session-orchestrator 4.1.0 → 4.2.0

package/skills/bootstrap/public-fallback.md

@@ -5,32 +5,38 @@
 
 ## Step 1: Detect PATH_TYPE (Silent — No User Interaction)
 
-Read `plan-baseline-path` from Session Config in `CLAUDE.md` (or `AGENTS.md` on Codex):
+Run the dependency-free local contract reader. It uses the existing configuration
+resolvers, with precedence `SO_BASELINE_PATH` → matching named baseline →
+`owner.yaml` `paths.baseline-path` → committed Session Config. Paths resolve
+host-locally and are never written into the contract result.
 
 ```bash
-BASELINE_PATH=$(grep -m1 "^plan-baseline-path:" "$REPO_ROOT/CLAUDE.md" 2>/dev/null | awk '{print $2}')
-# Expand leading ~ to $HOME so paths like ~/Projects/projects-baseline work correctly
-BASELINE_PATH="${BASELINE_PATH/#\~/$HOME}"
+BOOTSTRAP_CONTRACT=$(node "$PLUGIN_ROOT/scripts/baseline-archetypes.mjs" --repo "$REPO_ROOT") || exit 2
+PATH_TYPE=$(printf '%s' "$BOOTSTRAP_CONTRACT" | node --input-type=module -e '
+let input = ""; for await (const chunk of process.stdin) input += chunk;
+process.stdout.write(JSON.parse(input).status);
+')
+export BOOTSTRAP_CONTRACT PATH_TYPE
 ```
 
-Decision logic (evaluated in order — first match wins):
+| Reader outcome | Bootstrap behavior |
+|----------------|--------------------|
+| No configured baseline, empty value, or missing directory | `public`; use bundled templates |
+| Existing baseline with valid reduced schema v1 export | `private`; retain `archetypes` and `selected` |
+| Existing baseline with missing CLI, invalid export, unsafe source, or producer failure | Abort; report the sanitized error reason |
+| Valid private contract but no matching repository markers | `private`, `selected: null`; require selection for Standard/Deep |
 
-| Condition | PATH_TYPE |
-|-----------|-----------|
-| `plan-baseline-path` key is absent in Session Config | `public` |
-| `plan-baseline-path` key is present but value is empty | `public` |
-| Key is present, value is non-empty, AND `test -d "$BASELINE_PATH"` succeeds | `private` |
-| Key is present, value is non-empty, BUT path does not exist on disk | `public` |
-
-Set `PATH_TYPE = private | public`. Do not report this detection to the user — it is silent.
-
-> **Note on rules-fetch (Phase 3.5 of SKILL.md):** The optional rules-fetch step runs regardless of `PATH_TYPE`. Both private (with `plan-baseline-path` set) and public (without it) repos can opt into the fetch by setting `baseline-ref` in Session Config. The fetch is independent of how the initial scaffold was generated.
-
----
+Lookup is offline and read-only. A broken configured contract never silently
+switches to a public archetype. Missing directories retain the established
+public fallback. Never guess a baseline path or fetch one automatically.
 
 ## Private Path
 
-When `PATH_TYPE = private`, the baseline templates are used directly. No new logic is needed here — the existing tier-template flow (`fast-template.md`, `standard-template.md`, `deep-template.md`) already calls `$BASELINE_PATH` scripts for CLAUDE.md generation and archetype file sourcing. Continue with the calling template file's steps unchanged.
+Read and execute [`private-contract.md`](private-contract.md): use its selection,
+staged scaffold, command/CI expectations, and S99 rule projection. Keep
+`CONFIRMED_ARCHETYPE` as the validated contract ID throughout the tier flow.
+The optional remote rules fetch is only a public-path opt-in; a configured
+private baseline supplies selected rules locally.
 
 ---
 
@@ -38,6 +44,12 @@ When `PATH_TYPE = private`, the baseline templates are used directly. No new log
 
 When `PATH_TYPE = public`, no `projects-baseline` is available. Use the plugin-bundled templates and platform-appropriate CLAUDE.md generation described below.
 
+For each file newly created by these steps, append its relative filename to the
+existing `BOOTSTRAP_FILES` array. This includes instruction files, minimal
+README/gitignore files and each copied template file. Preserve the accumulated
+array through inherited tiers; never append a directory or an existing owner
+file just because it is present.
+
 ### Detect Platform
 
 Read the current platform using the patterns from `skills/_shared/platform-tools.md`:

package/skills/bootstrap/standard-template.md

@@ -5,6 +5,20 @@
 
 Standard tier is a strict superset of Fast tier. Execute all Fast-tier steps first, then the Standard-specific steps below.
 
+Track actual newly created relative files in one `BOOTSTRAP_FILES` array across
+all inherited steps. Append each file when created; preserve the array across
+repeated steps. Never append an existing owner file or a directory.
+
+## Private Contract Preparation
+
+When `PATH_TYPE = private`, resolve `CONFIRMED_ARCHETYPE` with
+`private-contract.md` and execute its Scaffold section **before** the inherited
+Fast steps. Preserve its rendered metadata, manifests, source, README and CI.
+Add its reported created files to `BOOTSTRAP_FILES`. Skip the four public
+archetype sections below, then continue at Step 3a, S99 and the lock/quality-policy
+steps. Populate command expectations from the selected contract as described
+in `private-contract.md`.
+
 ## Step 1–7: Execute Fast Tier
 
 Read and execute `skills/bootstrap/fast-template.md` Steps 1–7 in full. Do not skip any step. The Fast commit (`chore: bootstrap (fast)`) is NOT made — Fast steps produce files only; the single commit happens at Standard Step 7 below.
@@ -21,9 +35,9 @@ Before executing the stack-specific steps, resolve the final archetype:
 ARCHETYPE = CONFIRMED_ARCHETYPE  # set by SKILL.md from intensity-heuristic or user selection
 ```
 
-Valid values: `static-html` | `node-minimal` | `nextjs-minimal` | `python-uv`
+For `PATH_TYPE = public`, valid values are `static-html` | `node-minimal` | `nextjs-minimal` | `python-uv`. Private IDs come only from the validated contract.
 
-If `ARCHETYPE` is `null` or unset at this point, default to `node-minimal`.
+On the public path only, if `ARCHETYPE` is `null` or unset, default to `node-minimal`. A private missing/invalid selection aborts before scaffolding; it never reaches the public sections.
 
 The sections below are conditional on `ARCHETYPE`. Execute only the section that matches.
 
@@ -592,12 +606,11 @@ indent_size = 2
 
 Canonical implementation in [`_shared-template.md#parallel-sessions-rule`](_shared-template.md).
 
-Run `node "$PLUGIN_ROOT/scripts/lib/rules-sync.mjs" --repo-root "$REPO_ROOT"` — it vendors every
-rule registered in `rules/_index.md` (idempotent: missing→create, identical→skip, differs→overwrite),
-and it is the only writer that applies the pre-write validator, the basename-collision guard and the
-copy-on-write branch that preserves repo-private rules. The shared partial also runs
-`cp "$PLUGIN_ROOT/templates/_shared/loop.md" "$REPO_ROOT/.claude/loop.md"` so bare `/loop` gets a
-repo-aware maintenance prompt. See shared partial for full shell command. Issues #155, #633, #1060.
+Execute the shared partial's `syncBootstrapRules` action. It supplies private
+required basenames to `scripts/lib/rules-sync.mjs`, preserving its manifest,
+pre-write validation and local-override checks. The partial appends actual newly
+created rule paths, and creates `.claude/loop.md` only when missing. See the
+shared partial for the executable shell command. Issues #155, #633, #1060.
 
 Note: Runs before S99. S99 no longer fetches `parallel-sessions.md` from the baseline — that entry
 was removed from the S99 manifest in #1060. The baseline copy carries no provenance header, so
@@ -611,8 +624,10 @@ Create the metrics directory and an empty learnings file so the `/evolve` skill
 
