@gobing-ai/spur 0.3.62 → 0.3.64

package/config/workflows/history-anatomy.yaml

@@ -31,6 +31,10 @@
 #   date      — YYYY-MM-DD for --date (daily); empty for ad-hoc
 #   since     — inclusive ISO lower bound (ad-hoc; also normalizes daily via the DST-aware rule)
 #   until     — inclusive ISO upper bound (ad-hoc)
+#   baselineSince — declared home for the baseline-leg lower bound the analyze stage references;
+#               actual values flow through the run-scoped env file emitted by resolve-paths
+#               (0674 R2/R5 — a referenced var must have a declared home, never an implicit one)
+#   baselineUntil — baseline-leg upper bound, same contract as baselineSince
 #   focus     — ad-hoc focus string (required in ad-hoc mode, rejected in daily)
 #   recompute — "true" forces the full analyze/render/enrich/validate path (cache disposition
 #               forced-recompute)
@@ -57,10 +61,14 @@ vars:
   date: ""
   since: ""
   until: ""
+  baselineSince: ""
+  baselineUntil: ""
   focus: ""
   recompute: "false"
   output: ""
-  agent: "omp"
+  # 0676 R5: omp went quota-dead (HTTP 429) in the 2026-08-25 dogfood. The literal names a
+  # currently-reachable executor; `agent.default` in config still overrides via the precedence chain.
+  agent: "claude"
   spurBin: "spur"
   __runId: ""
   stepTimeoutMs: "1800000"
@@ -110,7 +118,8 @@ states:
           command: >-
             h=$(superskill script path sp history-anatomy-cache.mjs);
             node "$h" paths --helper "$h" --report-dir "$reportDir" --date "$date"
-            --output "$output" --out .spur/run/$__runId-paths.env
+            --output "$output" --mode "$mode" --since "$since" --until "$until"
+            --out .spur/run/$__runId-paths.txt
 
   - id: analyze
     description: >
@@ -122,11 +131,13 @@ states:
         options:
           command: >-
             mkdir -p .spur/run;
-            $spurBin history analyze --out .spur/run/$__runId-history-anatomy-current.json --since "$since" --until "$until" --json
+            . .spur/run/$__runId-paths.txt;
+            $spurBin history analyze --out .spur/run/$__runId-history-anatomy-current.json --since "$HA_SINCE" --until "$HA_UNTIL" --json
       - kind: shell
         options:
           command: >-
-            $spurBin history analyze --out .spur/run/$__runId-history-anatomy-baseline.json --since "$baselineSince" --until "$until" --json 2>/dev/null || true
+            . .spur/run/$__runId-paths.txt;
+            $spurBin history analyze --out .spur/run/$__runId-history-anatomy-baseline.json --since "$HA_BASELINE_SINCE" --until "$HA_BASELINE_UNTIL" --json 2>/dev/null || true
 
   - id: cache-probe
     description: >
@@ -138,7 +149,7 @@ states:
       - kind: shell
         options:
           command: >-
-            . .spur/run/$__runId-paths.env;
+            . .spur/run/$__runId-paths.txt;
             node "$HA_HELPER" probe --artifact .spur/run/$__runId-history-anatomy-current.json
             --baseline .spur/run/$__runId-history-anatomy-baseline.json --target "$HA_TARGET"
             --mode "$mode" --date "$HA_DATE" --recompute "$recompute" --executor "$agent"
@@ -161,8 +172,14 @@ states:
   - id: enrich
     description: >
       Model enrichment via the skill operation sp:history-anatomy enrich (0658 operations.md).
-      Consumes the two artifacts; authors the model half of the report.
+      Consumes the two artifacts; authors the model half of the report. A porcelain baseline
+      is captured before dispatch and asserted after: any working-tree file created outside the
+      declared output fails the run (0676 R3).
     onEnter:
+      - kind: shell
+        options:
+          command: >-
+            git status --porcelain > .spur/run/$__runId-baseline-enrich.txt || true
       - kind: agent.run
         options:
           agent: ${vars.agent}
@@ -171,10 +188,14 @@ states:
           role: reviewer
           expectFile: .spur/run/${vars.__runId}-candidate.md
           timeoutMs: ${vars.stepTimeoutMs}
+      - kind: shell
+        options:
+          command: >-
+            node "$(superskill script path sp history-anatomy-cache.mjs)" assert-clean --baseline .spur/run/$__runId-baseline-enrich.txt --expect .spur/run/$__runId-candidate.md
 
