@gobing-ai/spur 0.3.78 → 0.3.80

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@gobing-ai/spur",
-    "version": "0.3.78",
+    "version": "0.3.80",
     "description": "Spur CLI — local-first harness for mainstream coding agents: constraint checking, workflow orchestration, agent health, and history analytics. Bun-native; exposes the `spur` command.",
     "keywords": [
         "spur",
@@ -53,14 +53,14 @@
     },
     "devDependencies": {
         "@commander-js/extra-typings": "^14.0.0",
-        "@gobing-ai/ts-db": "^0.4.60",
-        "@gobing-ai/ts-ai-runner": "^0.4.60",
-        "@gobing-ai/ts-dual-workflow-engine": "^0.4.60",
-        "@gobing-ai/ts-infra": "^0.4.60",
-        "@gobing-ai/ts-llm-jsonl-importer": "^0.4.60",
-        "@gobing-ai/ts-rule-engine": "^0.4.60",
-        "@gobing-ai/ts-runtime": "^0.4.60",
-        "@gobing-ai/ts-utils": "^0.4.60",
+        "@gobing-ai/ts-db": "^0.4.62",
+        "@gobing-ai/ts-ai-runner": "^0.4.62",
+        "@gobing-ai/ts-dual-workflow-engine": "^0.4.62",
+        "@gobing-ai/ts-infra": "^0.4.62",
+        "@gobing-ai/ts-llm-jsonl-importer": "^0.4.62",
+        "@gobing-ai/ts-rule-engine": "^0.4.62",
+        "@gobing-ai/ts-runtime": "^0.4.62",
+        "@gobing-ai/ts-utils": "^0.4.62",
         "@types/bun": "1.3.14",
         "@types/figlet": "^1.7.0",
         "@types/node-notifier": "8.0.5",