 ```bash
 mkdir -p "$REPO_ROOT/.orchestrator/metrics"
-[[ -f "$REPO_ROOT/.orchestrator/metrics/learnings.jsonl" ]] || \
+if [[ ! -e "$REPO_ROOT/.orchestrator/metrics/learnings.jsonl" && ! -L "$REPO_ROOT/.orchestrator/metrics/learnings.jsonl" ]]; then
   : > "$REPO_ROOT/.orchestrator/metrics/learnings.jsonl"
+  BOOTSTRAP_FILES+=(.orchestrator/metrics/learnings.jsonl)
+fi
 ```
 
 **Idempotent.** Re-running bootstrap does not overwrite an existing file.
@@ -624,11 +639,13 @@ mkdir -p "$REPO_ROOT/.orchestrator/metrics"
 
 Canonical implementation in [`_shared-template.md#baseline-fetch`](_shared-template.md).
 
-OPT-IN: only fires when `baseline-ref` is in Session Config, `GITLAB_TOKEN` is set, and
+PRIVATE: applies the selected local contract rule union without network access, preserving existing files and excluding every plugin-owned basename. An invalid contract aborts.
+
+PUBLIC OPT-IN: only fires when `baseline-ref` is in Session Config, `GITLAB_TOKEN` is set, and
 `scripts/lib/fetch-baseline.mjs` exists. Fetches `.claude/rules/*.md` from the baseline GitLab
 project (default project 52) and writes `.claude/.baseline-fetch.lock`. Does NOT abort on failure.
-The rule manifest includes `owner-persona.md` (alongside `parallel-sessions.md`, `development.md`,
-and the rest of the always-on rules). See shared partial for full implementation.
+The private rule manifest comes from the selected contract. Every plugin-owned
+basename is excluded from either delivery path. See the shared partial.
 
 ---
 
@@ -649,6 +666,8 @@ Write `.orchestrator/bootstrap.lock` **atomically** (mktemp + mv prevents a corr
 process is interrupted mid-write):
 
 ```bash
+_LOCK_CREATED=false
+[[ -e "$REPO_ROOT/.orchestrator/bootstrap.lock" || -L "$REPO_ROOT/.orchestrator/bootstrap.lock" ]] || _LOCK_CREATED=true
 _LOCK_TMP=$(mktemp "$REPO_ROOT/.orchestrator/bootstrap.lock.XXXXXX")
 cat > "$_LOCK_TMP" << LOCK
 # .orchestrator/bootstrap.lock
@@ -661,6 +680,7 @@ plugin-version: <session-orchestrator plugin version — read from $PLUGIN_ROOT/
 bootstrapped-at: <current ISO 8601 UTC — same value as timestamp; distinct field for age-validation probe>
 LOCK
 mv "$_LOCK_TMP" "$REPO_ROOT/.orchestrator/bootstrap.lock"
+if [[ "$_LOCK_CREATED" = true ]]; then BOOTSTRAP_FILES+=(.orchestrator/bootstrap.lock); fi
 ```
 
 Set `source` using the same logic as fast-template Step 5:
@@ -673,8 +693,8 @@ Set `source` using the same logic as fast-template Step 5:
 
 Canonical implementation in [`_shared-template.md#quality-gate-policy`](_shared-template.md).
 
-Write `.orchestrator/policy/quality-gates.json` with package-manager-detected defaults (idempotent:
-skip if file already exists). Uses `scripts/lib/package-manager.mjs`; falls back to npm defaults.
+Write `.orchestrator/policy/quality-gates.json` from exact private contract gates,
+or package-manager defaults on the public path. Skip existing owner policy.
 See shared partial for full shell command. Issue #183.
 
 <!-- @include _shared-template.md#state-md-scaffold -->
@@ -682,8 +702,9 @@ See shared partial for full shell command. Issue #183.
 
 Canonical implementation in [`_shared-template.md#state-md-scaffold`](_shared-template.md).
 
-Scaffold `.claude/STATE.md` from `skills/bootstrap/STATE.md.template` (idempotent: skip if
-already exists). On Codex CLI / Cursor IDE, substitute `.codex/` or `.cursor/` for `.claude/`.
+Scaffold `.claude/STATE.md` (idempotent: skip if it already exists). <!-- path-check: example -->
+Use `skills/bootstrap/STATE.md.template`.
+On Codex CLI / Cursor IDE, substitute `.codex/` or `.cursor/` for `.claude/`.
 See shared partial for full shell command. Issue #184.
 
 <!-- @include _shared-template.md#agents-scaffold -->
@@ -701,15 +722,9 @@ Stage all created files and commit:
 
