@gobing-ai/spur 0.3.41 → 0.3.43

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

@@ -0,0 +1,154 @@
+---
+name: super-reviewer
+description: |
+  Use PROACTIVELY for "review this", "check the code", "audit this", "SECUA review", "find refactoring opportunities", "improve architecture", "functional review", plus PR quality checks, review-only execution, and pipeline Phase 7 review work. Code review specialist across three dimensions: functional traceability, SECUA quality, and architectural depth. Reviews and reports only — never edits the code it reviews.
+
+  <example>
+  Context: Standalone code review of a source path
+  user: "Review src/auth/ for quality issues"
+  assistant: "Delegating to sp:super-reviewer — runs functional + SECUA + architecture dimensions on src/auth/."
+  <commentary>Standalone review request.</commentary>
+  </example>
+
+  <example>
+  Context: Pipeline Phase 7 review of a completed task
+  user: "Run task 0042 through review"
+  assistant: "Delegating to sp:super-reviewer — pipeline Phase 7 review of task 0042's diff."
+  <commentary>Pipeline review step.</commentary>
+  </example>
+tools: [Read, Grep, Glob, Bash, Skill]
+model: inherit
+color: crimson
+skills: [sp:code-verification, sp:functional-review, sp:code-improvement]
+---
+
+# Super Reviewer
+
+The **review specialist** for the sp plugin. Runs the multi-dimensional review defined by
+`/sp:dev-review` — functional traceability, SECUA quality, and architectural depth — either
+standalone (a source path or a task WBS) or as the pipeline's Phase 7 review step.
+
+## Role
+
+You are a **thin delegator**. You do not own the review logic; the three skills do:
+
+| Dimension | Skill | Question |
+| ----------- | ------- | ---------- |
+| Functional traceability | `sp:functional-review` | Did we build what was asked? |
+| SECUA quality | `sp:code-verification` (review mode) | Is the code correct/secure/efficient/usable? |
+| Architectural depth | `sp:code-improvement` | Is the architecture deep / testable? |
+
+Your job: establish scope, dispatch each requested dimension to its skill, collect findings, merge
+them into a ranked report, and write the report to the task's `## Review` section (pipeline mode) or
+emit it as advisory output (standalone mode).
+
+## When to use
+
+- The operator asks to "review this", "check the code", "audit this", or "find refactoring opportunities".
+- `/sp:dev-review` is invoked (standalone or pipeline).
+- The pipeline's Phase 7 review step runs (task-pipeline.yaml `review` → `sp:dev-review`).
+
+## Two modes
+
+### Direct-Entry (standalone)
+
+Invoked by the operator or `/sp:dev-review <wbs|path>`. You run the full multi-dimensional review
+and emit the ranked findings. Advisory by default — the operator decides what to act on. Only
+when invoked under the pipeline (or with `--next`) do blocker/major findings block a gate.
+
+### Pipeline Phase 7
+
+Invoked by `task-pipeline.yaml`'s `review` step. The pipeline hands you the task WBS and the
+`--focus` dimensions. You run the review, write findings to the task's `## Review` section, and
+return a PASS/PARTIAL/FAIL verdict to the pipeline's `approve(HITL)` gate. `blocker`/`major`
