@gobing-ai/spur 0.3.62 → 0.3.63

package/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
     "plugins": [
         {
             "name": "sp",
-            "version": "0.3.62",
+            "version": "0.3.63",
             "source": "./plugins/sp"
         }
     ]

package/config/corpus-baseline.json

@@ -15044,14 +15044,6 @@
             "reason": "No verdict artifact and the tracked ## Testing section carries no recoverable coverage evidence; tasks predate durable verification recording (F93 fallback state, task 0673).",
             "since": "2026-08-25"
         },
-        {
-            "kind": "task",
-            "id": "0102",
-            "code": "L4.anchor-subject-mismatch",
-            "severity": "error",
-            "reason": "Point-window matcher residue (probe 2): cited line resolves and is in bounds but does not name the row subject because the matcher reads only the cited lines — see note § L4.anchor-subject-mismatch (2026-08-25), ADR-083.",
-            "since": "2026-08-25"
-        },
         {
             "kind": "task",
             "id": "0384",
@@ -15339,6 +15331,206 @@
             "severity": "warning",
             "reason": "Anchor path cannot resolve from project root (bare or plugin-relative) or line range exceeds file — see note § L4.stale-line-anchor (2026-08-25), ADR-083.",
             "since": "2026-08-25"
+        },
+        {
+            "kind": "feature",
+            "id": "E1",
+            "code": "L4.scenario-unverified",
+            "severity": "warning",
+            "reason": "Linked historical task 0474 has no canonical PASS verdict with MET requirements; accepted until evidence is recovered or rerun, with two-sided removal when it lands.",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "feature",
+            "id": "F4",
+            "code": "L4.scenario-unverified",
+            "severity": "warning",
+            "reason": "Linked historical task 0418 has no canonical PASS verdict with MET requirements; accepted until evidence is recovered or rerun, with two-sided removal when it lands.",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "feature",
+            "id": "F91",
+            "code": "L4.scenario-unverified",
+            "severity": "warning",
+            "reason": "Linked historical task 0582 has no canonical PASS verdict with MET requirements; accepted until evidence is recovered or rerun, with two-sided removal when it lands.",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "feature",
+            "id": "G4",
+            "code": "L4.scenario-unverified",
+            "severity": "warning",
+            "reason": "Linked historical task 0529 has no canonical PASS verdict with MET requirements; accepted until evidence is recovered or rerun, with two-sided removal when it lands.",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "feature",
+            "id": "I3",
+            "code": "L4.scenario-unverified",
+            "severity": "warning",
+            "reason": "Linked historical tasks 0539/0540 have no canonical PASS verdict with MET requirements; accepted until evidence is recovered or rerun, with two-sided removal when it lands.",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "feature",
+            "id": "I81",
+            "code": "L4.dogfood-missing",
+            "severity": "warning",
+            "reason": "Self-referential history-anatomy work has no tracked dogfood artifact yet; accepted pending feature verification, with two-sided removal when the artifact lands.",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "feature",
+            "id": "I81",
+            "code": "L4.scenario-unverified",
+            "severity": "warning",
+            "reason": "Linked tasks 0674/0680 predate canonical PASS recording for these scenarios; accepted until evidence is recovered or rerun, with two-sided removal when it lands.",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "feature",
+            "id": "J4",
+            "code": "L4.scenario-unverified",
+            "severity": "warning",
+            "reason": "Linked historical tasks 0374-0378 have no canonical PASS verdicts with MET requirements; accepted until evidence is recovered or rerun, with two-sided removal when it lands.",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "feature",
+            "id": "K",
+            "code": "L4.scenario-unverified",
+            "severity": "warning",
+            "reason": "Linked historical task 0525 has no canonical PASS verdict with MET requirements; accepted until evidence is recovered or rerun, with two-sided removal when it lands.",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0342",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current source line shifts exposed another closed-task point-window mismatch; preserve the historical citation pending the accepted F91 matcher/corpus migration (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0588",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Task 0685 intentionally removed generated demo specs from the tracked tree, invalidating a historical 0588 point anchor; preserve that evidence pending F91 corpus migration (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0609",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Task 0685 intentionally evolved the agent-wait surface and shifted 0609's historical point anchor; preserve that evidence pending F91 corpus migration (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0631",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "The reserved 0685 DDL shifted migration-source line windows and exposed closed-task matcher residue; preserve historical citations pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0639",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current config-source line shifts exposed another closed-task point-window mismatch; preserve the historical citation pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0645",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current web-source line shifts exposed another closed-task point-window mismatch; preserve the historical citation pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0655",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current web-source line shifts exposed another closed-task point-window mismatch; preserve the historical citation pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0665",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current workflow-source line shifts exposed another closed-task point-window mismatch; preserve the historical citation pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0666",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current agent-source line shifts exposed another closed-task point-window mismatch; preserve the historical citation pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0667",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current workflow-source line shifts exposed another closed-task point-window mismatch; preserve the historical citation pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0669",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current history-anatomy source/test line shifts exposed closed-task point-window residue; preserve historical citations pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0670",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current ADR line shifts exposed another closed-task point-window mismatch; preserve the historical citation pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0674",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current history-anatomy source line shifts exposed another closed-task point-window mismatch; preserve the historical citation pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0676",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current history-anatomy source/test line shifts exposed closed-task point-window residue; preserve historical citations pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0680",
+            "code": "L4.anchor-subject-mismatch",
+            "severity": "error",
+            "reason": "Current history-anatomy source/test line shifts exposed closed-task point-window residue; preserve historical citations pending F91 (ADR-083).",
+            "since": "2026-08-26"
+        },
+        {
+            "kind": "task",
+            "id": "0685",
+            "code": "L4.missing-feature-id",
+            "severity": "warning",
+            "reason": "Standalone operator-design task completed with a canonical PASS but no parent feature existed; do not invent a post-hoc feature edge solely to silence the advisory.",
+            "since": "2026-08-26"
         }
     ]
 }