 ```bash
 cd "$REPO_ROOT"
-BOOTSTRAP_FILES=(
-  CLAUDE.md AGENTS.md .gitignore README.md .orchestrator/bootstrap.lock
-  .orchestrator/policy/quality-gates.json
-  package.json pyproject.toml tsconfig.json eslint.config.mjs .prettierrc
-  .editorconfig src/ tests/ .claude/
-)
 # Add only the files bootstrap created — no sweeping -u/-A to avoid catching pre-existing files
-for _f in "${BOOTSTRAP_FILES[@]}"; do
-  [[ -e "$_f" ]] && git add -- "$_f"
+for _f in ${BOOTSTRAP_FILES[@]+"${BOOTSTRAP_FILES[@]}"}; do
+  [[ -f "$_f" && ! -L "$_f" ]] && git add -- "$_f"
 done
 git commit -m "chore: bootstrap (standard)"
 ```

package/skills/discovery/probes-ui.md

@@ -142,6 +142,6 @@ fpRisk: low | medium | high
 
 **Default Severity:** Per-rule (high for the absolute-ban tells, low for advisory quality nits). `fpRisk` is reported so triage can weight high-FP rules (`ai-purple-gradient`) more skeptically.
 
-> **Precision boundary (honest):** this regex tier cannot resolve CSS cascade, so `side-stripe-border` flags any ≥2px side accent even when the element is unrounded — `.claude/rules/frontend.md` bans those (>1px accent), but a cascade-aware detector would narrow further. The heavier static-HTML + browser tiers are deliberately omitted (cost ≫ value for a probe/hook). See `scripts/lib/frontend-detect/rules.mjs`.
+> **Precision boundary (honest):** this regex tier cannot resolve CSS cascade, so `side-stripe-border` flags any ≥2px side accent even when the element is unrounded — `rules/opt-in-stack/frontend.md` bans those (>1px accent), but a cascade-aware detector would narrow further. The heavier static-HTML + browser tiers are deliberately omitted (cost ≫ value for a probe/hook). See `scripts/lib/frontend-detect/rules.mjs`.
 
 ---

package/skills/docs-orchestrator/audience-mapping.md

@@ -8,7 +8,7 @@ Rules for mapping session scope to target audiences, content sources, and docume
 
 | Audience | Target files (globs) | Typical update triggers |
 |----------|----------------------|-------------------------|
-| User | `README.md`, `docs/user/**/*.md`, `docs/getting-started.md`, `examples/**/*.md` | new CLI command, breaking API change, install flow change, new user-facing feature, changed example output |
+| User | `README.md`, `docs/user/**/*.md`, `docs/getting-started.md`, `examples/**/*.md` | new CLI command, breaking API change, install flow change, new user-facing feature, changed example output <!-- path-check: example --> |
 | Dev | `CLAUDE.md` (or `AGENTS.md` on Codex CLI), `docs/dev/**/*.md`, `docs/adr/**/*.md` | architecture decision, major refactor, new module/subsystem, test coverage change, dependency upgrade, ADR-worthy choice |
 | Vault/Ops | `<vault>/01-projects/<slug>/context.md`, `<vault>/01-projects/<slug>/decisions.md`, `<vault>/01-projects/<slug>/people.md` | project status change, ownership transition, stack/infra decision, cross-project dependency, migration, archival event |
 

package/skills/evolve/SKILL.md

@@ -634,7 +634,7 @@ const result = await runDialecticDeriver({
 ```
 
 ### Step 6.4: Diff Output & Apply Gate
-- If dry-run (default): present diff inline; write to `.orchestrator/dialectic-pending.md` (atomic tmp+rename); EXIT. Suggestion: "Re-run with `/evolve --dialectic --apply` to apply."
+- If dry-run (default): present diff inline; write to `.orchestrator/dialectic-pending.md` (atomic tmp+rename); EXIT. Suggestion: "Re-run with `/evolve --dialectic --apply` to apply." <!-- path-check: example -->
 - If `--apply`: call `mergePeerCard(existingBody, managedUpdates)` from `scripts/lib/peer-cards/merger.mjs` for each card target, then `writePeerCard(repoRoot, 'user', mergedUserCard)` and `writePeerCard(repoRoot, 'agent', mergedAgentCard)` from `scripts/lib/peer-cards/writer.mjs`. Update the `updated:` frontmatter.
 - Report: `Dialectic-derived: M deltas to USER.md, N deltas to AGENT.md. Dry-run | Applied. Tokens: in=<X> out=<Y>.`
 
@@ -666,7 +666,7 @@ await recordDialecticRun({
 - `status: 'budget-exceeded'` → emit `{status:'budget-exceeded', used:N, budget:M}`, do NOT truncate
 - `status: 'would-empty-card'` → warn + require `--allow-emptying` flag
 - `status: 'empty-input'` → exit clean with message "dialectic: skipped (no input)"
-- subagent crash → log ⚠, exit cleanly (do NOT write to `.orchestrator/dialectic-pending.md`)
+- subagent crash → log ⚠, exit cleanly (do NOT write to `.orchestrator/dialectic-pending.md`) <!-- path-check: example -->
 
 **Telemetry (#1200, #1206) — emitted by `scripts/dialectic-deriver.mjs` for THREE of the five
 outcomes.** `budget-exceeded`, `would-empty-card`, and `empty-input` are `runDialecticDeriver()`

package/skills/gitlab-ops/SKILL.md

@@ -111,7 +111,7 @@ done
 **Taxonomy convention — `priority` REVERSED to scoped `::` (supersedes #727 for this one axis).**
 
 - **`priority::<level>` is canonical.** #727's stated rationale was that "this repo mirrors to GitHub, which has no scoped-label semantics … while a migration would break every existing label reference and issue." Both halves were checked on 2026-07-25 and neither holds:
-  - **Issues are not mirrored at all.** `aiat-poc-infra/docs/github-mirror-runbook.md:1,5` describes a git **push-mirror** with GitHub as "read-only downstream"; `docs/gitlab-team-org-2026-06-21.md:45` confirms there is no two-way GitLab issue sync. Nothing crosses the boundary that a label rename could break.
+  - **Issues are not mirrored at all.** `aiat-poc-infra/docs/github-mirror-runbook.md:1,5` describes a git **push-mirror** with GitHub as "read-only downstream"; the external team-organization audit `docs/gitlab-team-org-2026-06-21.md:45` confirms there is no two-way GitLab issue sync. Nothing crosses the boundary that a label rename could break. <!-- path-check: example -->
   - **GitHub already uses the scoped form.** `gh api "repos/AIAT-AIandBusinessgrowth/aiat-barrierefrei-engine/labels"` returns `priority::high`, `priority::low`, `priority::med`, `priority::medium` across 77 open issues, and **zero** `priority:high`. Same pattern on `aiat-doc-vlm`. GitHub treats `::` as an ordinary string; it merely does not enforce mutual exclusion.
   - Volume agrees independently: **416 `priority::` against 249 `priority:` and 7 bare** at the time of the decision. Chasing the minority spelling would mean re-labelling the majority.
   Producers were migrated FIRST (this change); the label-data migration follows separately, because migrating data before producers means the divergence returns within a day.
@@ -340,8 +340,8 @@ Bash calls when the current session contains no prior `Read` on a matching templ
 **When this matters:** before you or a subagent opens an MR, PR, or issue via CLI, a
 matching template must have been read in the current session:
 
-- GitHub: `.github/PULL_REQUEST_TEMPLATE.md` / `.github/ISSUE_TEMPLATE*`
-- GitLab: `.gitlab/merge_request_templates/Default.md` / `.gitlab/issue_templates/*`
+- GitHub: `.github/pull_request_template.md` / `.github/ISSUE_TEMPLATE*`
+- GitLab: `.gitlab/merge_request_templates/Default.md` / `.gitlab/issue_templates/*` <!-- path-check: example -->
 
 Accepted template paths are configured in `.orchestrator/policy/templates-policy.json`
 (versioned, operator-editable). Default behaviour:

package/skills/grill/SKILL.md

@@ -33,7 +33,7 @@ Read `soul.md` in this skill directory before anything else. It defines WHO you
 Establish *what* you are grilling and ground yourself in the *code* before asking the user anything.
 