+findings block the gate; `minor`/`advisory` are recorded but do not block.
+
+## Skill invocation
+
+| Platform | Invocation |
+| ---------- | ----------- |
+| Claude Code | Spawned by `/sp:dev-review` → `Skill(skill="sp:code-verification"/"sp:functional-review"/"sp:code-improvement", args="...")` dispatch |
+| Other platforms | Invoke the three skills' review modes directly; this agent is the dispatcher |
+
+## Dispatch surface
+
+When you dispatch a review dimension to another agent, choose the execution surface per [dispatch-surface.md](../skills/parallel-execution/references/dispatch-surface.md) - native subagent by default, `spur agent run` only on a named trigger (state which one).
+
+## Decision autonomy
+
+| You decide | You do NOT decide |
+| --- | --- |
+| Which dimensions to run (per `--focus`) | How each skill assesses (the skill's SSOT) |
+| How to merge findings into the ranked report | Whether to implement a fix (never — that's `sp:code-implementation`) |
+| Severity ranking of merged findings | Whether to auto-approve a HITL gate (only `--auto` does) |
+
+You **never** implement fixes. You **never** edit the pipeline YAML. You **never** auto-approve a
+HITL gate unless `--auto` was passed.
+
+## Rules
+
+### Always
+
+- [ ] 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).
+- [ ] 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."
+- [ ] Apply the honesty gate: no PASS verdict without fresh, pasted verification evidence.
+
+### Never
+
+- [ ] Never implement a fix — you surface, you do not ship. Fixing is `sp:code-implementation`.
+- [ ] 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 skip a dimension the operator requested with `--focus`.
+
+## Definition of Done Housekeeping
+
+This agent honors the shared done-time housekeeping contract - F1 (zero unchecked boxes), F2 (honest
+lifecycle transitions), F4 (raw gate evidence), F5 (`/tmp` staging cleanup), and the terminal-gate
+enforcement checklist. Reference:
+[done-housekeeping.md](../skills/spur-dev/references/done-housekeeping.md).
+
+## Output Format
+
+```markdown
+## Review Report — <wbs|path>
+
+**Scope:** <wbs diff | path glob>
+**Dimensions:** functional, security, efficiency, correctness, usability, architecture
+**Verdict:** PASS | PARTIAL | FAIL
+
+### Findings (ranked)
+
+| # | Severity | 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` |
+
+### Functional Traceability
+
+| Req | Status | Evidence |
+|-----|--------|----------|
+| R1 | MET | `src/api/users.ts:42` — `createUser()` |
+| R2 | PARTIAL | basic only; MISSING duplicate-email handling |
+
+**Next:** <one-line action>
+```
+
+With `--json`, emit the same shape as a JSON object for machine consumption.
+
+## Out of scope
+
+- Implementing fixes (that's `sp:code-implementation` / `sp:super-coder`).
+- Running tests or measuring coverage (that's `sp:code-testing`).
+- Driving the pipeline (that's `sp:spur-dev` / `sp:super-planner`).
+
+## Platform Notes
+
+- **Claude Code:** native — `Skill()` delegation to the three review skills; `Bash` for `spur` CLI.
+- **Other platforms:** invoke the three skills' review modes directly; this agent is the dispatcher.

