def initialize(plastic_home: DEFAULT_PLASTIC_HOME, agents: DEFAULT_AGENTS,
+                  bookend_amnesty: LEGACY_BOOKEND_AMNESTY)
     @plastic_home = plastic_home
     @agents = agents
+    @bookend_amnesty = bookend_amnesty
   end
 
   # --- Flag parsing ---
@@ -577,6 +587,7 @@ class Doctor
     conflicts = [] # canonical INDEX-wins disagreement (fail)
     gaps = []      # terminal completeness gaps on immutable/legacy history (warn)
     stalled = []   # terminal but End tail unfinished (warn)
+    phantoms = []  # savepoint.md line(s) disk evidence contradicts (warn, never fail; intent 134)
 
     done_signal_stores(scopes).each do |store|
       index_sections_by_dir(store[:index]).each do |dirname, in_sections|
@@ -596,6 +607,24 @@ class Doctor
                        "(INDEX is canonical — move it to its terminal section or revert outcome.md)"
         end
 
+        # Savepoint truthfulness (advisory, never fail; intent 134): a line the disk contradicts
+        # (a phantom milestone, a duplicate pair, or a state line with an absent prerequisite).
+        # Live intents auto-rebuild via plastic-intent-savepoint; terminal intents are immutable,
+        # so a phantom there is report-only. Composition with intent 170a: a pre-161 legacy intent
+        # on the frozen bookend amnesty is grandfathered here too. Its immutable history carries
+        # known pre-convention drift (the same class the audit-echo gap forgives), so it must not
+        # resurface through this advisory. The suppression is scope-qualified exactly like the
+        # audit-echo amnesty; every live intent and every non-amnestied terminal still fires.
+        phantom_lines = Bridge.savepoint_phantom_lines(dir)
+        phantom_id = dirname.split("--", 2).first
+        phantom_amnestied = terminal && @bookend_amnesty.fetch(store[:scope], []).include?(phantom_id)
+        if phantom_lines.any? && !phantom_amnestied
+          detail = phantom_lines.map { |line, reason| "#{line} (#{reason})" }.join("; ")
+          scope_note = terminal ? "terminal in INDEX, report-only (immutable history)" : "live intent, auto-rebuildable"
+          phantoms << "#{label}: #{phantom_lines.size} phantom savepoint line(s) contradicted by " \
+                      "disk, #{scope_note}: #{detail}"
+        end
+
         # Completeness gap (warn, not fail): a terminal intent whose outcome.md is
         # missing/placeholder. Legacy terminal intents predate this convention and
         # are immutable, so this is advisory, never breakage.
@@ -608,11 +637,18 @@ class Doctor
         next unless terminal
 
         # Audit echo (weakest signal, D1): the savepoint should carry a
-        # `Done delivered|abandoned` line. Missing on legacy history -> advisory gap.
+        # `Done delivered|abandoned` line. Missing on legacy history -> advisory
+        # gap, unless the (scope, id) is on the frozen pre-161 amnesty list
+        # (intent 170a). The amnesty is scope-qualified: an id on the list for
+        # one scope does not grandfather the same id in another scope.
         savepoint = File.join(dir, "savepoint.md")
         if File.exist?(savepoint) && File.read(savepoint) !~ /\bDone\b.*\b(delivered|abandoned)\b/
-          gaps << "#{label}: terminal in INDEX but savepoint.md has no " \
-                  "`Done delivered|abandoned` line (audit echo missing)"
+          id = dirname.split("--", 2).first
+          amnestied = @bookend_amnesty.fetch(store[:scope], []).include?(id)
+          unless amnestied
+            gaps << "#{label}: terminal in INDEX but savepoint.md has no " \
+                    "`Done delivered|abandoned` line (audit echo missing)"
+          end
         end
 
         # Stalled completion: the End tail never released the delivery lock, so the
@@ -682,6 +718,26 @@ class Doctor
       )
     end
 