 1. **Resolve the target.** Parse `$ARGUMENTS`:
-   - A file path (e.g. `docs/prd/2026-06-09-export.md`, `STATE.md`, a spec) → read it in full.
+   - A file path (e.g. `docs/prd/2026-06-09-export.md`, `STATE.md`, a spec) → read it in full. <!-- path-check: example -->
    - A topic/slug or empty → grill the plan or idea already present in the current conversation. If there is no plan in context, ask the user — via AUQ — to state the plan in one or two sentences before continuing.
 2. **Ground in the codebase.** Read the project's domain language if present (`CONTEXT.md`, `.orchestrator/steering/*.md`, relevant `docs/adr/*`), then Grep/Glob the areas the plan touches. Build a short mental model of what the code *actually* does today. This is what lets you run the code-contradiction tactic.
 3. **State the target back.** In 1–2 plain-text sentences, summarize what you understand the plan to be and what you've grounded it against. This catches a wrong target before you waste a grill on it.

package/skills/memory-cleanup/SKILL.md

@@ -35,8 +35,8 @@ This skill accepts two optional flags. Default (no flag) runs the interactive 4-
 
 | Flag | Behavior |
 |---|---|
-| `--dry-run` | Run Phases 1-3 read-only; instead of mutating MEMORY.md / topic files, write a complete-body MEMORY.md proposal (single fenced block — never a unified-diff) to `.orchestrator/pending-dream.md` (atomic). Exit 0. |
-| `--apply-pending` | Read `.orchestrator/pending-dream.md`; refuse if older than 14 days (`stale`) or if MEMORY.md changed since the producing --dry-run (`stale-index`, #788); apply diff; delete pending file; print `auto-dream applied: -<X> lines, +<Y> entries`. Exit 0. |
+| `--dry-run` | Run Phases 1-3 read-only; instead of mutating MEMORY.md / topic files, write a complete-body MEMORY.md proposal (single fenced block — never a unified-diff) to `.orchestrator/pending-dream.md` (atomic). Exit 0. <!-- path-check: example --> |
+| `--apply-pending` | Read `.orchestrator/pending-dream.md`; refuse if older than 14 days (`stale`) or if MEMORY.md changed since the producing --dry-run (`stale-index`, #788); apply diff; delete pending file; print `auto-dream applied: -<X> lines, +<Y> entries`. Exit 0. <!-- path-check: example --> |
 
 Flags are mutually exclusive — passing both is an error. Absence of both = legacy interactive mode (Phases 1-4 below).
 

package/skills/plan/mode-new.md

@@ -40,6 +40,15 @@ Agent({ subagent_type: "Explore", description: "Check ecosystem for conflicts",
 5. **Core problem being solved** — Open-ended. Claude suggests structure if answer is vague.
 6. **GitLab group** — Select the GitLab host explicitly, then discover available groups dynamically. Run `ls $BASELINE_PATH/templates/` for project types, and check for a groups config in `$BASELINE_PATH/config/` or run `glab api --hostname "$GITLAB_HOST" "groups?per_page=100&min_access_level=10"` to discover GitLab groups — read each entry's `full_path` field. (`glab` has no `group` subcommand at all — invoking one exits 1 with `Unknown command "group"`.) Present findings via AskUserQuestion.
 
+### Optional private capability context — after Wave 1
+
+Before Wave 2 research, apply [Private capability context](../_shared/private-capability-context.md)
+only when the owner has explicitly supplied or authorized a local catalog lookup
+for an explicitly private/internal planning audience. Use eligible findings to
+inform the existing shared-patterns research and reuse alternatives; keep the
+archetype research and questions below. With no authorized context, or with a
+public/unknown audience, skip this optional step without a prompt or a lookup.
+
 ### Wave 2 — Technical Details (5 questions, dynamic per archetype)
 
 **Pre-wave agents:**

package/skills/reconcile/SKILL.md

@@ -238,7 +238,7 @@ Exit after printing. Do not proceed to Phase 4.
 
 ## Phase 4: Write Pending Sidecar (Normal Mode Only)
 
-Write the proposals to `.orchestrator/metrics/reconcile-pending.md` as a human-readable
+Create the runtime proposal sidecar `.orchestrator/metrics/reconcile-pending.md` as a human-readable <!-- path-check: example -->
 record before presenting the AUQ. This sidecar is informational only — it lets the operator
 see the full proposal set in an editor alongside the AUQ prompt.
 