   - id: structure-gate
     description: >
-      Deterministic structure gate via the helper (0659). Asserts the eleven sections in order,
+      Deterministic structure gate via the helper (0659). Asserts the twelve sections in order,
       per-finding fields, no placeholders, evidence anchors. Not reachable on the hit path from
       enrich — always gated before validation.
     onEnter:
@@ -187,8 +208,12 @@ states:
   - id: validate
     description: >
       Independent evidence validation via the skill operation sp:history-anatomy validate.
-      Publication is reachable only from a PASS here.
+      Publication is reachable only from a PASS here. Same undeclared-write assertion as enrich (0676 R3).
     onEnter:
+      - kind: shell
+        options:
+          command: >-
+            git status --porcelain > .spur/run/$__runId-baseline-validate.txt || true
       - kind: agent.run
         options:
           agent: ${vars.agent}
@@ -197,6 +222,10 @@ states:
           role: reviewer
           expectFile: .spur/run/${vars.__runId}-validation.txt
           timeoutMs: ${vars.stepTimeoutMs}
+      - kind: shell
+        options:
+          command: >-
+            node "$(superskill script path sp history-anatomy-cache.mjs)" assert-clean --baseline .spur/run/$__runId-baseline-validate.txt --expect .spur/run/$__runId-validation.txt
 
   - id: correct
     description: >
@@ -219,7 +248,7 @@ states:
       - kind: shell
         options:
           command: >-
-            . .spur/run/$__runId-paths.env;
+            . .spur/run/$__runId-paths.txt;
             node "$HA_HELPER" refresh --report "$HA_TARGET"
             --out .spur/run/$__runId-publishable.md --disposition hit
 
@@ -233,7 +262,7 @@ states:
       - kind: shell
         options:
           command: >-
-            . .spur/run/$__runId-paths.env;
+            . .spur/run/$__runId-paths.txt;
             node "$HA_HELPER" stamp --candidate .spur/run/$__runId-candidate.md
             --provenance .spur/run/$__runId-provenance.json
             --out .spur/run/$__runId-publishable.md
@@ -247,7 +276,7 @@ states:
       - kind: shell
         options:
           command: >-
-            . .spur/run/$__runId-paths.env;
+            . .spur/run/$__runId-paths.txt;
             mkdir -p "$(dirname "$HA_TARGET")";
             node "$HA_HELPER" publish .spur/run/$__runId-publishable.md "$HA_TARGET"
 

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@gobing-ai/spur",
-    "version": "0.3.62",
+    "version": "0.3.64",
     "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": "^0.4.42",
-        "@gobing-ai/ts-ai-runner": "^0.4.42",
-        "@gobing-ai/ts-dual-workflow-engine": "^0.4.42",
-        "@gobing-ai/ts-infra": "^0.4.42",
-        "@gobing-ai/ts-llm-jsonl-importer": "^0.4.42",
-        "@gobing-ai/ts-rule-engine": "^0.4.42",
-        "@gobing-ai/ts-runtime": "^0.4.42",
-        "@gobing-ai/ts-utils": "^0.4.42",
+        "@gobing-ai/ts-db": "^0.4.45",
+        "@gobing-ai/ts-ai-runner": "^0.4.45",
+        "@gobing-ai/ts-dual-workflow-engine": "^0.4.45",
+        "@gobing-ai/ts-infra": "^0.4.45",
+        "@gobing-ai/ts-llm-jsonl-importer": "^0.4.45",
+        "@gobing-ai/ts-rule-engine": "^0.4.45",
+        "@gobing-ai/ts-runtime": "^0.4.45",
+        "@gobing-ai/ts-utils": "^0.4.45",
         "@types/bun": "1.3.14",
         "@types/figlet": "^1.7.0",
         "@types/node-notifier": "8.0.5",

package/plugins/sp/README.md

@@ -128,14 +128,14 @@ list this README is checked against.
 | `dev-debug`         | Systematic debugging protocol — reproduce, isolate, diagnose root cause, apply minimal fix, and verify with regression tests                                                                      |
 | `dev-daily`         | Generate a daily summary report from agent usage data, git history, and notes                                                                                                                     |
 | `dev-dogfood`       | Dogfood an agent skill/command/CLI — drive it end-to-end with bounded auto-fix, self-monitor, and emit a comprehensive report                                                                     |
-| `dev-find-issue`    | Generate the daily/ad-hoc history-anatomy diagnostic report over already-imported history — mode contract, closed finding taxonomy, eleven-section report contract, cache branch, atomic publication; forwards to sp:history-anatomy                               |
+| `dev-find-issue`    | Generate the daily/ad-hoc history-anatomy diagnostic report over already-imported history — mode contract, closed finding taxonomy, twelve-section report contract, cache branch, atomic publication; forwards to sp:history-anatomy                               |
 | `dev-find-conflict` | Authority-aware semantic audit across source, task, feature, and project authority files — detect conflicts, resolve claim-specific authority, and route confirmed repairs through owner surfaces |
 | `dev-find-next`     | Prompt-first feature frontier prioritizer — ranks the open feature frontier by derived importance/urgency with per-candidate evidence; gates unactionable features; emits tree defects as proposals only     |
 | `dev-fixall`        | Fix all lint, type, and test errors systematically across the working tree                                                                                                                        |
 | `dev-simplify`      | Simplify recently-changed code for clarity without changing behavior — incremental, test-after-each, revert on regression                                                                         |
 | `dev-arch`          | Survey a codebase (or module tree) for shallow modules and deepening opportunities — emit a ranked MARKDOWN candidate report that feeds the planning half; never auto-refactors                   |
 | `dev-reverse`       | Reverse-engineer a codebase — analyze unfamiliar repos, generate HLD/architecture docs, audit quality/security, and produce onboarding documentation                                              |
-| `dev-gitmsg`        | Generate conventional commit message(s) from staged changes via per-file summarization, optionally commit                                                                                         |
+| `dev-gitmsg`        | Generate conventional commit message(s) from the current change set via one bounded diff capture, optionally commit                                                                                         |
 | `dev-gtd`           | Get things done — quality gate (auto-fix) → conventional commit → push → gh verify in one flow; optional act CI simulation via `--act`                                                          |
 | `dev-changelog`     | Generate changelog from git commits                                                                                                                                                               |
 