package/plugins/sp/README.md

@@ -171,10 +171,12 @@ Commands above are thin wrappers; the actual logic lives in `skills/`. The spine
 dispatches five competency skills by function — design (`sp:sys-architecture`), decomposition
 (`sp:spec-decomposition`), implementation (`sp:code-implementation`), testing (`sp:code-testing`),
 and verification (`sp:code-verification`) — plus a CLI facade (`sp:spur-cli`, one reference per
-`spur` noun) and standalone technique skills (`sp:next-router`, `sp:test-driven-development`, `sp:brainstorm`,
-`sp:wayfinder`, `sp:sys-debugging`, `sp:code-review`, `sp:code-simplification`, `sp:code-improvement`,
-`sp:parallel-execution`, `sp:branch-workflow`, `sp:doc-evolve`, `sp:dogfood-testing`,
-`sp:daily-summary`, `sp:reverse-engineering`, `sp:issue-finding`, `sp:conflict-finding`,
+`spur` noun) and standalone technique skills (`sp:next-router`, `sp:next-feature`,
+`sp:test-driven-development`, `sp:source-driven-development`, `sp:doubt-driven-development`,
+`sp:brainstorm`, `sp:wayfinder`, `sp:sys-debugging`, `sp:code-review`, `sp:pr-reviewing`,
+`sp:functional-review`, `sp:code-simplification`, `sp:code-improvement`, `sp:parallel-execution`,
+`sp:branch-workflow`, `sp:doc-evolve`, `sp:dogfood-testing`, `sp:daily-summary`,
+`sp:reverse-engineering`, `sp:history-anatomy`, `sp:issue-finding`, `sp:conflict-finding`,
 `sp:indexed-context`, `sp:session-review`, `sp:redesign-web-ui`). See
 [skills/spur-dev/SKILL.md](skills/spur-dev/SKILL.md)'s Step routing table for which skill owns which
 pipeline step.
@@ -215,6 +217,7 @@ plugins/sp/
 │   │   └── references/routing-table.md
 │   ├── parallel-execution/          # Fan-out decision framework + patterns
 │   │   └── references/{fan-out-patterns, result-synthesis}.md
+│   ├── pr-reviewing/                # GitHub PR review loop backing /sp:dev-pr-review
 │   ├── source-driven-development/   # Source-first API/contract verification (SKILL.md only)
 │   ├── spec-decomposition/          # Feature/spec → task-batch competency
 │   │   └── references/decomposition.md
@@ -255,6 +258,8 @@ plugins/sp/
 ├── agents/                          # 4 specialist subagents (expert-spur, super-coder, super-planner, super-reviewer)
 ├── hooks/                           # hooks.json + task-write-guard.{ts,test.ts} + context-{session-start,post-tool,session-stop}.ts
 │                                    # + careful-guard.{ts,test.ts} + context-hooks.test.ts + token-estimate.test.ts
+│                                    # + shared policy modules: agent-hint.ts, destructive-policy.{ts,test.ts}, task-file-policy.{ts,test.ts}
+│                                    # + pi/guard-extension.{ts,test.ts} (plugin.json `extensions.pi` entry point)
 ├── scripts/                         # Executable helpers, split from prompts (ADR-031) — validate-commands.ts (thin-wrapper validator), batch-preflight.ts + scripts/<skill>/
 │                                    # (daily-summary: {daily-summary, logger}.ts; dogfood-testing: {detect-pipeline-driving, validate-report}.ts)
 ├── tests/                           # Plugin tests — command-contract.test.ts + skill-structure.test.ts + batch-preflight.test.ts + per-skill suites
@@ -318,13 +323,13 @@ surface or run one workflow. All skills target the same five core platforms: `cl
 | `daily-summary`             | 1.0.0 | Daily summary report generator — orchestrates ccusage CLI + git history into structured markdown summaries                                                                                                                                 |
 | `doc-evolve`                | 1.0   | Key-document evolution per `docs/99_PROJECT_CONSTITUTION.md` — drift audits, same-commit sync checks, frontmatter-contract verification, machine-appended lessons                                                                          |
 | `reverse-engineering`       | 1.1   | Codebase analysis / HLD generation / audit — depth-driven reverse engineering with orthogonal mode, focus, and format controls; backs `/sp:dev-reverse`                                                                                    |
-| `issue-finding`             | 1.1   | Session-log forensics — multi-source discovery, bottleneck ranking, optional topic focus, CLI-gated fix task generation; **legacy path** — superseded by `history-anatomy` for indexed reporting; backs no current command; directly invocable as sp:issue-finding |
+| `issue-finding`             | 2.0   | Session-log forensics — multi-source discovery, bottleneck ranking, optional topic focus, CLI-gated fix task generation; **legacy path** — superseded by `history-anatomy` for indexed reporting; backs no current command; directly invocable as sp:issue-finding |
 | `conflict-finding`          | 1.0   | Authority-aware semantic audit — four-pillar (source/task/feature/authority) conflict discovery, claim-specific authority resolution, reproducible evidence, confirmed owner-routed remediation; backs `/sp:dev-find-conflict`             |
 | `next-feature`              | 1.0   | Prompt-first feature frontier prioritizer — sync-first precondition, B3 actionability gate (cited, never restated), tiered rubric over measured signals, D1–D4 defect proposals conforming to the restructure map schema; backs `/sp:dev-find-next` |
 | `pr-reviewing`              | 1.0   | GitHub Codex PR review — PR prepare/reuse, `@codex review` request with per-HEAD dedupe, bounded polling, findings normalization, validated fix + re-review; spine SSOT `pr-review.yaml` + `scripts/pr-reviewing.ts`; backs `/sp:dev-pr-review`     |
 | `indexed-context`           | 1.0   | Cross-agent project context — anatomy/learnings/pitfalls/buglog/memory in `.spur/context/`; hook-tracked token-ledger; graceful degradation on agents without hooks                                                                        |
 | `history-anatomy`           | 1.0   | Diagnostic interpretation owner over already-imported history — daily/ad-hoc mode contract, closed finding taxonomy, twelve-section report contract, `enrich`/`validate` rubrics; no workflow launch, no JSONL fallback, no corpus mutation                                                                   |
-| `session-review`            | 1.0   | Inline review of the active coding-agent session — compact outcomes, evidence-backed resolved/open issue classification, proposal-only improvements, and next actions; no workflow, import, delegation, or mutation                                                                                           |
+| `session-review`            | 1.1   | Inline review of the active coding-agent session — compact outcomes, evidence-backed resolved/open issue classification, proposal-only improvements, and next actions; no workflow, import, delegation, or mutation                                                                                           |
 | `redesign-web-ui`           | 1.0   | Existing-UI visual upgrade — audit generic AI fingerprints, apply in-stack polish against `DESIGN.md` / live tokens, verify behavior and viewports; does not migrate frameworks                                                                                                                            |
 
 #### Bounded coexistence and retirement gate — `sp:issue-finding` (HA-S1 0661)
@@ -418,7 +423,7 @@ the pipeline's Phase 7 review step.
 | ---------------- | ------------ | ----------------------------------------------------------------------- | ------- | ------------------------------------------------------------------------------- |
 | `expert-spur`    | expert       | `sp:spur-cli`                                                           | green   | "create tasks", "feature lifecycle", "add a rule", "author a workflow"          |
 | `super-coder`    | builder      | `sp:sys-architecture` + `sp:code-implementation` + `sp:code-testing` + `sp:sys-debugging` | blue    | "implement this", "write the code", "fix this bug", "design the architecture"   |
-| `super-planner`  | orchestrator | `sp:spur-dev` + `sp:dogfood-testing`                                    | green   | "run this task end to end", "run all tasks", "run the batch", "runall"          |
+| `super-planner`  | orchestrator | `sp:spur-dev` + `sp:parallel-execution` + `sp:dogfood-testing` + `sp:next-router` | green   | "run this task end to end", "run all tasks", "run the batch", "runall"          |
 | `super-reviewer` | reviewer     | `sp:code-verification` + `sp:functional-review` + `sp:code-improvement` | crimson | "review this", "check the code", "SECUA review", "run task 0042 through review" |
 