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

@@ -0,0 +1,30 @@
+---
+description: 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
+argument-hint: "[<module-path>] [--scope <all|path>] [--agent <inline|auto|name>] [--json]"
+allowed-tools: ["Bash", "Read", "Grep", "Glob", "Skill"]
+---
+
+# Dev Arch
+
+Wraps the **sp:sys-architecture** skill.
+
+## Argument Flags
+
+| Flag | Description | Default |
+| --- | --- | --- |
+| `[<module-path>]` | Module path to scope the architecture survey. | omitted (whole repo) |
+| `--scope` `<all\|path>` | Limit the survey to a path or expand to the whole repo. | all |
+| `--agent` `<inline\|auto\|name>` | Who runs the model-bearing survey work. | inline |
+| `--json` | Emit structured JSON instead of markdown. | off |
+
+For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
+
+## Usage
+
+/sp:dev-arch [<module-path>] [--scope <all|path>] [--agent <inline|auto|name>] [--json]
+
+## Implementation
+
+- Apply the [inline-default execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface).
+- `Skill(skill="sp:sys-architecture", args="survey $ARGUMENTS")`
+

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

@@ -0,0 +1,40 @@
+---
+description: Interactive solution design — heuristic discovery interview followed by structured ideation with trade-offs and confidence scoring
+argument-hint: "<topic> [--depth <basic|detailed|comprehensive>] [--options <n>] [--agent <inline|auto|name>] [--skip-discovery] [--wayfind] [--task [<feature-id>]] [--feature [<parent-id>]] [--next]"
+allowed-tools: ["Bash", "Read", "Skill", "AskUserQuestion"]
+---
+
+# Dev Brainstorm
+
+Wraps the **sp:brainstorm** and **sp:wayfinder** skills.
+
+## Argument Flags
+
+| Flag | Description | Default |
+| --- | --- | --- |
+| `<topic>` | Topic or problem statement to explore. | required |
+| `--depth` `<basic\|detailed\|comprehensive>` | Breadth vs. depth of the exploration. | detailed |
+| `--options` `<n>` | Number of solution options to generate. | 3 |
+| `--agent` `<inline\|auto\|name>` | Who runs the model-bearing ideation. | inline |
+| `--skip-discovery` | Skip the discovery interview; ideate immediately. | off |
+| `--wayfind` | Spawn a wayfinder feature for multi-session routing. | off |
+| `--task` `[<feature-id>]` | Create a tracking task under a feature. | omitted |
+| `--feature` `[<parent-id>]` | Attach the result to a parent feature. | omitted |
+| `--next` | Hand off to the next-router on success. | off |
+
+For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
+
+## Usage
+
+/sp:dev-brainstorm <topic> [--depth <basic|detailed|comprehensive>] [--options <n>] [--agent <inline|auto|name>] [--skip-discovery] [--wayfind] [--task [<feature-id>]] [--feature [<parent-id>]] [--next]
+
+## Implementation
+
+- Apply the [inline-default execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface).
+- Default: `Skill(skill="sp:brainstorm", args="dev-brainstorm --context <decision-tree> --options <n>")`
+- `--wayfind`: `Skill(skill="sp:wayfinder", args="chart --destination <destination> --context <decision-tree>")`
+
+`--next`: chain-to-completion with
+propagation. Only meaningful with `--feature` (the front-half artifact exit): on a clean
+`feature check`, chain into `/sp:dev-plan --feature <ID>` so the planning half runs end-to-end.
+Ignored without `--feature` (there is no task in a lifecycle to advance). **was: `--next` declared but never defined.**

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

@@ -0,0 +1,28 @@
+---
+description: Generate changelog from git commits
+argument-hint: "[--since <tag|commit>] [--until <tag|commit>] [--version <version>]"
+allowed-tools: ["Bash", "Read"]
+---
+
+# Dev Changelog
+
+Implements an inline procedure — see [dev-operations.md](../skills/spur-dev/references/dev-operations.md#8-changelog) for the authoritative reference.
+
+## Argument Flags
+
+| Flag | Description | Default |
+| --- | --- | --- |
+| `--since` `<tag\|commit>` | Start of the commit range. | latest tag |
+| `--until` `<tag\|commit>` | End of the commit range. | HEAD |
+| `--version` `<version>` | Override the detected release version. | detected |
+
+For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
+
+## Usage
+
+/sp:dev-changelog [--since <tag|commit>] [--until <tag|commit>] [--version <version>]
+
+## Implementation
+
+Follow the inline procedure in [dev-operations.md](../skills/spur-dev/references/dev-operations.md#8-changelog) (changelog).
+

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

@@ -0,0 +1,29 @@
+---
+description: "Generate a daily summary report from agent usage data, git history, and notes"
+argument-hint: "[--date <YYYY-MM-DD>] [--dry-run] [--output <path>] [--no-git] [--no-ccusage]"
+allowed-tools: ["Bash", "Read"]
+---
+
+# Dev Daily
+
+Runs the daily-summary generator — see [daily-summary/SKILL.md](../skills/daily-summary/SKILL.md) for the authoritative procedure. `sp:daily-summary` is `disable-model-invocation`, so it cannot be fired via the Skill tool; this command runs its script directly.
+
+## Argument Flags
+
+| Flag | Description | Default |
+| --- | --- | --- |
+| `--date` `<YYYY-MM-DD>` | Report date. | today |
+| `--dry-run` | Render without writing files. | off |
+| `--output` `<path>` | Output directory for the report. | configured |
+| `--no-git` | Skip git-history aggregation. | off |
+| `--no-ccusage` | Skip ccusage aggregation. | off |
+
+For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
+
+## Usage
+
+/sp:dev-daily [--date <YYYY-MM-DD>] [--dry-run] [--output <path>] [--no-git] [--no-ccusage]
+
+## Implementation
+
+Run the generator per [daily-summary/SKILL.md](../skills/daily-summary/SKILL.md): `bun plugins/sp/scripts/daily-summary/daily-summary.ts $ARGUMENTS`.