@@ -173,7 +173,7 @@ and verification (`sp:code-verification`) — plus a CLI facade (`sp:spur-cli`,
 `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`, `sp:indexed-context`). See
+`sp:daily-summary`, `sp:reverse-engineering`, `sp:issue-finding`, `sp:conflict-finding`, `sp:indexed-context`, `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.
 
@@ -181,7 +181,7 @@ pipeline step.
 
 ```
 plugins/sp/
-├── skills/                          # Domain knowledge + workflow docs (28 skills)
+├── skills/                          # Domain knowledge + workflow docs (31 skills)
 │   ├── brainstorm/                  # Structured ideation workflow
 │   │   ├── agents/openai.yaml
 │   │   ├── examples/ideation-example.md
@@ -239,6 +239,8 @@ plugins/sp/
 │   │   └── references/{authority-resolution.md, comparison-protocol.md, finding-contract.md, remediation-routing.md}
 │   ├── next-feature/                # Prompt-first feature frontier prioritizer (backs /sp:dev-find-next)
 │   │   └── references/{signal-derivation.md, ranking-rubric.md, proposal-contract.md, handoff-routing.md}
+│   ├── redesign-web-ui/             # Existing-UI visual upgrade past generic AI defaults
+│   │   └── references/{audit-checklist, upgrade-techniques}.md
 │   ├── history-anatomy/             # Diagnostic interpretation owner over already-imported history (backs /sp:dev-find-issue)
 │   │   └── references/{modes.md, report-contract.md, operations.md}
 │   ├── sys-architecture/            # Architecture / ADR judgment competency
@@ -318,7 +320,8 @@ surface or run one workflow. All skills target the same five core platforms: `cl
 | `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, eleven-section report contract, `enrich`/`validate` rubrics; no workflow launch, no JSONL fallback, no corpus mutation                                                                   |
+| `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                                                                   |
+| `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)
 

package/plugins/sp/agents/expert-spur.md

@@ -45,10 +45,24 @@ guide and conventions before acting.
 - **Traceability audits** — verify every task links to a feature, every scenario maps to a task.
 - **Section-editing campaigns** — update the same section across multiple tasks.
 - **Rule-catalog work** — author, fine-tune, validate, or harden constraint rules across the catalog.
-- **Workflow work** — author, validate, dry-run, or refactor one or more workflows.
-  When authoring or refactoring, read the composition-measures section in
-  `sp:spur-cli` `references/workflows.md` and apply the advisory's fix-path map — findings are
-  advisory only; never block a run or edit an executing pipeline over them.
+- **Workflow work** — decide fit, author, validate, dry-run, tune, or refactor one or more workflows.
+  Read `sp:spur-cli` `references/workflows/workflow-fit-and-tuning.md` before authoring or
+  refactoring, and apply it in this order:
+  - **Fit first.** A process earns a `spur workflow` only when it replays, branches on a
+    machine-checkable predicate, **and** needs a durable per-run record. Fewer than three → recommend
+    a descriptive procedure or checklist and stop. Author the mode gate only after fit clears.
+  - **Simplicity is the budget, and it is measured.** `shell` commands at or under 5 non-comment
+    units, `agent.run` inputs referencing a slash command rather than carrying a raw prompt, guards
+    a single predicate. Over budget → pick a recorded owner from
+    `docs/design/workflow-shell-ownership.md`; never reformat to dodge the measure.
+  - **Latency and observability are authoring decisions.** Minimize `agent.run` node count first;
+    soft status-file probe over repeated probing; guards ordered cheapest-discriminating-first;
+    `iterationBound` from a latency budget; states named for outcomes; `failureStates` declared.
+  - **Refactor in a named direction** — promote (prose → workflow), demote (workflow → prose),
+    or optimize in place. Back an optimization with a before/after `spur workflow trace` pair,
+    never with a feel.
+  - Composition-advisory findings (`workflow validate --json` → `composition`) are advisory only;
+    never block a run or edit an executing pipeline over them.
 - **Corpus health checks** — run `check`/`validate` across a batch and report findings.
 
 For a single operation, use the `spur` CLI directly. For the planning/execution lifecycle, use
@@ -72,12 +86,14 @@ Invoke `sp:spur-cli` for verb guidance and per-noun conventions:
 - [ ] Run the corpus-wide sweep after batch edits: `spur task check --corpus --json` (fails on structural errors outside `config/corpus-baseline.json`).
 - [ ] Use `spur task update --section --from-file` for all task section edits.
 - [ ] Run the noun's scoped `refresh` after batch operations where one exists (`spur task refresh`, `spur feature refresh --feature <id>` or `--all`).
+- [ ] Run the workflow fit gate before authoring any new workflow, and recommend a descriptive procedure when it does not clear all three parts.
 
 ### Never
 
 - [ ] Never edit corpus files directly — always through CLI verbs.