 Each agent has:

package/plugins/sp/agents/super-reviewer.md

@@ -97,7 +97,8 @@ HITL gate unless `--auto` was passed.
 - [ ] Establish scope first: WBS mode (task diff) or path mode (source glob). Derive the diff
       scope the same way `sp:code-verification` Step 3 does.
 - [ ] Dispatch each requested dimension to its owning skill — do not inline the review logic.
-- [ ] Merge findings into a single ranked report (severity: blocker > major > minor > advisory).
+- [ ] Merge findings into a single ranked report, emitting native priority cells
+      (`P1 (blocker)` > `P2 (major)` > `P3 (minor)` > `P4 (advisory)` — see Output Format).
 - [ ] In pipeline mode, write the merged report to the task's `## Review` section via
       `spur task update <wbs> --section Review --from-file`; in standalone mode, emit as output.
 - [ ] Cite `file:line` evidence for every finding — no vague "implemented correctly."
@@ -109,6 +110,8 @@ HITL gate unless `--auto` was passed.
 - [ ] Never edit `task-pipeline.yaml` or reach into a pipeline step.
 - [ ] Never auto-approve a HITL gate unless `--auto` was passed.
 - [ ] Never soften a FAIL to PARTIAL, or PARTIAL to PASS, to avoid surfacing.
+- [ ] Never emit a word-only Severity cell, an empty priority scaffold, or a `##`/`###` heading
+      inside a `### Review` body — all three fail the existing checkers.
 - [ ] Never skip a dimension the operator requested with `--focus`.
 
 ## Definition of Done Housekeeping
@@ -120,22 +123,44 @@ enforcement checklist. Reference:
 
 ## Output Format
 
+### Priority vocabulary (task 0818 R3)
+
+Emit priorities **natively** — the consumer (`hasPopulatedPriorityTable`,
+`packages/app/src/services/task-check.ts`) requires a `P1`–`P4` cell, and a word-only severity cell
+fails it. One explicit mapping, no transcription step anywhere downstream:
+
+| Priority cell | Severity | Meaning |
+| --- | --- | --- |
+| `P1 (blocker)` | blocker | Ships broken or unsafe; blocks the verdict |
+| `P2 (major)` | major | Real defect or structural problem; must be dispositioned |
+| `P3 (minor)` | minor | Localized issue; fix or accept explicitly |
+| `P4 (advisory)` | advisory | Observation, non-blocking |
+
+Severity words stay visible in the same cell — the mapping adds the machine-readable label, it does
+not replace the semantics.
+
+**Section-relative headings.** In pipeline mode the report body is written *into* the task's
+`### Review` section, so every heading inside it MUST be `####` or deeper. A `##`/`###` heading in
+the body becomes a new top-level task section and corrupts the document. In standalone mode
+(emitted as output, not written to a task) the same body may be rendered one level shallower.
+
 ```markdown
-## Review Report — <wbs|path>
+#### Review Report — <wbs|path>
 
 **Scope:** <wbs diff | path glob>
 **Dimensions:** functional, security, efficiency, correctness, usability, architecture
 **Verdict:** PASS | PARTIAL | FAIL
 
-### Findings (ranked)
+##### Findings (ranked)
 
-| # | Severity | Dimension | Finding | Location |
+| # | Priority | Dimension | Finding | Location |
 |---|----------|-----------|---------|----------|
-| 1 | blocker | security | SQL injection in query builder | `src/api/users.ts:42` |
-| 2 | major | architecture | Shallow pass-through UserService | `src/services/users.ts:15` |
-| 3 | minor | correctness | Missing error branch in createUser | `src/api/users.ts:48` |
+| 1 | P1 (blocker) | security | SQL injection in query builder | `src/api/users.ts:42` |
+| 2 | P2 (major) | architecture | Shallow pass-through UserService | `src/services/users.ts:15` |
+| 3 | P3 (minor) | correctness | Missing error branch in createUser | `src/api/users.ts:48` |
+| 4 | P4 (advisory) | usability | `createUser` error text omits the field name | `src/api/users.ts:51` |
 
-### Functional Traceability
+##### Functional Traceability
 
 | Req | Status | Evidence |
 |-----|--------|----------|
@@ -145,6 +170,16 @@ enforcement checklist. Reference:
 **Next:** <one-line action>
 ```
 
+**No findings.** Never invent a defect to populate the table. Emit one substantive `P4 (advisory)`
+row that states what was reviewed and what was found — placeholder cells (empty, `—`, `n/a`) are
+rejected by the checker, and so they should be:
+
+```markdown
+| # | Priority | Dimension | Finding | Location |
+|---|----------|-----------|---------|----------|
+| 1 | P4 (advisory) | — | No P1–P3 findings: 6 changed files reviewed across all six dimensions; R1–R3 traceable to tests | `packages/app/src/workflow/proof-input-fingerprint.ts:102-160` |
+```
+
 With `--json`, emit the same shape as a JSON object for machine consumption.
 
 ## Out of scope

package/plugins/sp/plugin.json

@@ -1,6 +1,6 @@
 {
     "name": "sp",
-    "version": "0.3.78",
+    "version": "0.3.80",
     "description": "Spur — a local-first harness engineering toolkit that wraps mainstream coding agents with constraint checking, workflow orchestration, and history analytics.",
     "extensions": {
         "pi": ["./hooks/pi/guard-extension.ts"]