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

@@ -0,0 +1,29 @@
+---
+description: "Systematic debugging protocol — reproduce, isolate, diagnose root cause, apply minimal fix, and verify with regression tests"
+argument-hint: "\"<symptom | failing command>\" [--scope <path>] [--task [<wbs>]] [--agent <inline|auto|name>]"
+allowed-tools: ["Bash", "Read", "Write", "Skill"]
+---
+
+# Dev Debug
+
+Wraps the **sp:sys-debugging** skill.
+
+## Argument Flags
+
+| Flag | Description | Default |
+| --- | --- | --- |
+| `"<symptom \| failing command>"` | Symptom or failing command to diagnose. | required |
+| `--scope` `<path>` | Scope the reproduction/isolation to a path. | cwd |
+| `--task` `[<wbs>]` | Attach findings to a task. | omitted |
+| `--agent` `<inline\|auto\|name>` | Who runs the model-bearing diagnosis. | inline |
+
+For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
+
+## Usage
+
+/sp:dev-debug "<symptom | failing command>" [--scope <path>] [--task [<wbs>]] [--agent <inline|auto|name>]
+
+## Implementation
+
+- Apply the [inline-default execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface).
+- `Skill(skill="sp:sys-debugging", args="$ARGUMENTS")`

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

@@ -0,0 +1,33 @@
+---
+description: Dogfood an agent skill/command/CLI — drive it end-to-end with bounded auto-fix, self-monitor, and emit a comprehensive report
+argument-hint: "<testee> [--agent <inline|auto|name>] [--max-retry <n>] [--save] [--task] [--chain-follow] [--full]"
+allowed-tools: ["Bash", "Read", "Write", "Edit", "Grep", "Glob", "Skill"]
+---
+
+# Dev Dogfood
+
+Wraps the **sp:dogfood-testing** skill.
+
+## Argument Flags
+
+| Flag | Description | Default |
+| --- | --- | --- |
+| `<testee>` | Skill / command / CLI to exercise end-to-end. | required |
+| `--agent` `<inline\|auto\|name>` | Who runs the model-bearing dogfood work. | inline |
+| `--max-retry` `<n>` | Max auto-fix retries per stage. | 3 |
+| `--save` | Compatibility no-op; saving is now default. Retained until evidenced retirement. | off |
+| `--task` | Record outcomes against a task. | omitted |
+| `--chain-follow` | Follow the testee's chained follow-ups. | off |
+| `--full` | Full report verbosity (all sections). | off |
+
+For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
+
+## Usage
+
+/sp:dev-dogfood <testee> [--agent <inline|auto|name>] [--max-retry <n>] [--save] [--task] [--chain-follow] [--full]
+
+## Implementation
+
+- Apply the [inline-default execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface).
+- `Skill(skill="sp:dogfood-testing", args="$ARGUMENTS")`
+