+    # savepoint_truthful: advisory only, never fails the run (intent 134). A phantom line on a
+    # live intent auto-rebuilds; on terminal (immutable) history it stays report-only.
+    if phantoms.empty?
+      checks << check(
+        category: "done_signals", name: "savepoint_truthful", status: "pass",
+        message: "No savepoint.md lines are contradicted by disk (phantom-line check clean)"
+      )
+    else
+      checks << check(
+        category: "done_signals", name: "savepoint_truthful", status: "warn",
+        message: "#{phantoms.size} intent#{phantoms.size == 1 ? "" : "s"} carry savepoint.md " \
+                 "line(s) contradicted by disk (advisory; terminal history stays report-only)",
+        details: phantoms, fixable: true,
+        fix_hint: "For a live (Active) intent, run plastic-intent-savepoint to rebuild via " \
+                  "Bridge.rebuild_savepoint. Terminal (Completed/Abandoned) intents are immutable: " \
+                  "a phantom there stays advisory unless an explicit human grant authorizes the " \
+                  "124a manual Done-bookend repair."
+      )
+    end
+
     checks
   end
 
@@ -1271,9 +1327,85 @@ class Doctor
       end
     end
 
+    checks += check_agent_model_drift(agent_key)
+
     checks
   end
 
+  # agent_model_drift - advisory (never fail) config-vs-frontmatter comparison
+  # for every installed <agent_dir>/agents/plastic-*.md file (intent 170, D1).
+  # Resolution mirrors read-config's own precedence (project override -> global
+  # override -> shipped AgentModels::TIER_DEFAULTS), reusing AgentModels'
+  # `override_map` directly so this stays hermetically DI-testable (no
+  # shell-out to `read-config`, no ENV/global seam). There is no live project
+  # scope at doctor-run time for a globally-installed agent file, so the
+  # project layer is empty here; the resolver still supports one, matching the
+  # same `override_map(project_config:, global_config:)` shape the installer
+  # already calls.
+  #
+  # Classification per installed agent basename:
+  #   - no `agents.models.<basename>` override AND frontmatter == resolved
+  #     default -> pass (clean)
+  #   - no override AND frontmatter != resolved default -> warn (real drift)
+  #   - an override IS configured -> pass/informational, LISTED as a
+  #     sanctioned override, regardless of whether frontmatter matches (that
+  #     mismatch is the override working, e.g. `plastic-brainstorming: fable`)
+  #   - zero installed agent files -> pass (nothing to check)
+  # This check never returns "fail".
+  def check_agent_model_drift(agent_key)
+    agent_config = agents[agent_key]
+    return [] unless agent_config
+
+    agents_dir = File.join(agent_config[:dir], "agents")
+    installed = Dir.glob(File.join(agents_dir, "plastic-*.md")).sort
+
+    if installed.empty?
+      return [check(
+        category: "core_files", name: "agent_model_drift", status: "pass",
+        message: "No installed plastic-* agent files to check for model drift"
+      )]
+    end
+
+    global_config = load_yaml_safe(File.join(plastic_home, "config.yml")) || {}
+    overrides = AgentModels.override_map(project_config: {}, global_config: global_config)
+
+    drifted = []
+    sanctioned = []
+
+    installed.each do |path|
+      basename = File.basename(path, ".md")
+      installed_model = (parse_frontmatter(path) || {})["model"]
+      resolved_default = AgentModels::TIER_DEFAULTS[basename]
+      override = overrides[basename]
+
+      if override
+        sanctioned << "#{basename}: frontmatter=#{installed_model.inspect}, sanctioned override=#{override.inspect}"
+      elsif installed_model != resolved_default
+        drifted << "#{basename}: frontmatter=#{installed_model.inspect}, resolved default=#{resolved_default.inspect}"
+      end
+    end
+
+    if drifted.empty?
+      message = if sanctioned.empty?
+                  "No agent-model drift (#{installed.size} installed agent(s) match the resolved default)"
+                else
+                  "No unsanctioned agent-model drift; #{sanctioned.size} sanctioned override(s) in effect"
+                end
+      [check(
+        category: "core_files", name: "agent_model_drift", status: "pass",
+        message: message,
+        details: sanctioned
+      )]
+    else
+      [check(
+        category: "core_files", name: "agent_model_drift", status: "warn",
+        message: "#{drifted.size} installed agent(s) have unsanctioned model drift vs the config-resolved default",
+        details: drifted + sanctioned,
+        fixable: false
+      )]
+    end
+  end
+
   # --- Check category: manifest sync (binary core integrity) ---
 
   # Verify, for BOTH the global manifest and the agent-side manifest, that every
@@ -1674,6 +1806,48 @@ class Doctor
     )
   end
 