package/plugins/sp/scripts/verify-answer-lint.ts

@@ -282,7 +282,8 @@ function stripAcWrappers(title: string): string {
  * Normalize an AC identity to its canonical key, mirroring the documented
  * matching behavior of feature-check `rowMatchesScenario` + ac-style-guide
  * "Four accepted id forms" (exact/bare title, `Scenario:` prefix, bracket
- * tags, `AC-N` ordinal) without importing that private matcher or adopting
+ * tags, `AC-N` ordinal) plus the task-side bold-trajectory paragraph
+ * (0817 R3), without importing that private matcher or adopting
  * its permissive trailing-Gherkin fallback (0804 R4). Comparison is
  * case/quote/whitespace-insensitive. A paraphrase normalizes differently
  * and still fails.
@@ -307,7 +308,7 @@ function normalizeAcTitle(title: string): string {
  * A checklist-declared spelling always wins over the positional alias.
  */
 interface AcIdentityIndex {
-    /** normalized canonical title → a declared spelling (label, token, or title). */
+    /** normalized canonical title → a declared spelling (label, token, title, or bold trajectory). */
     readonly byTitle: Map<string, string>;
     /** AC-N → task scenario title at that 1-based ordinal. */
     readonly taskScenarios: string[];
@@ -331,6 +332,19 @@ function buildAcIdentityIndex(taskContent: string, featureContent: string | null
         const leading = label.split(/\s+/)[0] ?? '';
         if (leading && leading !== label) declareIdentity(leading);
     }
+    // Bold-trajectory form (task 0817 R3): answers may cite an AC by a bare
+    // `**AC id**` paragraph (house style for long/complex ids). Only whole-line
+    // bold spans count — the line-anchored lazy regex rejects lines with two
+    // spans, keeping interpolated bold text out of the index. The head (text
+    // before the first colon) is declared like a checklist label, mirroring
+    // the `(?::|$)` label extraction above.
+    for (const m of section.matchAll(/^\*\*(.+?)\*\*\s*$/gm)) {
+        const inner = (m[1] ?? '').trim();
+        if (!inner) continue;
+        declareIdentity(inner);
+        const head = inner.split(':')[0]?.trim() ?? '';
+        if (head && head !== inner) declareIdentity(head);
+    }
     const scenarioTitles = (content: string): string[] =>
         [...content.matchAll(/^[ \t]*Scenario:\s*(.+)\s*$/gm)].map((m) => (m[1] ?? '').trim()).filter((t) => t !== '');
     const taskScenarios = scenarioTitles(sectionBetween(taskContent, 'Acceptance Criteria'));
@@ -348,6 +362,10 @@ type AcIdentityResolution = { ok: true; canonical: string } | { ok: false; error
  * alias — accepted only against a real scenario ordinal, and refused with an
  * actionable diagnostic when task and feature ordinals disagree. Undeclared
  * `ACn` tokens, paraphrases and invented ordinals never resolve.
+ * `ACn` tokens, paraphrases and invented ordinals never resolve.
+ *
+ * Declared forms recognized in the index include the bold-trajectory
+ * `**AC id**` paragraph (task 0817 R3); the AC-N failure hint names it.
  */
 function resolveAcIdentity(rowId: string, index: AcIdentityIndex): AcIdentityResolution {
     const canonical = index.byTitle.get(normalizeAcTitle(rowId));
@@ -365,7 +383,7 @@ function resolveAcIdentity(rowId: string, index: AcIdentityIndex): AcIdentityRes
                 ok: false,
                 error:
                     `AC id "${rowId}" uses the AC-${n} positional alias but no scenario exists at that ordinal ` +
-                    '(task scenario list and linked-feature scenario list) — cite the exact scenario title or checklist label',
+                    '(task scenario list and linked-feature scenario list) — cite the exact scenario title, checklist label, or a bare `**AC id**` paragraph',
             };
         }
         if (candidates.length > 1) {

package/plugins/sp/skills/conflict-finding/SKILL.md

@@ -94,6 +94,12 @@ Resolve `<scope>` and `--pillar`; confirm the repository root; establish **audit
 numbered-document mutation of any kind. With `--resolve`, no write happens until a repair set is
 presented, explicitly confirmed, and freshness-revalidated.
 
+Validate every enum flag against the domain declared by the command surface
+(`plugins/sp/commands/dev-find-conflict.md`): `--pillar` ∈ `source|tasks|features|authority|all`,
+`--mode` ∈ `adaptive|full`, `--agent` ∈ `inline|auto|name`. An out-of-domain value **refuses** the
+audit before any discovery work — report the received value, the flag's valid domain, and stop;
+never silently coerce or ignore it. Only `<scope>` is free-form and exempt from this check.
+
 ### Step 2 — Discover local authority
 
 Read entry/process rules (`AGENTS.md`, `docs/99_PROJECT_CONSTITUTION.md`) before interpreting any

package/plugins/sp/skills/daily-summary/SKILL.md

@@ -166,6 +166,6 @@ Read the skill file and follow the workflow manually.
 ## Additional Resources
 
 - **Script source:** [scripts/daily-summary/daily-summary.ts](../../scripts/daily-summary/daily-summary.ts) — CLI implementation
-- **Tests:** [tests/daily-summary.test.ts](tests/daily-summary.test.ts) — unit coverage for parsing, date ranges, markdown output
+- **Tests:** [tests/daily-summary/daily-summary.test.ts](../../tests/daily-summary/daily-summary.test.ts) — unit coverage for parsing, date ranges, markdown output
 - **Related skills:** `sp:dev-handover` (blocker handoff), `sp:dev-changelog` (commit-based changelog), `sp:spur-cli` (task management)
 - **Upstream CLI:** [ccusage](https://github.com/ryoppippi/ccusage) — AI agent token usage reporter

package/plugins/sp/skills/doc-evolve/SKILL.md

@@ -4,7 +4,7 @@ description: "Evolve docs/00-05 + AGENTS.md per docs/99_PROJECT_CONSTITUTION.md:
 license: Apache-2.0
 metadata:
   author: spur
-  version: "1.0"
+  version: "1.1"
   platforms: "claude-code,codex,openclaw,opencode,antigravity"
   interactions:
     - reviewer
@@ -30,17 +30,17 @@ this skill applies it.
 