 - [ ] Never reimplement verb logic or validation — the CLI owns it.
 - [ ] Never drive the planning/execution lifecycle through this agent — use `sp:spur-dev`.
+- [ ] Never author a workflow whose every node is a raw-prompt `agent.run` — that is a descriptive procedure paying a process spawn per step.
 
 ## Output Format
 

package/plugins/sp/commands/dev-find-issue.md

@@ -1,7 +1,7 @@
 ---
-description: "Generate the daily or ad-hoc history-anatomy diagnostic report over already-imported history: the eleven-section report contract, closed finding taxonomy, cache branch, bounded correction, and atomic publication. Triggers: find issues, post-mortem, performance analysis, session review, history-anatomy, run the daily report, ad-hoc diagnosis"
+description: "Generate the daily or ad-hoc history-anatomy diagnostic report over already-imported history: the twelve-section report contract, closed finding taxonomy, cache branch, bounded correction, and atomic publication. Triggers: find issues, post-mortem, performance analysis, session review, history-anatomy, run the daily report, ad-hoc diagnosis"
 role: reviewer
-argument-hint: "[<focus>] [--mode <daily|ad-hoc>] [--date <YYYY-MM-DD>] [--since <RFC3339>] [--until <RFC3339>] [--recompute] [--agent <inline|auto|name>] [--output <path>]"
+argument-hint: "[<focus>] [--mode <daily|ad-hoc>] [--date <YYYY-MM-DD>] [--since <RFC3339>] [--until <RFC3339>] [--recompute] [--agent <auto|name>] [--output <path>]"
 allowed-tools: ["Bash", "Read", "Skill"]
 ---
 
@@ -10,7 +10,7 @@ allowed-tools: ["Bash", "Read", "Skill"]
 Wraps the **sp:history-anatomy** skill — the independent owner of diagnostic interpretation over
 already-imported history. The skill resolves the mode contract (daily is the default and uses the
 current local calendar day; ad-hoc requires a focus plus two ordered bounds), owns the report
-contract (eleven sections, closed finding taxonomy, evidence rules, recurrence ledger), and
+contract (twelve sections, closed finding taxonomy, evidence rules, recurrence ledger), and
 exposes the `enrich` and `validate` operations the `history-anatomy.yaml` workflow invokes.
 Publication is atomic and gated behind both the deterministic structure gate and independent
 evidence validation. This command never triggers an import.
@@ -25,7 +25,7 @@ evidence validation. This command never triggers an import.
 | `--since` `<RFC3339>`                  | Inclusive lower bound (ad-hoc; required).                                                          | omitted  |
 | `--until` `<RFC3339>`                  | Inclusive upper bound (ad-hoc; required).                                                          | omitted  |
 | `--recompute`                          | Force the full analyze/render/enrich/validate path; records disposition forced-recompute.          | off      |
-| `--agent` `<inline\|auto\|name>`       | Execution surface selector.                                                                        | inline   |
+| `--agent` `<auto\|name>`               | Execution surface selector. This target is engine-driven (headless). Per task 0687, omit and explicit `--agent inline` resolve identically — tier resolution with one warning naming the substituted executor; there is deliberately **no** host-session inline driver for `history-anatomy.yaml` (mechanism (b)). A name pins the executor. | omitted  |
 | `--output` `<path>`                    | Explicit report output path (ad-hoc; default writes to the run directory).                         | run dir  |
 
 For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).

package/plugins/sp/commands/dev-gitmsg.md

@@ -1,7 +1,7 @@
 ---
-description: Generate conventional commit message(s) from staged changes via per-file summarization, optionally commit
+description: Generate conventional commit message(s) from the current change set via one bounded diff capture, optionally commit
 role: scribe
-argument-hint: "[--commit] [--squash] [--scope <path>]"
+argument-hint: "[--commit] [--squash] [--all] [--scope <path>]"
 allowed-tools: ["Bash", "Read"]
 ---
 
@@ -13,17 +13,23 @@ Implements an inline procedure — see [dev-operations.md](../skills/spur-dev/re
 
 | Flag | Description | Default |
 | --- | --- | --- |
-| `--commit` | Stage and commit with the generated message. | off |
-| `--squash` | Squash staged changes into one commit. | off |
-| `--scope` `<path>` | Scope the diff to a path. | all staged changes |
+| `--commit` | Commit the change set — one commit per concern. | off |
+| `--squash` | Collapse every concern into one message and one commit; implies `--commit`. | off |
+| `--all` | Widen the change set past the index to every change in the tree — unstaged **and untracked**. | off |
+| `--scope` `<path>` | Path filter on the change set; always wins over change-set auto-discovery. | the whole change set |
 
 For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
 
 ## Usage
 
-/sp:dev-gitmsg [--commit] [--squash] [--scope <path>]
+/sp:dev-gitmsg [--commit] [--squash] [--all] [--scope <path>]
 
 ## Implementation
 
 Follow the inline procedure in [dev-operations.md](../skills/spur-dev/references/dev-operations.md#9-gitmsg) (gitmsg).
 