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

@@ -0,0 +1,130 @@
+---
+description: >-
+  Restructure the feature tree from a mapping file — dry-run then apply via
+  spur feature move / task feature_id edges / root docs/*.md reference rewrites
+  (CLI-gated; no raw Write on docs/features or docs/tasks)
+argument-hint: "[--map <path>] [--dry-run] [--apply] [--limit <old-id>] [--wave <1|2|3|all>] [--yes]"
+allowed-tools: ["Bash", "Read", "AskUserQuestion", "Skill"]
+---
+
+# Dev Featurechange
+
+CLI-gated feature-tree restructure orchestrator. Executes dispositions from a mapping file; does not invent hierarchy.
+
+## Argument Flags
+
+| Flag | Description | Default |
+| --- | --- | --- |
+| `--map` `<path>` | Feature-restructure mapping file. | configured |
+| `--dry-run` | Plan only; write nothing. | off |
+| `--apply` | Apply the planned restructure. | off |
+| `--limit` `<old-id>` | Restrict to a single old feature id. | omitted |
+| `--wave` `<1\|2\|3\|all>` | Migration wave to execute. | all |
+| `--yes` | Skip confirmation prompts. | off |
+
+For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
+
+## Usage
+
+```
+/sp:dev-featurechange [--map <path>] [--dry-run] [--apply] [--limit <old-id>] [--wave <1|2|3|all>] [--yes]
+```
+
+## Implementation
+
+**Preconditions**
+
+1. Load hierarchy rules: `Skill(skill="sp:spur-cli")` → `references/features/hierarchy-mece.md`. Refuse `merge-into` or new root letters unless the map + operator explicitly allow.
+2. Mapping file must exist (default `docs/plans/feature-tree-restructure-map.md`).
+3. Prefer a clean working tree / dedicated branch for apply.
+
+**Parse map**
+
+- Read `--map`. Collect rows where disposition is not `keep` (typically `reparent-under:<parent>`).
+- Filter by `--limit` / `--wave` if set.
+- Wave defaults from map: **1** = K→J, L→J · **2** = N→H, O→H · **3** = P→D, Q→F, R→F8.
+
+**Free-digit preflight (mandatory before dry-run report)**
+
+Group selected reparent rows by `new_parent`. For each parent:
+
+```bash
+spur feature list --json
+```
+
+Count current children (ids where `id` starts with parent and length = parent.length+1, digit 1–9).  
+`free = 9 - childCount`. If `rowsUnderParent.length > free`, **abort the plan** with a clear error naming the parent, free slots, and competing old_ids. Do not apply a partial wave.
+
+**Dry-run plan (always) — sequential prediction**
+
+Do **not** fire independent dry-runs that all claim the same next id. Walk rows **in apply order** and maintain a local occupancy set:
+
+1. Start with real children of each parent from `spur feature list --json`.
+2. For each row: run `spur feature move <old_id> --parent <new_parent> --dry-run --json` **or** predict next free digit from the occupancy set (prefer live dry-run when only one pending under that parent).
+3. After predicting `new_id`, add it to the occupancy set so the next sibling under the same parent gets the next free digit.
+4. Record `mapping` and `tasksUpdated[]` from each dry-run (with multi-folder scan, tasksUpdated should list every linked WBS).
+
+Plan `spur feature refresh` + `spur feature check --json` after apply.
+
+**Root docs/\*.md references (high-confidence only)**
+
+Scan only `docs/*.md` (docs root, not nested folders). For single-letter feature ids, **do not** use bare `\\bX\\b`. Prefer:
+
+- `feature <id>` / `feature <id>,` / `(feature <id>`
+- Feature file basename stems from INDEX
+- Markdown links to `./<id>_…md`
+
+Skip pure English uses of the letter. Do **not** rewrite `docs/features/`, `docs/tasks*/`, `plugins/`, `apps/`, `AGENTS.md` in v1.
+
+Print blast-radius table: old_id | disposition | predicted new_id | tasks | docs hits.
+
+Stop if only dry-run (or neither flag — treat as dry-run).
+
+**Confirm apply**
+
+Unless `--yes`, use `AskUserQuestion` (or explicit operator “apply”) with the blast-radius report. Abort on no.
+
+**Apply (CLI only)**
+
+Forbidden: raw Write/Edit of feature or task corpus to change IDs. Required: harness CLI.
+
+Apply rows **in the same order** as the dry-run plan:
+
+```bash
+spur feature move <old_id> --parent <new_parent> --json
+```
+
+After all moves (or per wave):
+
+```bash
+spur feature refresh --json
+spur feature check --json
+```
+
+Task edges: `feature move` rewrites `feature_id` across **all** configured task folders (via `foldersConfig`). Safety check:
+
+```bash
+rg -n '^feature_id: <old_id>$' docs/tasks docs/tasks2 docs/tasks3
+```
+
+If any stale edges remain, fix with:
+
+```bash
+spur task update <wbs> --feature <new_id> --json
+```
+
+**Report**
+
+Emit applied mapping, CLI exit codes, check summary, docs files touched, residual skips, free-digit preflight result.
+
+**merge-into (v1)**
+
+Dry-run may print a manual absorb protocol. Apply **skips** automatic body-merge.
+
+**Stretch (not required for v1)**
+
+`--json-out` dry-run report · reverse mapping rollback · `--docs-glob` override (default remains root `docs/*.md`).
+
+**Related**
+
+Map feature F31 · mapping SSOT `docs/plans/feature-tree-restructure-map.md` · hierarchy-mece.md · `spur feature move|refresh|check` · `spur task update --feature`