 **Read `docs/99_PROJECT_CONSTITUTION.md` first.** It is the single source of truth for *how* these
 files are maintained (authority §2, doc map §4.1, frontmatter contracts §4.3, sync triggers §5,
-per-file edit rules §6, the audit §7, lessons §8). This skill is a runbook for executing §5/§7/§8;
+per-file edit rules §6, the audit §7, lesson routing §8). This skill is a runbook for executing §5/§7/§8;
 when the two disagree, the constitution wins and this skill is the bug.
 
 ## Operations
 
 | Operation | What it does | Constitution authority | Deterministic helper |
 | --------- | ------------ | ---------------------- | -------------------- |
-| **drift-audit** | Reality (code/shipped) vs. what a key file says, and cross-doc contradictions | §7 (the 8-item checklist) | `rg` the real CLI/config surface; diff vs `04`/`AGENTS.md`/`00` |
-| **sync-check** | Did a change touch the docs its trigger obligates in the same commit? | §5 (triggers T1–T8) | git diff of code/config vs. the matching doc edit |
+| **drift-audit** | Reality (code/shipped) vs. what a key file says, and cross-doc contradictions | §7 | `rg` the real CLI/config surface; diff vs `04`/`AGENTS.md`/`00` |
+| **sync-check** | Did a change touch the docs its trigger obligates in the same commit? | §5 (applicable triggers) | git diff of code/config vs. the matching doc edit |
 | **contract-verify** | Each doc's frontmatter matches its §4.1 row; `updated_at` is plausible | §4.3 | parse frontmatter; compare `owns`/`authority` vs §4.1; `git log` recency |
-| **lesson-append** | Append a dated lesson; dedup; promote recurring ones to a rule | §8 | format-check the line; `rg` for an equivalent before adding |
+| **lesson-append** | Record a useful lesson in existing project context; deduplicate; propose governance changes separately | §8 | format-check the line; `rg` for an equivalent before adding |
 
 No thin `dev-docs` command wrapper exists (`dev-operations.md §7`). Invoke this skill directly for
 an audit or a lesson, or reach it via `/sp:dev-plan`'s docs step and `/sp:spur-init`'s `customize`.
@@ -84,48 +84,40 @@ stubs filled or deliberately documented; `bun run lint` passes where applicable.
 Walk the §7 checklist. Each item pairs a detection command with the doc it validates:
 
 ```bash
-# Real CLI surface vs. what 04 / AGENTS.md / 00 claim
+# Real CLI surface vs. owning non-UI contracts
 rg -n "\.command\('" apps/cli/src/commands/        # the true verb list
-rg -n '^#### `spur ' docs/04_DESIGN.md             # documented commands
+rg -n '^#### `spur ' docs/design/             # documented commands
 # → diff the two sets; a verb in code but not in 04 is T3 drift.
 
 # 05 status rows vs. reality
-rg -n '✅|🔶|⏳|💤' docs/05_FEATURES.md             # claimed states
+cat docs/features/INDEX.md                         # generated feature states
 # → spot-check each ✅/🔶 against code; confirm no ⏳ quietly shipped.
 
 # 02 phase bullets name real things (no dead names)
 # 03 module descriptions vs. the real tree
-fd -t d -d 2 . apps packages                       # real modules
+rg --files apps packages                       # real modules
 # Frontmatter contracts (see contract-verify) + updated_at recency
 git log -1 --format='%ci' -- docs/04_DESIGN.md     # last touch vs. recent surface changes
 ```
 
-**Repair protocol (§7, always this order):** fix the **authoritative** doc first (append-only files
-by dated amendment, never rewrite), then the derived docs that restate/sequence it, then
-`AGENTS.md`, then **flag what drifted and why** in the commit/task (a silent fix hides the systemic
-cause). Anything systemic becomes a §8 lesson — or, if it recurs, a new §6 rule.
+**Repair protocol (§7):** fix the authoritative statement first, then affected detail/index/entry
+files. Preserve ADR numbers, original titles/dates and decision history; editorial condensation
+follows §6.1, while actual reversals need a superseding decision. Record findings in a task/report.
+Routine lessons go to existing learning/context storage (§8); no automatic constitution edits.
 
 Output a **drift report**: per finding, `{ doc, what code says, what the doc says, authority, repair
 }`. A clean report lists the checks run and that each returned no delta.
 
 ## sync-check (§5)
 
-Given a change (a diff, or a just-finished task), check the same-commit obligations:
+Read the live constitution §5; it owns the trigger table. Classify each changed fact, identify
+its owner, and inspect the diff to confirm required synchronization. Update an index or AGENTS.md
+only when its own facts changed. A satellite edit with an unchanged index pointer is synchronized.
 