+One diff capture per run — `-U0`, lockfiles excluded, 60 KB cap — is the token contract; never re-read
+the diff wider. Neither `--commit` nor `--squash` → messages only. `--commit` → one commit per concern, split automatically,
+so the operator is never asked to re-stage and re-run. `--squash` → one commit for everything.
+An empty index widens to the whole tree only on a message-only run, and says so; a committing run
+stops there and prints the exact `--all` re-run line instead of guessing.

package/plugins/sp/commands/dev-gtd.md

@@ -62,25 +62,14 @@ The real GitHub CI runner passes. **Do not** modify the build infrastructure to
 Then stop the run (this stage failed). The operator can proceed by re-running without `--act`.
 
 **3 — Generate a conventional commit message.** Follow the gitmsg procedure (the same one
-`/sp:dev-gitmsg` runs). Run `git diff --cached --stat` (add `-- <path>` when `--scope` is given) for
-the outline; if it is empty, stage the intended changes first and report "no staged changes" if
-nothing was meant to be committed. Capture the full diff to a temp file
-(`TEMP_FILE="/tmp/gitdiff_$(date +%s)"; git diff --cached > "$TEMP_FILE" 2>&1`). Read it and write
-**one sentence per changed file** — what changed and why. Group the per-file sentences by concern;
-for each group derive its commit type (`feat` · `fix` · `refactor` · `docs` · `chore` · `perf` ·
-`test` · `style`), scope (affected module/package, or the `--scope` value), and message:
-
-```
-<type>(<scope>): <summary>
-
-<body — optional bullets from the group's per-file sentences>
-```
-
-Summary: imperative mood, ≤72 chars, lowercase first word, no period. Body only when the change is
-non-obvious. Resolve groups: one group → emit its message; multiple groups → emit one message per
-group plus a split recommendation (stage per concern, re-run); under this all-in-one flow, prefer a
-single combined message (dominant type/scope, per-file bullets) so the push is atomic. Delete the
-temp file (`rm "$TEMP_FILE"`) — no `/tmp` diff residue.
+`/sp:dev-gitmsg` runs) — see
+[dev-operations.md](../skills/spur-dev/references/dev-operations.md#9-gitmsg): one bounded diff
+capture, concern grouping, conventional `<type>(<scope>): <summary>` formatting. Two deviations
+belong to this flow: read the change set with `--all` semantics (this stage commits everything the
+gate just proved green, not only what happens to be staged), and resolve multiple concerns to a
+**single combined message** (dominant type/scope, one body bullet per concern) so the push is
+atomic. `--scope <path>` bounds the capture as usual. If the change set is empty, report
+"no changes to commit" and stop.
 
 **4 — Commit.** Stage all intended changes (`git add`) and commit with the resolved message
 (`git commit -m "$MESSAGE"`). When `--dry-run`, print the message and the copy-paste `git commit` /

package/plugins/sp/commands/dev-idea.md

@@ -1,7 +1,7 @@
 ---
 description: Turn a vague idea into a feature with AC and a decomposed task batch — discovery, idea-eval, feature-create, AC, feature-check, system-design, decompose, batch-create (Design by default), handoff
 role: planner
-argument-hint: "\"<idea>\" [--auto] [--skip-design] [--approve-taste] [--agent <inline|auto|name>]"
+argument-hint: "\"<idea>\" [--auto] [--skip-design] [--approve-taste] [--agent <auto|name>]"
 allowed-tools: ["Bash", "Read", "Skill", "AskUserQuestion"]
 ---
 
@@ -20,7 +20,7 @@ contract below maps to that workflow's transitions.
 | `--approve-taste` | With `--auto`: set idea_approved + design_approved so idea-eval / design-approval do not pause. | off |
 | `--idea-approved` | Compatibility alias for idea_approved=true (subset of --approve-taste). | off |
 | `--design-approved` | Compatibility alias for design_approved=true (subset of --approve-taste). | off |
-| `--agent` `<inline\|auto\|name>` | Who runs the model-bearing ideation. The pipeline's `agent.run` stages are headless — they always dispatch a subprocess, so `--agent inline` is rejected there with the stable special error (exit 2). Use `omit` (resolves to `agent.default`), `auto` (tier-resolves an executor), or a name (pins that executor). | agent.default |
+| `--agent` `<auto\|name>` | Who runs the model-bearing ideation. The pipeline's `agent.run` stages are headless — they always dispatch a subprocess. Omission and explicit `--agent inline` resolve identically per task 0687: tier substitution plus one warning naming the substituted executor; `auto` (tier-resolves an executor); a name (pins that executor). | inline |
 
 For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
 
@@ -31,7 +31,7 @@ For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag
   [--auto]              # skip objective HITL only (feature-check, batch-create)
   [--skip-design]       # design package off (system-design + task Design)
   [--approve-taste]     # with --auto: skip idea-eval + design-approval pauses
-  [--agent <inline|auto|name>]   # who runs the model-bearing ideation (default: agent.default)
+  [--agent <auto|name>]          # who runs the model-bearing ideation (default: agent.default)
 ```
 