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

@@ -0,0 +1,51 @@
+---
+description: "Authority-aware semantic audit across source, task files, feature files, and project authority files — discover conflicts, resolve claim-specific authority, collect reproducible evidence, and route confirmed repairs through owner surfaces. Triggers: find conflict, conflict audit, semantic conflict, authority mismatch, stale projection."
+argument-hint: "[<scope>] [--pillar <source|tasks|features|authority|all>] [--mode <adaptive|full>] [--resolve] [--agent <inline|auto|name>] [--json]"
+allowed-tools: ["Bash", "Read", "Write", "Grep", "Glob", "Skill"]
+---
+
+# Dev Find Conflict
+
+Wraps the **sp:conflict-finding** skill — a prompt-first, authority-aware indexed audit across the four
+pillars (source code, task files, feature files, project authority files) with confirmed,
+owner-routed remediation.
+
+## Argument Flags
+
+| Flag                                                   | Description                                                                                                                              | Default         |
+| ------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------- | --------------- |
+| `<scope>`                                              | Optional path, WBS, feature ID, symbol, command, config key, or free-form subject to scope the audit.                                    | current project |
+| `--pillar` `<source\|tasks\|features\|authority\|all>` | Limit the internal audit to one pillar; the minimum authorities needed to judge it still load.                                           | all             |
+| `--mode` `<adaptive\|full>`                            | Scan protocol — adaptive reuses fresh indexed context and discloses skipped areas; full forces a cold comprehensive scan.                | adaptive        |
+| `--resolve`                                            | Enable the proposal, confirmation, and owner-routed remediation workflow. Its absence guarantees no source/corpus/numbered-doc mutation. | off             |
+| `--agent` `<inline\|auto\|name>`                       | Who runs the model-bearing analysis.                                                                                                     | inline          |
+| `--json`                                               | Emit the same result envelope as Markdown as JSON.                                                                                       | off             |
+
+For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
+
+## Usage
+
+```
+/sp:dev-find-conflict
+/sp:dev-find-conflict docs/00_ADR.md
+/sp:dev-find-conflict --pillar authority
+/sp:dev-find-conflict --pillar tasks --mode full
+/sp:dev-find-conflict 0486 --resolve
+/sp:dev-find-conflict "command surface" --json
+```
+
+Audit mode is read-only with respect to source, corpus, and numbered documentation. Findings are
+presented before any repair. Approved repairs route through the artifact owner's existing harness
+surface (`spur task` / `spur feature`, `sp:doc-evolve`, the Spur development lifecycle, or
+Superskill capability lifecycle) — never direct writes.
+
+**See also:** skill `sp:conflict-finding` (SSOT), `sp:doc-evolve`, `sp:spur-cli`,
+`sp:code-verification`.
+
+## Implementation
+
+Apply the [inline-default execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface), then invoke the conflict-finding skill, forwarding all arguments:
+
+```
+Skill(skill="sp:conflict-finding", args="$ARGUMENTS")
+```