-| If the change… | Trigger | …the same commit must touch |
-| -------------- | ------- | --------------------------- |
-| adds/changes a command, flag, config key, env var, schema, DTO | **T3** | `04_DESIGN` + the `AGENTS.md` surface block |
-| ships a feature or changes its state | **T4** | its `05` row (+ a `01` scope row if new surface) |
-| makes a new cross-cutting decision (or reverses one) | **T1** | `00` first (dated), then `03`, `01` if scope shifts |
-| would contradict an existing ADR | **T2** | **stop** — add the superseding ADR entry first |
-| completes/reorders a phase | **T5** | `02` (the real shipped name) |
-| adds/cuts/defers scope | **T6** | `01` + placement in `02` |
-| changes the doc map or process | **T7** | this file → re-sync `AGENTS.md` (§4.4) → siblings |
-| plans a multi-wave batch | **T8** | schedule "doc sync" as an explicit work item |
-
-Detection is a diff read: list the changed code/config paths, map each to its trigger, then confirm
-the obligated doc was edited in the same change. A surface change with no `04` edit is the canonical
-miss (the one this whole §5 table exists to prevent).
+T1 applies only to real architectural choices passing §6.1. Feature approvals, task completion,
+bugfixes restoring an existing contract and verification receipts do not justify ADR entries.
+T7 applies only to operator-authorized governance corrections under §6.8; a routine doc edit or
+lesson does not justify touching the constitution. Portable changes include in-scope init templates.
 
 ## contract-verify (§4.3)
 
@@ -140,19 +132,13 @@ stale given recent commits?"
 
 ## lesson-append (§8)
 
-Append a lesson to the right per-file section of §8:
-
-```
-- [YYYY-MM-DD] <project>: <lesson — what went wrong / what to do instead>
-```
+Read constitution §8 for the existing project's destination. Record a useful, deduplicated
+lesson in existing learning/context storage or a dated report, with evidence. Do not append
+lessons to the constitution. Do not create a second learning ledger when one already exists.
 
-- **Low threshold** — when in doubt, append. **Check for an equivalent first** (`rg` the section);
-  bump its date instead of duplicating.
-- **Promotion is the only sanctioned deletion:** a lesson that recurs or hardens into practice is
-  promoted into a §6 rule (or §5 trigger) and removed from §8. Lessons are the inbox; §5/§6 are the
-  law.
-- Lessons carry project provenance (this file is byte-identical across projects except §8 + the §3
-  tool column) — a lesson from one project is a warning, not yet a law, for the others.
+A recurring lesson may justify proposing a document-governance correction; apply it only within
+operator-authorized §6.8 scope. Task receipts remain in task records. Fresh project templates
+contain neither inherited lessons nor fabricated decisions/status claims.
 
 ## What this skill is NOT
 

package/plugins/sp/skills/doc-evolve/references/operations.md

@@ -15,41 +15,33 @@ it enforces; the skill never invents process.
 
 | Operation | Authority § | What "done" means |
 | --------- | ----------- | ----------------- |
-| drift-audit | §7 | the 8-item §7 checklist run, each backed by a command; report lists deltas (or the zero-delta commands) |
-| sync-check | §5 (T1–T8) | every changed surface mapped to its trigger; the obligated doc confirmed edited in the same change |
+| drift-audit | §7 | the affected §7 checks run, each backed by a command; report lists deltas (or the zero-delta commands) |
+| sync-check | §5 (applicable §5 triggers) | every changed surface mapped to its trigger; the obligated doc confirmed edited in the same change |
 | contract-verify | §4.3 (+ §4.1) | each doc's frontmatter `owns`/`authority` matches its §4.1 row; `updated_at` plausible |
-| lesson-append | §8 | a dedup'd, correctly-formatted dated line in the right per-file section |
+| lesson-append | §8 | a deduplicated lesson in existing learning/context storage, never appended to 99 |
 
 ## drift-audit — §7 checklist → detection commands
 
 | §7 item | Detection (deterministic) | Authoritative doc |
 | ------- | ------------------------- | ----------------- |
-| Real CLI surface vs docs | `rg -n "\.command\('" apps/cli/src/commands/` vs `rg -n '^#### \`spur ' docs/04_DESIGN.md` | `04` + `AGENTS.md` surface, `00` committed-surface |
-| `05` ✅/🔶 spot-check; no ⏳ quietly shipped | `rg -n '✅\|🔶\|⏳\|💤' docs/05_FEATURES.md`, then check each against code | `05` |
+| Real CLI surface vs docs | Compare source-local help/registrations with owning `docs/design/` contracts | `04` satellites |
+| Feature state matches evidence | Read the feature tool's generated index, then inspect affected acceptance evidence | `05` / feature records |
 | Every shipped surface has a `01` scope row | surface set (above) vs `rg` of `01` scope table | `01` |
 | `02` phase bullets name real things | read `02` current-phase bullets; grep each name in code/docs | `02` |
-| `03` modules vs real tree | `fd -t d -d 2 . apps packages` vs `03` module list | `03` |
+| `03` modules vs real tree | `rg --files apps packages` vs `03` module map | `03` |
 | `04` covers every command/flag/config/schema | the verb/flag/config set vs `04` | `04` |
 | `AGENTS.md` doc map == §4.1 | diff the two tables | `AGENTS.md` (§4.4) |
 | frontmatter matches §4.1 + `updated_at` plausible | see contract-verify | each doc (§4.3) |
 
 **Judgment:** is a candidate real drift (vs. an intentional, documented exception)? Which doc is
-authoritative? What is the *minimal* repair (a one-line dated amendment beats a rewrite)?
+authoritative? What is the *minimal* repair (preserve decision history and condense only editorial noise under §6.1)?
 