 There is **no** `--design` force flag. Design is default-on; only `--skip-design` opts out.

package/plugins/sp/commands/dev-plan.md

@@ -16,7 +16,7 @@ Wraps the **sp:spur-dev** skill.
 | `"<description>"` | Feature description to plan. | required |
 | `--feature` `<id>` | Attach to an existing feature. | omitted |
 | `--parent` `<feature-id>` | Create under a parent feature. | omitted |
-| `--agent` `<inline\|auto\|name>` | Who runs the model-bearing planning. The planning pipeline's `agent.run` stages are headless — they always dispatch a subprocess. Explicit `--agent inline` is rejected there with the stable special error (exit 2): a headless surface cannot host a session — no dispatch, no `agent.default` fallback. Use `omit` (resolves to `agent.default`), `auto` (tier-resolves an executor), or a name (pins that executor). | agent.default |
+| `--agent` `<inline\|auto\|name>` | Who runs the model-bearing planning. The planning pipeline's `agent.run` stages are headless — they always dispatch a subprocess. `inline` — also what omission resolves to since task 0687 — substitutes tier resolution there with one warning naming the resolved executor; `auto` (tier-resolves an executor); a name (pins that executor). | inline |
 | `--skip-design` | Omit the system-design hop. | off |
 | `--auto` | Skip objective HITL gates. | off |
 | `--approve-taste` | With --auto: skip design-approval pause. | off |

package/plugins/sp/commands/dev-run.md

@@ -15,7 +15,7 @@ Wraps the **sp:spur-dev** and **sp:code-implementation** skills.
 | --- | --- | --- |
 | `<wbs>` | Task WBS to run. | required |
 | `--mode` `<full\|implement>` | Full pipeline or single implement step. | full |
-| `--agent` `<inline\|auto\|name>` | Who runs the model-bearing stages. In an interactive session, omit/`inline` keeps the controller in the host session (non-subprocess) — **omit**'s eligible full-mode `agent.run` stages may dispatch once to a native subagent, with host fallback (task 0508); explicit `--agent inline` is the zero-dispatch carve-out (every stage executes in the invoking session, never a native subagent). `auto` or a name keeps subprocess dispatch. | omit |
+| `--agent` `<inline\|auto\|name>` | Who runs the model-bearing stages. omit and explicit `--agent inline` resolve identically (task 0687): eligible stages dispatch once to a native subagent with host-session fallback (0508 eligibility); otherwise every stage executes in the invoking session. `auto` or a name keeps subprocess dispatch.. | omit |
 | `--auto` | Skip objective HITL confirmations. | off |
 | `--next` | Chain-to-completion via the next-router. | off |
 | `--wrap` | Run the wrap hop after the main step. The `--agent` selector is preserved into the `/sp:dev-wrap <wbs>` handoff when supplied; omission remains omission. The wrap hop is workflow-backed and reports its trigger-3 subprocess override. | off |
@@ -39,7 +39,7 @@ For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag
 
 **Flags:**
 
-- `--auto` | `--agent <inline|auto|name>` — Skip objective HITL confirmations (taste/irreversible gates still pause). `--agent` names who does the model-bearing work. Interactive omit/`inline` keeps the controller and implement-only stages in this session; full mode reads `task-pipeline.yaml` as the SSOT and interprets its actions/guards through the inline driver, where **omitted** `--agent`'s eligible `agent.run` stages may dispatch once to a native subagent and otherwise run in the host (task 0508); explicit `--agent inline` is the zero-dispatch carve-out — every stage executes in the invoking session. It records `stage <id> executed inline in session <session-id>` or `stage <id> executed via subagent <agent-id> (host session <session-id>)` in the run log. `auto` or a name is merged into `vars.agent` and `vars.implementAgent` and keeps the existing subprocess workflow. Headless `spur workflow run` / `spur agent run` is unchanged. See the [execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface).
+- `--auto` | `--agent <inline|auto|name>` — Skip objective HITL confirmations (taste/irreversible gates still pause). `--agent` names who does the model-bearing work. Interactive omit/`inline` keeps the controller and implement-only stages in this session; full mode reads `task-pipeline.yaml` as the SSOT and interprets its actions/guards through the inline driver, whose eligible `agent.run` stages dispatch once to a native subagent and otherwise run in the host (0508 eligibility — task 0687 resolved-inline) It records `stage <id> executed inline in session <session-id>` or `stage <id> executed via subagent <agent-id> (host session <session-id>)` in the run log. `auto` or a name is merged into `vars.agent` and `vars.implementAgent` and keeps the existing subprocess workflow. Headless `spur workflow run` / `spur agent run` is unchanged. See the [execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface).
 