package/skills/session-end/SKILL.md

@@ -280,8 +280,8 @@ Present to the user the **Session Summary**: Completed / Carried Over / Dropped
 | `references/phase-3-documentation-updates.md` | Phase 3 full procedural body — final heartbeat (#590-3), 3.0 Defensive Cleanup, 3.1 SSOT files, 3.2/3.2a docs + handover, 3.3 rules freshness, 3.4/3.4a STATE.md write + snapshot cleanup, 3.45 Telemetry Flush, 3.5/3.5a/3.6.x memory + learnings + tail dispatcher, 3.7/3.7a/3.7b/3.7c/3.7d metrics, recommendations, durable commit, vault board, session-eval |
 | `phase-3-2-docs-verification.md` | Phase 3.2 full procedural body — docs-tasks load, SESSION_START_REF, per-task loop, mode-gated report, Documentation Coverage block |
 | `learning-patterns.md` | Phases 3.5a + 3.6 extraction heuristics, confidence updates, passive decay, and JSONL write procedure |
-| `phase-3-6-tail.md` | Phase 3.6.x tail — full unabridged detail procedures for all six tail phases: 3.6.3 Memory-Proposals Collection (`collectProposals` + AUQ multiSelect + `promoteAndClear`, composing `writeApproved` + `clearProposalsJsonl` behind a mechanical write-before-clear guard, #828), 3.6.4 Expired-Learnings Sweep (Epic #723 B4), 3.6.5 Auto-Dream nudge (`shouldDispatchAutoDream`, #614), 3.6.6 Skill-Applied Judge (#645 L3 — `runSkillJudge`, coordinator-writes), 3.6.7 Auto-Dialectic nudge (`shouldDispatchAutoDialectic`, #614), 3.6.8 Reconciliation Rule Proposals (#696 FA3 — `runReconcile` + AUQ + `writeApprovedRules`). Loaded on demand by the SKILL.md skip-plan dispatcher (#724) — only phases with `run: true` in the `planTailPhases()` plan execute |
-| `scripts/lib/session-end/phase-skip.mjs` | Phase 3.6.x tail skip-plan aggregator (#724) — `planTailPhases({repoRoot, config, sessionId, platform})` → `{plan, skippedReport}`; side-effect-free (reconcile/sweep via dry-run — no writes), never-throws (per-phase probe error fail-opens to `run: true`); wraps the six existing signal helpers with config gates first, then input detection |
+| `phase-3-6-tail.md` | Phase 3.6.x tail — detail procedures for the tail phases: 3.6.3 Memory-Proposals Collection (`collectProposals` + AUQ multiSelect + `promoteAndClear`, composing `writeApproved` + `clearProposalsJsonl` behind a mechanical write-before-clear guard, #828), **3.6.4 Expired-Learnings Sweep — MECHANICAL since 2026-09-09**: after `planTailPhases()`, call `runTailPhases({ repoRoot, plan })` from `scripts/lib/session-end/tail-runner.mjs` (delegating to `runExpiredSweep`) and report `result['3.6.4']` (`ran`, `scanned`, `archived`); the event `orchestrator.learnings.sweep_applied` is the proof it ran (Epic #723 B4), **3.6.5 Auto-Dream — RETIRED** and **3.6.7 Auto-Dialectic — RETIRED** (both replaced by the session-start `maintenance-due` probe, `checkMaintenanceDue` in `scripts/lib/maintenance-due-banner.mjs`; headings kept as two-line stubs because other docs cite them), 3.6.6 Skill-Applied Judge (#645 L3 — `runSkillJudge`, coordinator-writes), 3.6.8 Reconciliation Rule Proposals (#696 FA3 — `runReconcile` + AUQ + `writeApprovedRules`). Loaded on demand by the SKILL.md skip-plan dispatcher (#724) — only phases with `run: true` in the `planTailPhases()` plan execute |
+| `scripts/lib/session-end/phase-skip.mjs` | Phase 3.6.x tail skip-plan aggregator (#724) — `planTailPhases({repoRoot, config, sessionId, platform})` → `{plan, skippedReport}`; side-effect-free (reconcile/sweep via dry-run — no writes), never-throws (per-phase probe error fail-opens to `run: true`). Since 2026-09-09 it plans FOUR phases, not six: the 3.6.5 (auto-dream) and 3.6.7 (auto-dialectic) deciders were removed with those phases' retirement. Its APPLY half for 3.6.4 is `scripts/lib/session-end/tail-runner.mjs` (`runTailPhases`, `runExpiredSweep`) — the planner fails OPEN, the runner fails CLOSED |
 | `references/phase-3-documentation-updates.md` § 3.45 | Telemetry Flush (advisory, #844; MECHANICAL since #1138 — `hooks/on-session-end.mjs` calls `flush()` itself at the end of every teardown and emits an `orchestrator.telemetry.flush` breadcrumb, so this phase is the DESCRIPTION and the fallback, never the trigger; a coordinator that skips it changes nothing) — `flush()` from `scripts/lib/telemetry/sync.mjs` drains the host-local send-queue fire-and-forget; no config key (send-gate is `resolveConsent()` inside the module, fail-closed); skip when `persistence: false`; never-throw + ~3s-bounded, offline → bounded oldest-dropped queue, optional `Telemetry: sent/queued/gated` close-summary line, NEVER an error banner; runs late in the close after Phase 3.7 |
 | `session-metrics-write.md` | Phase 3.7 JSONL append, vault-mirror invocation, durable narrative mirror (`mirrorNarrative`, #675), and behavior matrix |
 | `phase-3-7a-recommendations.md` | Phase 3.7a full procedural body — computeV0Recommendation call, STATE.md field write, data source guarantee, error mode |
@@ -293,6 +293,7 @@ Present to the user the **Session Summary**: Completed / Carried Over / Dropped
 | `references/phase-4a-worktree-cleanup.md` | Phase 4a full procedural body — auto-promoted-worktree detection (`detectAutoPromotedWorktree`, marker-keyed since #1069), clean-check, clean auto-remove path, dirty 3-option AUQ (`Behalten`/`Löschen`/`Manuell`), PSA-003 + #490 ordering rationale |
 | `references/phase-4b-worktree-orphan-sweep.md` | Phase 4b full procedural body — `checkWorktreeOrphans()` read-only proposal set, the coordinator-rendered AUQ, opt-in `worktree-orphans.enabled` gate |
 | `references/phase-5-issue-cleanup.md` | Phase 5 full procedural body — close resolved issues (`stripStatusLabels`, #308), Step 3 filing of the Phase 1.65 carry-list incl. the deferred `createSpiralCarryoverIssue` and `markOpenQuestionAnsweredOnDisk`, Step 3b `[Backlog-Sammel]` overflow, discovery-issue creation |
+| `references/phase-5-issue-cleanup.md` § Step 3b.2 (issue-budget reconcile) | Phase 5 issue-budget cross-check — `reconcileIssueBudget({ repoRoot, record, sessionId, rawSessionId, config })` from `scripts/lib/issue-budget-reconcile.mjs` runs on the in-memory session record BEFORE it is appended to `sessions.jsonl`, `emitIssueBudgetReconciled` records `orchestrator.issue_budget.reconciled`, and `formatIssueBudgetReconcileWarn(result)` prints the verdict (`match` / `no-ledger` / `escaped` / `stale-record`) in the Final Report. Ordered AFTER the overflow drain (which resets `overflow[]`) and BEFORE `reapStaleBudgetFiles` (which must not remove the file being read) |
 | `references/session-summary-template.md` | Phase 6 Final Report — the full Session Summary template (Completed / Carried Over / Dropped at Handover Gate / New Issues / Unresolved Review Findings / Metrics incl. Docs Health + Custom Phases / Next Session Recommendations) plus the Test-delta and Documentation-Coverage anchors |
 
 ## Anti-Patterns

package/skills/session-end/phase-3-2-docs-verification.md

@@ -57,7 +57,7 @@ The following mini-table mirrors `skills/docs-orchestrator/audience-mapping.md`
 
 | Audience | Target file patterns |
 |----------|----------------------|
-| `user` | `README.md`, `docs/user/**/*.md`, `docs/getting-started.md`, `examples/**/*.md` |
+| `user` | `README.md`, `docs/user/**/*.md`, `docs/getting-started.md`, `examples/**/*.md` <!-- path-check: example --> |
 | `dev` | `CLAUDE.md` (or `AGENTS.md` on Codex CLI), `docs/dev/**/*.md`, `docs/adr/**/*.md` |
 | `vault` | `<vault>/01-projects/<slug>/context.md`, `<vault>/01-projects/<slug>/decisions.md`, `<vault>/01-projects/<slug>/people.md` |
 

package/skills/session-end/phase-3-6-tail.md

@@ -11,7 +11,7 @@
 > - `memory.proposals.enabled` is `false` (default: `true`)
 > - `.orchestrator/metrics/proposals.jsonl` does not exist OR contains zero entries
 
-After learnings are written (Phase 3.6) and BEFORE auto-dream dispatch (Phase 3.6.5), collect agent-proposed memory entries written during this session and present them to the operator via `AskUserQuestion` multiSelect. Approved entries flow to `learnings.jsonl` with `_provenance: agent-proposed@<wave-id>`. Rejected entries are archived to `.orchestrator/proposals.rejected.log`.
+After learnings are written (Phase 3.6) and BEFORE the Skill-Applied Judge (Phase 3.6.6 — Phase 3.6.5 is retired), collect agent-proposed memory entries written during this session and present them to the operator via `AskUserQuestion` multiSelect. Approved entries flow to `learnings.jsonl` with `_provenance: agent-proposed@<wave-id>`. Rejected entries are archived to `.orchestrator/proposals.rejected.log`.
 