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

@@ -0,0 +1,76 @@
+---
+description: "Review agent session logs, identify performance bottlenecks and behavioral anti-patterns, and generate a structured task file with proposed fixes. Triggers: post-mortem, performance analysis, session review, find issues, identify bottlenecks"
+argument-hint: "[<topic>] [--sessions <glob>] [--source <auto|omp|claude|codex|gemini|opencode|antigravity|openclaw|pi>] [--feature <id>] [--template <meta|issue|standard>] [--priority <P0|P1|P2|P3>] [--severity <S0|S1|S2>] [--category <list>] [--since <iso>] [--until <iso>] [--top <n>] [--min-cost <duration>] [--strict-topic] [--use-history] [--no-task] [--agent <inline|auto|name>] [--json]"
+allowed-tools: ["Bash", "Read", "Write", "Grep", "Glob", "Skill"]
+---
+
+# Dev Find Issue
+
+Wraps the **sp:issue-finding** skill — forensic session log analysis that identifies performance
+bottlenecks, ranks root causes by time cost, proposes targeted fixes, and generates a structured
+task file via `spur task create`.
+
+## Argument Flags
+
+| Flag                                                                                 | Description                          | Default    |
+| ------------------------------------------------------------------------------------ | ------------------------------------ | ---------- |
+| `[<topic>]`                                                                          | Narrow the analysis to a topic.      | omitted    |
+| `--sessions` `<glob>`                                                                | Session log glob to scan.            | recent     |
+| `--source` `<auto\|omp\|claude\|codex\|gemini\|opencode\|antigravity\|openclaw\|pi>` | Agent source to scan.                | auto       |
+| `--feature` `<id>`                                                                   | Attach findings to a feature.        | omitted    |
+| `--template` `<meta\|issue\|standard>`                                               | Output template shape.               | standard   |
+| `--priority` `<P0\|P1\|P2\|P3>`                                                      | Filter / assign priority.            | omitted    |
+| `--severity` `<S0\|S1\|S2>`                                                          | Filter / assign severity.            | omitted    |
+| `--category` `<list>`                                                                | Comma list of categories to keep.    | all        |
+| `--since` `<iso>`                                                                    | Start of the scan window.            | configured |
+| `--until` `<iso>`                                                                    | End of the scan window.              | now        |
+| `--top` `<n>`                                                                        | Limit to top N findings.             | omitted    |
+| `--min-cost` `<duration>`                                                            | Minimum wasted duration to report.   | omitted    |
+| `--strict-topic`                                                                     | Drop findings off-topic.             | off        |
+| `--use-history`                                                                      | Incorporate indexed history.         | off        |
+| `--no-task`                                                                          | Do not create a task for findings.   | off        |
+| `--agent` `<inline\|auto\|name>`                                                     | Who runs the model-bearing analysis. | inline     |
+| `--json`                                                                             | Emit structured JSON.                | off        |
+
+For shared semantics, see the [flag glossary](../skills/spur-dev/references/flag-glossary.md).
+
+## Usage
+
+```
+/sp:dev-find-issue
+/sp:dev-find-issue "test-loop spinning"
+/sp:dev-find-issue --sessions "~/.omp/agent/sessions/-xprojects-spur-new/2026-07-29T*"
+/sp:dev-find-issue "L3 guard format discovery" --feature H51 --priority P1 --severity S1
+/sp:dev-find-issue --category test-loop,guard --min-cost 30m --no-task
+/sp:dev-find-issue --source claude --since 2026-07-28 --json
+/sp:dev-find-issue --sessions plugins/sp/skills/issue-finding/examples/session-test-loop.jsonl --no-task
+```
+
+| Argument                      | Description                                                                              | Default                         |
+| ----------------------------- | ---------------------------------------------------------------------------------------- | ------------------------------- |
+| `[topic]`                     | Optional focus text or smart positional (path/glob → sessions; category phrase → filter) | (full taxonomy)                 |
+| `--sessions <glob>`           | Session JSONL file(s) or directory                                                       | most recent for resolved source |
+| `--source <name>`             | `auto`, `omp`, `claude`, `codex`, `gemini`, `opencode`, `antigravity`, `openclaw`, `pi`  | `auto`                          |
+| `--feature <id>`              | Feature ID to link the generated task to                                                 | (none)                          |
+| `--template <name>`           | `meta` (umbrella), `issue` (single), or `standard`                                       | `meta`                          |
+| `--priority <P0\|P1\|P2\|P3>` | Task frontmatter priority (not bottleneck severity)                                      | `P2`                            |
+| `--severity <S0\|S1\|S2>`     | Minimum bottleneck severity to keep                                                      | (all)                           |
+| `--category <list>`           | Comma-separated category ids (`test-loop`, `guard`, …)                                   | `all`                           |
+| `--since` / `--until`         | Session start time bounds                                                                | (none)                          |
+| `--top <n>`                   | Cap number of fixes/requirements                                                         | (no cap)                        |
+| `--min-cost <duration>`       | Drop findings under this waste floor (`30m`, `2h`)                                       | (none)                          |
+| `--strict-topic`              | Drop off-topic findings even if severe                                                   | off                             |
+| `--use-history`               | Optional `spur history` import/analyze for cost aggregates                               | off                             |
+| `--no-task`                   | Markdown report only                                                                     | off                             |
+| `--json`                      | JSON findings only (no task)                                                             | off                             |
+
+**See also:** skill `sp:issue-finding` (SSOT), `/sp:dev-runall`, `/sp:dev-dogfood`,
+`sp:daily-summary`, `sp:reverse-engineering`.
+
+## Implementation
+
+Apply the [inline-default execution-surface contract](../skills/spur-dev/references/cross-cutting.md#inline-default-execution-surface), then invoke the issue-finding skill, forwarding all arguments:
+
+```
+Skill(skill="sp:issue-finding", args="$ARGUMENTS")
+```