 `--worktree` `[<name>]` (run the task's pipeline in an isolated git worktree — FF-merge onto the
 base ref on full success, retain intact on any failure/halt/non-FF; bare form creates a fresh tree,

package/plugins/sp/commands/dev-runall.md

@@ -18,7 +18,7 @@ Wraps the **sp:spur-dev** skill.
 | `--mode` `<sequential\|parallel>` | Batch execution order. | sequential |
 | `--keep-going` | Continue past per-task failures. | off |
 | `--auto` | Skip objective HITL gates. | off |
-| `--agent` `<inline\|auto\|name>` | Who runs each task's pipeline stages. Interactive sequential omit/`inline` uses the host-session driver — host-controlled; **omit**'s eligible `agent.run` stages may use a native subagent (task 0508); explicit `--agent inline` is the zero-dispatch carve-out (every stage executes in the invoking session). `auto`, a name, parallel mode, and headless invocation use subprocesses. | omit |
+| `--agent` `<inline\|auto\|name>` | Who runs each task's pipeline stages. Interactive sequential omit/`inline` uses the host-session driver with unified inline semantics (task 0687 — see below)). `auto`, a name, parallel mode, and headless invocation use subprocesses. | omit |
 | `--json` | Emit structured JSON. | off |
 | `--wrap` | Run the wrap hop per task. The `--agent` selector is preserved into each `/sp:dev-wrap <wbs>` handoff when supplied; omission remains omission. | off |
 | `--next` | Chain-to-completion via the next-router. | off |
@@ -81,6 +81,6 @@ full distinction.
 
 ## Implementation
 
-- Apply the [inline-default execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface). Interactive sequential omit/`inline` keeps the orchestrator in the host session through the [inline pipeline driver](../skills/spur-dev/references/inline-pipeline-driver.md); **omitted** `--agent`'s eligible `agent.run` stages may dispatch once to a native subagent with host fallback (task 0508); explicit `--agent inline` is the zero-dispatch carve-out. `--agent auto`, a name, or parallel mode retains the isolated per-task workflow boundary.
+- Apply the [inline-default execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface). Interactive sequential omit/`inline` keeps the orchestrator in the host session through the [inline pipeline driver](../skills/spur-dev/references/inline-pipeline-driver.md); the resolved selector applies uniformly — eligible `agent.run` stages dispatch once to a native subagent with host fallback (0508). `--agent auto`, a name, or parallel mode retains the isolated per-task workflow boundary.
 - Interactive sequential omit/inline: `Skill(skill="sp:spur-dev", args="runall-inline $ARGUMENTS")`.
 - Explicit executor or parallel mode: `Skill(skill="sp:spur-dev", args="runall $ARGUMENTS")` → `sp:super-planner` agent.

package/plugins/sp/commands/dev-wrap.md

@@ -14,7 +14,7 @@ Wraps the **wrapup-pipeline.yaml** workflow.
 | Flag | Description | Default |
 | --- | --- | --- |
 | `<wbs>` | Task WBS to wrap. | required |
-| `--agent` `<inline\|auto\|name>` | Who runs the wrap's model-bearing steps. Wrap is workflow-backed (headless): `omit` resolves to `agent.default` (objective trigger 3 — durable auditable run record required); explicit `--agent inline` is rejected with the stable special error — a headless workflow surface cannot host a session; `auto` tier-resolves an executor; a name pins that executor into `vars.agent`. | agent.default |
+| `--agent` `<inline\|auto\|name>` | Who runs the wrap's model-bearing steps. Wrap is workflow-backed (headless): `omit` and `--agent inline` resolve identically per task 0687 — tier substitution under objective trigger 3 (durable auditable run record required) with a warning naming the substituted executor; `auto` tier-resolves an executor; a name pins that executor into `vars.agent`. | inline |
 | `--auto` | Skip objective HITL gates. | off |
 | `--merge` | Merge the wrap branch. | off |
 | `--dry-run` | Render the wrap without writing. | off |
@@ -32,13 +32,13 @@ For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag
 - Resolve the executor **before** launching the workflow:
   - `--agent <name>` → pass the name unchanged into `vars.agent`.
   - `--agent auto` → tier-resolve a concrete executor first, then merge it into `vars.agent`.
-  - omit → resolve to `agent.default`; explicit `--agent inline` → rejected with the stable special error (headless surface — no dispatch, no `agent.default` fallback).
+  - omit and explicit `--agent inline` resolve identically (task 0687): tier substitution plus one warning naming the resolved executor (headless surface).
 - Emit a pre-dispatch notice naming the override before `spur workflow run`, exactly:
-  `execution surface: subprocess`, `reason: trigger 3 — durable auditable run record required`, `requested agent: inline|auto|<name>` (explicit `inline` rejects before dispatch — no executor resolves), `executor: agent.default|<resolved-name>`.
+  `execution surface: subprocess`, `reason: trigger 3 — durable auditable run record required`, `requested agent: inline|auto|<name>` (explicit `inline` substitutes tier resolution and warns), `executor: <substituted-name>|<resolved-name>`.
 - The wrap workflow still creates its durable run record (task_run_links / trace) — the notice reports the override, it does not change the workflow.
 
 ```bash
-AGENT=… # resolved above: agent.default for omitted, tier-resolved for auto, unchanged for <name>; explicit inline errors (headless)
+AGENT=… # omit≡inline → tier-substituted executor + warning; auto tier-resolved; <name> unchanged
 echo "execution surface: subprocess; reason: trigger 3 — durable auditable run record required; requested agent: <inline|auto|name>; executor: $AGENT"
 VARS=$(jq -nc --arg tasks "[\"$WBS\"]" --arg agent "$AGENT" --arg profile "$PROFILE" --arg merge "$MERGE" \
   '{tasks:$tasks, agent:$agent, profile:$profile, merge:$merge}')
@@ -46,5 +46,4 @@ spur workflow run wrapup-pipeline.yaml --vars "$VARS" [--dry-run]
 ```
 