+  # --- Check category: skill-lint (advisory only; intent 85b) ---
+  #
+  # Reports SkillLint's five structural checks over the skills/ tree as a
+  # single ADVISORY finding. Always status: "pass", so it can never contribute
+  # to doctor's warn/fail exit code (summarize buckets purely by status; the
+  # lint verdict belongs to a future ship gate, intent 100, not to doctor).
+  # Resolves the same repo skills/ directory `scripts/skill-lint` defaults to,
+  # relative to this script's own location. Skills install flat and renamed
+  # (plastic-<name>) under each agent's own skills/ dir, a different directory
+  # shape SkillLint's frontmatter name-check does not target, so an installed
+  # ~/.plastic/scripts/doctor.rb with no sibling skills/ tree has nothing in
+  # scope here and reports a silent pass rather than guessing at a mismatched
+  # layout.
+  def check_skill_lint
+    dir = File.expand_path("../skills", __dir__)
+    unless File.directory?(dir)
+      return [check(
+        category: "skill_lint", name: "skill_lint", status: "pass",
+        message: "No skills/ directory found at #{tilde(dir)} to lint (nothing in scope for this advisory check)"
+      )]
+    end
+
+    result = SkillLint.new(skills_dir: dir).run
+
+    if result.ok?
+      [check(
+        category: "skill_lint", name: "skill_lint", status: "pass",
+        message: "skill-lint: clean (0 violations across the skills/ tree)"
+      )]
+    else
+      by_check = result.violations.group_by { |v| v[:check] }.transform_values(&:size)
+      counts = by_check.map { |check_id, n| "#{check_id}: #{n}" }.join(", ")
+      details = result.violations.map { |v| "#{v[:check]} #{v[:skill]} #{v[:file]}:#{v[:line]}: #{v[:message]}" }
+      [check(
+        category: "skill_lint", name: "skill_lint", status: "pass",
+        message: "skill-lint: #{result.violations.size} advisory violation(s) found (#{counts}); " \
+                  "informational only, never affects doctor's exit code",
+        details: details
+      )]
+    end
+  end
+
   # --- Run all checks ---
 
   def run_checks(agent_key)
@@ -1686,6 +1860,7 @@ class Doctor
     all_checks += check_deprecations
     all_checks += check_qmd
     all_checks += check_done_signals
+    all_checks += check_skill_lint
 
     summarize(all_checks, agent_key)
   end
@@ -1801,4 +1976,4 @@ class Doctor
 
 end
 
-Doctor.new.cli(ARGV) if $PROGRAM_NAME == __FILE__
+Doctor.new(plastic_home: ENV.fetch("PLASTIC_HOME") { Doctor::DEFAULT_PLASTIC_HOME }).cli(ARGV) if $PROGRAM_NAME == __FILE__

package/scripts/hook-continue

@@ -19,9 +19,9 @@ cockpit, _err, status = Open3.capture3("ruby", dashboard, "continue")
 exit 0 unless status.success? && !cockpit.strip.empty?
 
 context = cockpit.rstrip +
-  "\n\nFollow the plastic-intent-continuing skill workflow to resume: " \
-  "if active intents exist, read their state and resume; otherwise offer the " \
-  "Value×Effort matrix items above, surfacing any stale (Nd) / ⚑ triage intents."
+  "\n\nFollow the plastic-continuing skill workflow to resume: " \
+  "if active intents exist, read their state and resume; otherwise surface the " \
+  "most-valuable next work and any stale or triage intents from the board above."
 
 payload = {
   "hookSpecificOutput" => {

package/scripts/install.rb

@@ -168,4 +168,5 @@ class Install < InstallerCore
   end
 end
 
-exit(Install.new(package_root: ENV["PLASTIC_PACKAGE_ROOT"] || File.expand_path("..", __dir__)).cli(ARGV)) if $PROGRAM_NAME == __FILE__
+exit(Install.new(package_root: ENV["PLASTIC_PACKAGE_ROOT"] || File.expand_path("..", __dir__),
+                 plastic_home: ENV.fetch("PLASTIC_HOME") { InstallerCore::DEFAULT_PLASTIC_HOME }).cli(ARGV)) if $PROGRAM_NAME == __FILE__