-## sync-check — T1–T8 → obligations
+## sync-check — applicable §5 triggers → obligations
 
-Read the change (diff or finished task); for each changed path classify the trigger and confirm the
-obligated doc was touched in the same change. The high-frequency miss is **T3** (a CLI/config/schema
-change without the matching `04` + `AGENTS.md` edit) — check it first. (T1–T8 listed in the SKILL.md
-table; this reference is the detection recipe, not a restatement of the triggers.)
-
-```bash
-# Surface changed in this diff?
-git diff --name-only | rg 'apps/cli/src/commands/|packages/.*/schema|config/'
-# Was 04 / AGENTS.md touched in the same diff?
-git diff --name-only | rg 'docs/04_DESIGN.md|^AGENTS.md'
-# Both non-empty → likely synced; surface-changed-but-no-04 → T3 drift.
-```
+Read the diff and the live constitution §5. Map changed facts to their owning document and
+check that contract, not merely whether a filename appears in the diff. Unchanged index pointers
+and entry guidance need no edits. T7 additionally requires the governance reason and existing
+operator authorization under §6.8; include affected templates.
 
 ## contract-verify — §4.3
 
@@ -65,15 +57,10 @@ Compare `owns`/`authority` against the §4.1 row (verbatim in meaning; §4.1 win
 
 ## lesson-append — §8
 
-```
-- [YYYY-MM-DD] <project>: <lesson — what went wrong / what to do instead>
-```
-
-1. Identify the per-file `### Lessons for <doc>` section (or the cross-cutting one).
-2. `rg` that section for an equivalent lesson — if found, **bump its date**, don't duplicate.
-3. Append the formatted line. If the lesson restates an existing §6 rule, it's already law — skip.
-4. If it has recurred, **promote** it to a §6 rule / §5 trigger and remove from §8 (the only
-   sanctioned deletion).
+1. Resolve the existing learning/context destination from the project's conventions.
+2. Search for an equivalent lesson; skip duplicates and routine completion receipts.
+3. Record the useful lesson with evidence outside the constitution.
+4. Propose any governance correction separately; recurrence does not authorize a §6.8 edit.
 
 ## Drift-report shape
 
@@ -84,7 +71,7 @@ Checks run: <n> (§7 items)  ·  Findings: <m>
 
 | # | Doc | Reality says | Doc says | Authority | Trigger | Repair |
 |---|-----|--------------|----------|-----------|---------|--------|
-| 1 | 04_DESIGN | `spur foo` exists (apps/cli/.../foo.ts) | absent | 04 (T3) | — | add the §6.4 command block |
+| 1 | 04_DESIGN | Changed command contract | Satellite describes old behavior | 04 | T3 | update its owning satellite under §6.5 |
 
 Zero-finding checks: <list the §7 items that returned no delta, with the command used>
 ```

package/plugins/sp/skills/spur-cli/references/tasks/verbs.md

@@ -67,6 +67,20 @@ frontmatter scalar.
   wholesale. No inline-body flag. Section names: `Background`, `Requirements`, `Acceptance Criteria`, `Q&A`, `Design`, `Plan`, `Solution`, `Testing`, `Review`, `References`, `History`, `Notes`.
 - **Frontmatter** (`--feature <id>`, `--priority <p>`): sets the scalar frontmatter field on an
   existing task — the only post-create path, allow-listed to `feature_id` / `parent_wbs` / `priority`.
+- **AC controls** (`--ac-altitude <graduating|task-local>`, `--ac-numbering task-local`) — independent
+  of each other (task 0818 R5). `--ac-altitude task-local` skips the **DD-09 feature-AC subset** rule
+  because the task's scenarios are intentionally not the feature's ship criteria; `--ac-numbering
+  task-local` opts the task into the **Requirements↔AC coverage** check inside the task. Setting one
+  never implies the other. `graduating` remains the default and DD-09 stays enforced for graduating
+  tasks. Use it for an issue/fix-batch task that is genuinely linked to a feature but whose
+  regression scenarios sit below that feature's ship criteria, and record the rationale in the task
+  body:
+
+  ```bash
+  # One frontmatter flag per call — `update` sets a single field and ignores the rest.
+  bun run apps/cli/src/index.ts task update 0818 --feature D6 --json
+  bun run apps/cli/src/index.ts task update 0818 --ac-altitude task-local --json
+  ```
 
 Exit code `2` when neither mode's required args are supplied (e.g. `--section` without `--from-file`,
 or no status and no `--section`/frontmatter flag).
@@ -183,7 +197,9 @@ traceability. Bare = whole corpus; with a WBS = one task. The matrix is loaded f
 
 **L4 traceability** resolves `feature_id` / `parent_wbs` / `dependencies` edges and checks **AC
 coverage** (DD-09): a task's scenarios must be a subset of its linked feature's AC by normalized
-title — orphans warn by default.
+title — orphans warn by default. A task declaring `ac_altitude: task-local` is exempt from that
+subset rule only (`--ac-altitude`, above); every graduating task is still enforced, and the exemption
+does not touch `ac_numbering`'s Requirements↔AC coverage or any other layer.
 
 `--json` emits an array of per-task results:
 

package/plugins/sp/skills/spur-cli/references/tasks.md

@@ -157,13 +157,43 @@ spur task update 0040 --section Review --from-file /tmp/review.md
   first, then point `--from-file` at it.
 
 **Frontmatter set** (the only post-create path to scalar fields, allow-listed to
-`feature_id`/`parent_wbs`/`priority`):
+`feature_id`/`parent_wbs`/`priority`, plus the two AC controls below):
 