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.env;
+            $spurBin history analyze --out .spur/run/$__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.env;
+            $spurBin history analyze --out .spur/run/$__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": "0.3.63",
     "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": "^0.4.43",
+        "@gobing-ai/ts-ai-runner": "^0.4.43",
+        "@gobing-ai/ts-dual-workflow-engine": "^0.4.43",
+        "@gobing-ai/ts-infra": "^0.4.43",
+        "@gobing-ai/ts-llm-jsonl-importer": "^0.4.43",
+        "@gobing-ai/ts-rule-engine": "^0.4.43",
+        "@gobing-ai/ts-runtime": "^0.4.43",
+        "@gobing-ai/ts-utils": "^0.4.43",
         "@types/bun": "1.3.14",
         "@types/figlet": "^1.7.0",
         "@types/node-notifier": "8.0.5",

package/plugins/sp/README.md

@@ -128,7 +128,7 @@ 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                                                                                                                        |
@@ -318,7 +318,7 @@ 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                                                                   |
 
 #### Bounded coexistence and retirement gate — `sp:issue-finding` (HA-S1 0661)
 

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): omit resolves through the executor precedence chain to `agent.default`, then the workflow literal. Explicit `--agent inline` is rejected with the stable special error (exit 2). | 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-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, 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 |
 
 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/plugin.json

@@ -1,6 +1,6 @@
 {
     "name": "sp",
-    "version": "0.3.62",
+    "version": "0.3.63",
     "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/references/environment-lens.md

@@ -0,0 +1,66 @@
+# Environment-improvement lens
+
+One mapping turns retrospective "environment" observations into concrete surface improvements
+across the two live report owners: `sp:dogfood-testing` report §6 and `sp:history-anatomy`
+sections 4/9. (The inspiration is an out-of-tree retrospective practice; it is deliberately not
+shipped or invoked by anything in this plugin.)
+
+**This file is the single source of truth for the seven categories and the placement rule.**
+Neither report projection restates the table below; each links here as its category table
+(task 0686 / feature I9; accepted design `docs/design/environment-improvement-lens.md`,
+ADR-084/085). There is deliberately no `/sp:dev-retro` command, no CLI change, and no protocol
+bump behind this mapping.
+
+## Canonical categories and projections
+
+Exactly one file (this one) enumerates these seven names. Encode them **only** in the projected
+field named by each column — never as a history-anatomy `category` (that vocabulary is frozen at
+`reliability | repetition | workflow | performance | coverage | telemetry | positive`).
+
+| Retro category | History-anatomy `category` (closed) | History-anatomy `<signal>` | Dogfood class |
+| --- | --- | --- | --- |
+| navigation | `workflow` | `navigation` | `environment` (P3–P2) |
+| automated checks | `reliability` | `automated-checks` | `environment`; action is a gate, not prose |
+| coding standards | `workflow` | `coding-standards` | `environment`; owner surface is review, never implementer |
+| AGENTS.md placement | `workflow` | `agents-md-placement` | `environment`; action = move to skill/reference/check |
+| tool economy | `performance` | `tool-economy` | existing cache-health P3; `environment` when the tool itself is the waste |
+| no-ops | `workflow` | `no-ops` | `environment`; `file:line` of the dead instruction |
+| information access | `telemetry` | `information-access` | existing chained-step `~unknown` P3; `environment` when access is missing |
+
+Dogfood class tags are optional and closed: `environment` | `testee` | `waste`. Grammar,
+classification table, and fix-mode boundaries live in the owning projection:
+[`report-template.md` §6](../skills/dogfood-testing/references/report-template.md).
+History-anatomy key grammar and the structure gate live in
+[`report-contract.md`](../skills/history-anatomy/references/report-contract.md).
+
+## Placement rule
+
+When an observation lands, choose a home in this order — never a new sentence in an
+always-loaded steering file when a lower step fits:
+
+1. **Automatable → propose a check.** Anything a linter, typechecker, test, script-contract
+   check, or filesystem linter could catch becomes a new-or-tighter automated gate
+   (`spur-check`, biome rules, bun tests), not a reminder sentence.
+2. **Coding standard → the review path.** The owner surface is `sp:code-verification`,
+   `sp:code-review`, or pipeline review — never the implementer skill.
+3. **Always-loaded steering (`AGENTS.md` / `CLAUDE.md`) → navigation pointer only.** Detail
+   moves to a skill, reference, or check; the steering file keeps at most a pointer.
+
+## Present-don't-apply
+
+Findings projected through this lens are **proposals**, in either owner's report. No projection
+applies a change, produces a diff, or claims to have executed anything. Dogfood bounded fix-mode
+may repair a failed `testee`-class step, but never mutates a finding tagged `environment`;
+class — not the cited file path — decides whether bounded fix may mutate. History-anatomy stays
+report-only. Accepted proposals reach the tree through operator-approved surfaces (`spur task
+create` handoff, manual edit), which remain explicit human gates.
+
+## Keep / drop boundary
+
+Kept here because both live reports consume it: the seven names above, their projections, and
+this placement rule. Dropped (each needs its own operator decision): installing or invoking the
+out-of-tree retro practice, a standalone retro command, `CODING_STANDARDS.md` as a file, runtime
+parsing of this markdown by validators, automatic remediation of environment findings, and
+folding the lens into wrap-up learnings or `.spur/context/` memory.
+`plugins/sp/skills/issue-finding/` remains the legacy coexistence non-target — it gains nothing
+from this mapping.