 The proposals queue is populated mid-session by wave-executor agents calling `node scripts/memory-propose.mjs --type ... --subject ... --insight ... --evidence ... --confidence ...`. The CLI enforces:
 - Quota per wave (default 5, configurable via `memory.proposals.quota-per-wave`)
@@ -138,40 +138,29 @@ The proposals queue is populated mid-session by wave-executor agents calling `no
 
 > Best-effort, non-blocking. Skip silently if the sweep script errors or `.orchestrator/metrics/learnings.jsonl` is absent.
 
-After learnings are written (Phase 3.6), run `node scripts/sweep-expired-learnings.mjs --json` (dry-run) against the learnings store. If the summary reports `archived > 0`, follow with `node scripts/sweep-expired-learnings.mjs --apply --json` to move the stale-past-grace entries into `.orchestrator/metrics/learnings-archive.jsonl` (append-only, never deleted). Note the resulting counts for the Phase 6 Final Report; any error surfaces on stderr with a non-zero exit (`1` usage error, `2` sweep failure) and never blocks close — the CLI does not write to `.orchestrator/metrics/sweep.log` (that path is the session-registry's own sweep log, unrelated to this CLI).
+**MECHANICAL since 2026-09-09.** This phase is no longer a two-command prose recipe ("run `--json`, then `--apply --json` when `archived > 0`") — that recipe was the reason the apply path had ZERO session-end callers: measured across three consumer repos, 0 sweeps had ever been applied and 628 learnings were resident in the active stores. The dry-run decision already lives in `planTailPhases()`; the APPLY half now lives in `scripts/lib/session-end/tail-runner.mjs`.
 
-### 3.6.5 Auto-Dream Dispatch (#502, F2.2)
+After learnings are written (Phase 3.6) and `planTailPhases()` has produced its `plan` (see § "Phase 3.6.x Tail — Mechanical Skip-Plan" in `references/phase-3-documentation-updates.md`), call `runTailPhases` ONCE and read the `3.6.4` slot of its keyed result:
 
-> Skip this phase if `memory-cleanup-threshold: 0` (kill-switch per PRD F2.2). Also skip on non-Claude-Code platforms (memory dir at `~/.claude/projects/` is Claude Code-only, mirrors Phase 3.5 gate).
+```javascript
+import { runTailPhases } from '${PLUGIN_ROOT}/scripts/lib/session-end/tail-runner.mjs';
 
-After learnings are written (Phase 3.6), determine whether to emit a **manual-cadence nudge** to run `/memory-cleanup --dry-run` in the next session. The decision uses MEMORY.md line count and a sessions-since-last-cleanup signal. There is no `memory-cleanup` agent in the registry, so the historical auto-dream subagent dispatch never fired (see #614) — the nudge replaces it. A manually-run `/memory-cleanup --dry-run` writes a complete-replacement MEMORY.md proposal (single fenced ` ```markdown ` block — never git-style diff hunks, see #717) to `.orchestrator/pending-dream.md` for the session after that to apply via `/memory-cleanup --apply-pending`.
+const tail = await runTailPhases({ repoRoot: process.cwd(), plan });
+const sweep = tail['3.6.4'];
+// { ran: true, scanned, archived, archivePath } | { ran: false, reason: 'plan-skip' | 'no-plan' | 'error', error? }
+```
 
-1. Read `memory-cleanup-threshold` (default 5) and `memory-cleanup-soft-limit` (default 180) from `$CONFIG`.
-2. Invoke `shouldDispatchAutoDream` from `scripts/lib/auto-dream.mjs`:
+- `runTailPhases` delegates to `runExpiredSweep({ repoRoot, plan, now })` — the same module's single-phase entry point — and returns a KEYED shape so a caller keeps working when a second phase becomes mechanical. Today exactly one phase is: 3.6.3, 3.6.5–3.6.8 stay coordinator-executed because they are AUQ-gated or need a subagent dispatch a library function cannot make.
+- **Never throws, fails CLOSED.** Any error yields `{ ran: false, reason: 'error' }` and the close proceeds. Stale-past-grace entries move into `.orchestrator/metrics/learnings-archive.jsonl` (append-only, never deleted).
+- **Report** `sweep.ran`, `sweep.scanned` and `sweep.archived` in the Phase 6 Final Report, e.g. `expired-sweep: 12 archived of 640 scanned`. When `ran: false`, report the `reason` instead — a skipped sweep is a stated outcome, never silence.
+- **The proof it ran is the event `orchestrator.learnings.sweep_applied`** in `.orchestrator/metrics/events.jsonl` (payload source `session-end-3.6.4`, which separates it from the standalone CLI). A close claiming a sweep with no such event did not sweep.
 
-   ```javascript
-   import { shouldDispatchAutoDream } from '${PLUGIN_ROOT}/scripts/lib/auto-dream.mjs';
-   import { resolveMemoryDir } from '${PLUGIN_ROOT}/scripts/lib/memory-paths.mjs';
-   const repoRoot = process.cwd();
-   const memoryDir = resolveMemoryDir(repoRoot);
-   const decision = await shouldDispatchAutoDream({
-     repoRoot,
-     memoryDir,
-     threshold: config['memory-cleanup-threshold'] ?? 5,
-     softLimit: config['memory-cleanup-soft-limit'] ?? 180,
-   });
-   ```
-3. If `decision.trigger === false`: log `auto-dream: not triggered (${decision.reason})` and continue. Emit no nudge.
-4. If `decision.trigger === true`: **do not dispatch a subagent** — there is no `memory-cleanup` agent in `agents/`, so the historical `Agent({…})` dispatch pointed at the agent name `memory-cleanup` (a subagent type that was never built) and never fired (see #614). Instead, emit a manual-cadence nudge and continue:
+The standalone `node scripts/sweep-expired-learnings.mjs --apply --json` CLI remains available for manual/out-of-session use; it is no longer the session-end path.
 
-   `auto-dream: cadence reached (${decision.reason}) — run /memory-cleanup --dry-run manually in the next session, then apply the proposal with /memory-cleanup --apply-pending.`
+### 3.6.5 Auto-Dream Dispatch (#502, F2.2) — RETIRED
 
-   The `shouldDispatchAutoDream` decision helper and `scripts/lib/auto-dream.mjs` lib stay in use: they compute the signal that drives this nudge and back the manual `/memory-cleanup` path (`writePendingDream` / `readPendingDream` / `applyPendingDream`).
-5. Record the outcome (skipped / nudge-emitted) so Phase 6 Final Report can surface a line: `auto-dream: manual /memory-cleanup --dry-run recommended (cadence reached) — apply with /memory-cleanup --apply-pending next session`.
-
-The pending-dream sidecar at `.orchestrator/pending-dream.md` is intentionally outside the vault tree — vault-mirror (Phase 3.7) must exclude it from its scope so the proposal survives the session close without being mirrored into 50-sessions/.
-
-Cross-reference: PRD F2.2 acceptance criteria; `scripts/lib/auto-dream.mjs` API (`shouldDispatchAutoDream`, `readDreamSignals`, `writePendingDream`, `readPendingDream`, `applyPendingDream`).
+> **RETIRED 2026-09-09.** The nudge is replaced by the session-start `maintenance-due` probe (`checkMaintenanceDue`, `scripts/lib/maintenance-due-banner.mjs`), whose `memory-cleanup` signal reuses the very same `shouldDispatchAutoDream` decision — a nudge emitted while the operator is closing down was read by nobody. Its decider is also gone from `planTailPhases()` in `scripts/lib/session-end/phase-skip.mjs`; the heading stays because other docs cite it.
+> The housekeeping session runs `/memory-cleanup` itself (see `skills/session-start/SKILL.md` Phase 7 — the maintenance loop). `scripts/lib/auto-dream.mjs` (`shouldDispatchAutoDream`, `readDreamSignals`, `writePendingDream`, `readPendingDream`, `applyPendingDream`) stays in use: the probe reads it, and `/memory-cleanup --dry-run` / `--apply-pending` still write and consume `.orchestrator/pending-dream.md`. <!-- path-check: example -->
 