 The executor resolution is described in the bullets above; the snippet's `AGENT` variable carries
-the resolved name (`agent.default` for omitted `--agent`; explicit `--agent inline` is rejected
-before dispatch).
+the resolved name (omit ≡ explicit `inline`; both tier-substitute with a warning).

package/plugins/sp/commands/dev-wrapall.md

@@ -16,7 +16,7 @@ Wraps the **wrapup-pipeline.yaml** workflow.
 | `--since` `<iso-date>` | Wrap tasks completed since a date. | configured |
 | `--feature` `<id>` | Wrap tasks in a feature. | omitted |
 | `--status` `<s>` | Only wrap tasks in a status. | done |
-| `--agent` `<inline\|auto\|name>` | Who runs the wrap's model-bearing steps. Wrap is workflow-backed (headless): `omit` resolves to `agent.default` (objective trigger 3 — durable auditable run record required); explicit `--agent inline` is rejected with the stable special error — a headless workflow surface cannot host a session; `auto` tier-resolves an executor; a name pins that executor into `vars.agent`. | agent.default |
+| `--agent` `<inline\|auto\|name>` | Who runs the wrap's model-bearing steps. Wrap is workflow-backed (headless): `omit` and `--agent inline` resolve identically per task 0687 — tier substitution under objective trigger 3 (durable auditable run record required) with a warning naming the substituted executor; `auto` tier-resolves an executor; a name pins that executor into `vars.agent`. | inline |
 | `--auto` | Skip objective HITL gates. | off |
 | `--merge` | Merge wrap branches. | off |
 | `--dry-run` | Render wraps without writing. | off |
@@ -34,13 +34,13 @@ For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag
 - Resolve the executor **before** launching the workflow:
   - `--agent <name>` → pass the name unchanged into `vars.agent`.
   - `--agent auto` → tier-resolve a concrete executor first, then merge it into `vars.agent`.
-  - omit → resolve to `agent.default`; explicit `--agent inline` → rejected with the stable special error (headless surface — no dispatch, no `agent.default` fallback).
+  - omit and explicit `--agent inline` resolve identically (task 0687): tier substitution plus one warning naming the resolved executor (headless surface).
 - Emit a pre-dispatch notice naming the override before `spur workflow run`, exactly:
-  `execution surface: subprocess`, `reason: trigger 3 — durable auditable run record required`, `requested agent: inline|auto|<name>` (explicit `inline` rejects before dispatch — no executor resolves), `executor: agent.default|<resolved-name>`.
+  `execution surface: subprocess`, `reason: trigger 3 — durable auditable run record required`, `requested agent: inline|auto|<name>` (explicit `inline` substitutes tier resolution and warns), `executor: <substituted-name>|<resolved-name>`.
 - The wrap workflow still creates its durable run record — the notice reports the override, it does not change the workflow.
 
 ```bash
-AGENT=… # resolved above: agent.default for omitted, tier-resolved for auto, unchanged for <name>; explicit inline errors (headless)
+AGENT=… # omit≡inline → tier-substituted executor + warning; auto tier-resolved; <name> unchanged
 echo "execution surface: subprocess; reason: trigger 3 — durable auditable run record required; requested agent: <inline|auto|name>; executor: $AGENT"
 VARS=$(jq -nc --arg tasks "$TASKS" --arg feature "$FEATURE" --arg agent "$AGENT" --arg profile "$PROFILE" --arg merge "$MERGE" \
   '{tasks:$tasks, feature:$feature, agent:$agent, profile:$profile, merge:$merge}')
@@ -48,6 +48,4 @@ spur workflow run wrapup-pipeline.yaml --vars "$VARS" [--dry-run]
 ```
 
 The executor resolution is described in the bullets above; the snippet's `AGENT` variable carries
-the resolved name (`agent.default` for omitted `--agent`; explicit `--agent inline` is rejected
-before dispatch).
-
+the resolved name (omit ≡ explicit `inline`; both tier-substitute with a warning).

package/plugins/sp/plugin.json

@@ -1,6 +1,6 @@
 {
     "name": "sp",
-    "version": "0.3.62",
+    "version": "0.3.64",
     "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"]