 ```bash
 spur task update 0040 --feature H2
 spur task update 0040 --priority P1
 ```
 
+### AC altitude — `--ac-altitude` (task 0818 R5)
+
+`--ac-altitude` and `--ac-numbering` are **independent** controls that are easy to confuse:
+
+| Flag | Controls | Default | `task-local` means |
+| --- | --- | --- | --- |
+| `--ac-altitude <graduating\|task-local>` | DD-09 **feature-AC subset** rule (task scenarios ⊆ linked feature AC) | `graduating` | the task's scenarios are deliberately **not** feature ship criteria — skip the subset rule |
+| `--ac-numbering <task-local>` | **Requirements↔AC coverage** inside the task | off | opt the task into the R-to-AC coverage check |
+
+Setting one says nothing about the other: a `task-local`-altitude task can still be under full
+R-to-AC coverage, and usually should be.
+
+**The standing pattern for an issue or fix-batch task.** Link it to the feature it substantively
+belongs to — do not leave it orphaned and do not relink unrelated corpus to silence a diagnostic.
+Then, *only* when its regression scenarios intentionally do not represent that feature's ship
+criteria, declare `--ac-altitude task-local` and record the rationale in the task body (Background
+or Design), so the choice is auditable rather than inferred:
+
+```bash
+# source-local CLI (before `bun link`, or when pinning to this checkout).
+# One frontmatter flag per call: `update` applies a single field, so a second
+# frontmatter flag in the same invocation is silently ignored.
+bun run apps/cli/src/index.ts task update 0818 --feature D6 --json
+bun run apps/cli/src/index.ts task update 0818 --ac-altitude task-local --json
+```
+
+`graduating` stays the default, and DD-09 stays enforced for every graduating task — this flag
+expresses a real altitude distinction, not a gate escape hatch. Ordinary orphan warnings are
+unchanged, and no checker policy changes.
+
 The section-write-then-replace pattern is the workflow agents use to fill in `Plan` / `Solution` /
 `Testing` / `Review` during a run. See
 [tasks/section-editing.md](tasks/section-editing.md) for the full recipe. For pipeline

package/plugins/sp/skills/spur-dev/references/ac-style-guide.md

@@ -113,6 +113,20 @@ Any of the four may additionally carry a **bracket tag** in any position — `[d
 `Scenario: [advisory] Foo`. Tags are stripped before matching (0398 R7), so tagging never breaks
 the linkage.
 
+Task-side, `verify-answer-lint` additionally accepts a fifth declared id source — a **bold-trajectory
+paragraph**: a whole-line `**AC id…**` paragraph inside the task's `### Acceptance Criteria`
+block (task 0817 R3). The id up to its first `:` and the paragraph's full spelling are both
+declared; two bold spans on one line are not a declaration (an interpolated bold id stays
+unmatchable):
+
+```markdown
+### Acceptance Criteria
+
+**AC-0817-HERM-SKIP: unpinned project-config resolution is suppressed.**
+
+| AC-0817-HERM-SKIP | MET | test | `tests/loader.test.ts:962` |        ← declared
+```
+
 ### The id is exactly the scenario title — no Gherkin body appended
 
 An AC row id must be **exactly** the scenario title (plus any of the four forms above), with the

package/plugins/sp/skills/spur-dev/references/cross-cutting.md

@@ -634,9 +634,9 @@ CLI-gated corpus artifact. The `wrapup-pipeline.yaml` `learning-capture` step wr
 
 - **Not CLI-gated.** The file is written directly by the wrap-up pipeline's `learning-capture`
   agent.run step. It does not go through `spur task update` or `spur feature update`.
-- **Not a validated corpus.** The file is a working scratchpad. High-value learnings are promoted
-  to `docs/99_PROJECT_CONSTITUTION.md §8` (lessons) by the `doc-sync` step (via `sp:doc-evolve`),
-  not by the learning-capture step itself.
+- **Not a validated corpus.** The file is a working scratchpad. Deduplicate reusable lessons in
+  existing project learning/context storage. Constitution §8 routes lessons outside that file;
+  doc-sync does not promote lessons into governance without operator-authorized §6.8 scope.
 - **Append-only within a session.** New entries are appended; existing entries are not rewritten.
 - **Grouped by date and task.** Each entry has a date and task WBS header so the operator can
   trace a learning back to its source task.