 ### 3.6.6 Skill-Applied Judge (#645, L3)
 
@@ -181,7 +170,7 @@ Cross-reference: PRD F2.2 acceptance criteria; `scripts/lib/auto-dream.mjs` API
 >
 > When skipped, log `skill-judge: disabled (skill-evolution.judge=false)` (or `persistence=false`) and return. **This is the disabled-path guarantee:** with the judge off, only L1 (`skill-invocations.jsonl`, written by the PreToolUse hook) and L2 (`scripts/lib/skill-health/join.mjs`) records exist — no judgment, no error, zero L3 code executes. Do NOT import `scripts/lib/skill-judge.mjs` on the disabled path.
 
-After learnings are written (Phase 3.6) and the auto-dream decision is made (Phase 3.6.5), and when the judge is enabled, run a **bounded, read-only LLM-judge** over this session's selected skills to emit ADVISORY per-skill applied/completed judgments to `.orchestrator/metrics/skill-judgments.jsonl`.
+After learnings are written (Phase 3.6), and when the judge is enabled, run a **bounded, read-only LLM-judge** over this session's selected skills to emit ADVISORY per-skill applied/completed judgments to `.orchestrator/metrics/skill-judgments.jsonl`.
 
 **The #614 distinction (the whole point of L3's Design A):** unlike the 3.6.5 / 3.6.7 nudge-only paths — which cannot dispatch a live subagent because the target read-only agents (`memory-cleanup`, `dialectic-deriver`) cannot write their own sidecars — L3 performs a **LIVE read-only dispatch**. This is #614-safe because the read-only `skill-applied-judge` agent **RETURNS JSON** and the **COORDINATOR writes the sidecar**, not the agent. A read-only agent that returns judgments is allowed; a read-only agent that must write a file is the #614 trap.
 
@@ -238,41 +227,10 @@ After learnings are written (Phase 3.6) and the auto-dream decision is made (Pha
 
 Cross-reference: PRD §A L3 acceptance criteria (#645, epic #643); `scripts/lib/skill-judge.mjs` API (`runSkillJudge`, `validateModel`, `estimateInputTokens`, `checkBudget`, `buildJudgePrompt`, `parseJudgeResponse`); `scripts/lib/skill-judgments-schema.mjs` (`appendSkillJudgment`, `readSkillJudgments`, `validateSkillJudgment`); agent `agents/skill-applied-judge.md`.
 
-### 3.6.7 Auto-Dialectic Dispatch (#506, F2.5)
-
-> Skip this phase if `dialectic.cadence: 0` (kill-switch per PRD F2.5 AC3). Also skip if `persistence` is `false` in Session Config.
-
-After learnings are written (Phase 3.6) and the auto-dream decision is made (Phase 3.6.5), determine whether to emit a **manual-cadence nudge** to run `/evolve --dialectic` in the next session. The decision uses sessions-since-last-dialectic counted against `.orchestrator/dialectic-last-run`. There is no `evolve` agent in the registry, and the nearest one (`dialectic-deriver`) is `sandbox-tier: read-only` and cannot write the sidecar — so the historical auto-dialectic subagent dispatch never fired (see #614). On trigger, emit the nudge and advance `.orchestrator/dialectic-last-run`; the timestamp is updated only when the nudge is emitted (not on skip), so the reminder surfaces once per cadence window rather than every session. A manually-run `/evolve --dialectic --dry-run` writes the proposed diff to `.orchestrator/dialectic-pending.md`.
-
-1. Read `dialectic.cadence` (default 5), `dialectic.model` (default haiku), `dialectic.budget-tokens` (default 8000) from `$CONFIG`.
-
-2. Invoke `decideAndRecordAutoDialectic` from `scripts/lib/auto-dialectic.mjs`:
-   ```javascript
-   import { decideAndRecordAutoDialectic } from '${PLUGIN_ROOT}/scripts/lib/auto-dialectic.mjs';
-   const decision = await decideAndRecordAutoDialectic({
-     repoRoot: process.cwd(),
-     cadence: config.dialectic?.cadence ?? 5,
-   });
-   ```
-   Same return shape as `shouldDispatchAutoDialectic` (`{trigger, reason, signals}`) — `decideAndRecordAutoDialectic` calls it internally and additionally emits the mechanical `orchestrator.dialectic.nudge_decided` telemetry record on all four return paths (#1200 part c), so the nudge decision is observable without depending on this prose actually reaching step 5/7.
-
-3. If `decision.trigger === false`: log `auto-dialectic: not triggered (${decision.reason})` and continue. Emit no nudge. Do NOT update `.orchestrator/dialectic-last-run`.
-
-4. **AC4 precondition guard:** Even if cadence met, if `signals.sessionsSinceLast === 0 && signals.learningsSinceLast === 0`, skip with reason `no-new-input-since-last-run`. The Final Report (Phase 6) MUST include the literal string `dialectic: skipped (no new input since last run)`.
-
-5. If `decision.trigger === true`: **do not dispatch a subagent** (see #614 — no `evolve` agent exists; `dialectic-deriver` is read-only and cannot write the sidecar). Instead, emit a manual-cadence nudge and continue:
-
-   `auto-dialectic: cadence reached (${decision.reason}) — run /evolve --dialectic --dry-run manually in the next session, review .orchestrator/dialectic-pending.md, then apply with /evolve --dialectic --apply.`
-
-   The `shouldDispatchAutoDialectic` decision helper and `scripts/lib/auto-dialectic.mjs` lib stay in use: they compute the cadence signal that drives this nudge.
-
-6. When the nudge is emitted (cadence reached), update `.orchestrator/dialectic-last-run` via `writeDialecticLastRun({ repoRoot, isoTimestamp: new Date().toISOString() })` so the cadence counter advances and the nudge does not repeat every session. Atomic; failures non-fatal.
-
-7. Record outcome (skipped / nudge-emitted) for Phase 6 Final Report: `auto-dialectic: manual /evolve --dialectic --dry-run recommended (cadence reached) — apply with /evolve --dialectic --apply next session`.
-
-The `.orchestrator/dialectic-pending.md` sidecar is intentionally outside the vault tree — vault-mirror (Phase 3.7) MUST exclude it from its scope.
+### 3.6.7 Auto-Dialectic Dispatch (#506, F2.5) — RETIRED
 
-Cross-reference: PRD F2.5 acceptance criteria (#506); `scripts/lib/auto-dialectic.mjs` API.
+> **RETIRED 2026-09-09.** The nudge is replaced by the session-start `maintenance-due` probe (`checkMaintenanceDue`, `scripts/lib/maintenance-due-banner.mjs`), whose `dialectic` signal reads the side-effect-free `shouldDispatchAutoDialectic` — never a variant that advances the last-run stamp, which would consume the very signal it reports. Its decider is also gone from `planTailPhases()` in `scripts/lib/session-end/phase-skip.mjs`; the heading stays because other docs cite it.
+> The housekeeping session runs `/evolve dialectic` itself (see `skills/session-start/SKILL.md` Phase 7 — the maintenance loop): dry-run first, review `.orchestrator/dialectic-pending.md`, then apply. `scripts/lib/auto-dialectic.mjs` (`shouldDispatchAutoDialectic`, `writeDialecticLastRun`) and the read-only `dialectic-deriver` agent stay in use on that manual path. The recording wrapper around that signal, and its `orchestrator.dialectic.nudge_decided` event, were removed in #1288 — nothing emits that event any more. <!-- path-check: example -->
 
 > **Dialectic chain rationale** — design choices in the manual `/evolve --dialectic` chain (`/evolve → runDialecticDeriver → dispatchAgent → Agent`). Session-end no longer auto-dispatches this chain (see #614 — the `evolve` agent never existed); the rationale below applies when you run `/evolve --dialectic` manually:
 > - **/evolve → subagent (not direct invoke):** the manual `/evolve --dialectic` skill spawns a subagent so the dialectic pass runs in a fresh context window — keeping the deriver's input-heavy payload (top-50 learnings + last-10 sessions + 2 peer cards + steering) out of the invoking coordinator's context, and letting the deriver run as Haiku while the coordinator stays Opus.
@@ -286,7 +244,7 @@ Cross-reference: PRD F2.5 acceptance criteria (#506); `scripts/lib/auto-dialecti
 > - `reconcile.enabled` is `false` (default: `false` — opt-in; this is the silent no-op path for all repos that have not opted in)
 > - `.orchestrator/metrics/learnings.jsonl` does not exist OR contains zero entries
 
-After the auto-dialectic nudge decision is made (Phase 3.6.7), and when the reconcile engine is enabled, run the **reconciliation engine** to turn high-confidence learnings into conditional-rule proposals and present them to the operator via `AskUserQuestion` multiSelect. Approved proposals flow to `.claude/rules/` via `writeApprovedRules`. Rejected proposals are archived to `.orchestrator/reconcile.rejected.log`. The engine NEVER writes `.claude/rules/` itself — every write is operator-AUQ-gated (#693 FA2/FA3 brandmauer).
+After the Skill-Applied Judge (Phase 3.6.6 — Phase 3.6.7 is retired), and when the reconcile engine is enabled, run the **reconciliation engine** to turn high-confidence learnings into conditional-rule proposals and present them to the operator via `AskUserQuestion` multiSelect. Approved proposals flow to `.claude/rules/` via `writeApprovedRules`. Rejected proposals are archived to `.orchestrator/reconcile.rejected.log`. The engine NEVER writes `.claude/rules/` itself — every write is operator-AUQ-gated (#693 FA2/FA3 brandmauer).
 
 #### Coordinator-direct procedure
 
@@ -323,7 +281,7 @@ After the auto-dialectic nudge decision is made (Phase 3.6.7), and when the reco
 
 3. If `surfaced.length === 0`: log `reconcile: 0 proposals above confidence floor (eligible=${summary.eligible}, rejected=${summary.rejected}, floor=${floor})` and continue. No AUQ, no sidecar write.
 
-4. **Write the human-readable proposal sidecar** `.orchestrator/metrics/reconcile-pending.md` so the operator can review raw content outside the AUQ:
+4. **Write the human-readable proposal sidecar** `.orchestrator/metrics/reconcile-pending.md` so the operator can review raw content outside the AUQ: <!-- path-check: example -->
 
    ```
    # Reconciliation Rule Proposals — <ISO timestamp>

package/skills/session-end/phase-3-7a-recommendations.md

@@ -76,7 +76,7 @@ try {
 
 ## Phase 3.7b: Durable-Commit Session Telemetry (#490 AC2)
 
-> **Ordering:** Runs AFTER Phase 3.7a (Recommendation fields just-written to STATE.md) and BEFORE Phase 3.4 (`status: completed`). The canonical runtime order is `… → 3.6.7 → 3.6.8 → 3.7 → 3.7a → 3.7b → 3.7c → 3.7d → 3.4`. Both session-end-owned files (`sessions.jsonl` from Phase 3.7, `STATE.md` from Phase 3.7a) have already been written to disk; this step only declares them as the durable-commit set.
+> **Ordering:** Runs AFTER Phase 3.7a (Recommendation fields just-written to STATE.md) and BEFORE Phase 3.4 (`status: completed`). The canonical runtime order is `… → 3.6.6 → 3.6.8 → 3.7 → 3.7a → 3.7b → 3.7c → 3.7d → 3.4` (3.6.5 Auto-Dream and 3.6.7 Auto-Dialectic were RETIRED 2026-09-09 — see `phase-3-6-tail.md`). Both session-end-owned files (`sessions.jsonl` from Phase 3.7, `STATE.md` from Phase 3.7a) have already been written to disk; this step only declares them as the durable-commit set.
 
 > **Ownership:** session-end commits ONLY the two files it owns — `.orchestrator/metrics/sessions.jsonl` and `<state-dir>/STATE.md`. `.orchestrator/metrics/autopilot.jsonl` is NOT session-end's responsibility: `scripts/lib/autopilot/loop.mjs` commits that file in the autopilot loop (the core `loop.mjs` wiring shipped in #490 Wave-2). Do not add autopilot.jsonl to the files array here.
 
@@ -95,6 +95,6 @@ await withDurableCommit(
 );
 ```
 
-- Use the platform-resolved `<state-dir>/STATE.md` path (e.g. `~/.claude/STATE.md` on Claude Code) — NOT a hardcoded `.claude/STATE.md`.
+- Use the platform-resolved `<state-dir>/STATE.md` path (e.g. `~/.claude/STATE.md` on Claude Code) — NOT a hardcoded `.claude/STATE.md`. <!-- path-check: example -->
 - The `files` array is staged individually by `durableCommit` (PSA-004: never `git add .`/`-A`); the existing `SAFE_BRANCH_RE` branch-name allowlist + cwd-confinement guards in `durable-telemetry.mjs` apply unchanged.
 - `enabled: false` short-circuits before any git command runs, so the local-execution path performs zero VCS mutation — Phase 4 (`git add` + commit) remains the single staging point for local closes.