claude-dev-env 8.15.0 → 8.16.0

package/.agents/agents/test_agent_frontmatter.py

@@ -518,76 +518,6 @@ EXPECTED_SOURCE_LINK_PAIRS = {
             "packages/claude-dev-env/rules/workers-done-before-complete.md",
         ),
     }),
-    "code-quality-agent.md": frozenset({
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-a-api-contracts.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-a-api-contracts.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-b-selector-engine-compat.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-b-selector-engine-compat.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-c-resource-cleanup.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-c-resource-cleanup.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-d-scoping-and-ordering.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-d-scoping-and-ordering.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-e-dead-code.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-e-dead-code.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-f-silent-failures.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-f-silent-failures.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-g-bounds-and-overflow.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-g-bounds-and-overflow.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-h-security-boundaries.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-h-security-boundaries.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-i-concurrency.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-i-concurrency.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-j-code-rules-compliance.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-j-code-rules-compliance.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-k-codebase-conflicts.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-k-codebase-conflicts.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-l-behavior-equivalence.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-l-behavior-equivalence.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-m-producer-consumer-cardinality.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-m-producer-consumer-cardinality.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-n-test-name-scenario-verifier.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-n-test-name-scenario-verifier.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-o-docstring-vs-impl-drift.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-o-docstring-vs-impl-drift.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-p-name-vs-behavior-contract.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-p-name-vs-behavior-contract.md",
-        ),
-        (
-            "<managed-root>/audit-rubrics/category_rubrics/category-q-cross-surface-claims.md",
-            "packages/claude-dev-env/audit-rubrics/category_rubrics/category-q-cross-surface-claims.md",
-        ),
-    }),
     "pr-description-writer.md": frozenset({
         (
             "<agents-home>/agents/reference/pr-description-illustrative-voice.md",
@@ -627,7 +557,6 @@ def test_named_agents_document_installed_paths_and_source_fallbacks() -> None:
     agents_directory = Path(__file__).parent.parent / "agents-archived"
     for each_agent_file_name in (
         "clean-coder.md",
-        "code-quality-agent.md",
         "pr-description-writer.md",
     ):
         agent_text = (agents_directory / each_agent_file_name).read_text(
@@ -690,7 +619,6 @@ def test_named_agents_resolve_active_managed_root_and_agents_home() -> None:
     agents_directory = Path(__file__).parent.parent / "agents-archived"
     for each_agent_file_name in (
         "clean-coder.md",
-        "code-quality-agent.md",
         "pr-description-writer.md",
     ):
         agent_text = (agents_directory / each_agent_file_name).read_text(

package/.agents/agents-archived/code-quality-agent.md

@@ -77,23 +77,23 @@ For each category's full description, examples, sub-bucket decomposition, and co
 
 | Letter | Category | Reference file |
 |---|---|---|
-| A | API contract verification | `<managed-root>/audit-rubrics/category_rubrics/category-a-api-contracts.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-a-api-contracts.md`) |
-| B | Selector / query / engine compatibility | `<managed-root>/audit-rubrics/category_rubrics/category-b-selector-engine-compat.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-b-selector-engine-compat.md`) |
-| C | Resource cleanup and lifecycle | `<managed-root>/audit-rubrics/category_rubrics/category-c-resource-cleanup.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-c-resource-cleanup.md`) |
-| D | Variable scoping, ordering, and unbound references | `<managed-root>/audit-rubrics/category_rubrics/category-d-scoping-and-ordering.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-d-scoping-and-ordering.md`) |
-| E | Dead code and unused imports | `<managed-root>/audit-rubrics/category_rubrics/category-e-dead-code.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-e-dead-code.md`) |
-| F | Silent failures | `<managed-root>/audit-rubrics/category_rubrics/category-f-silent-failures.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-f-silent-failures.md`) |
-| G | Off-by-one, bounds, integer overflow | `<managed-root>/audit-rubrics/category_rubrics/category-g-bounds-and-overflow.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-g-bounds-and-overflow.md`) |
-| H | Security boundaries | `<managed-root>/audit-rubrics/category_rubrics/category-h-security-boundaries.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-h-security-boundaries.md`) |
-| I | Concurrency hazards | `<managed-root>/audit-rubrics/category_rubrics/category-i-concurrency.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-i-concurrency.md`) |
-| J | CODE_RULES.md compliance | `<managed-root>/audit-rubrics/category_rubrics/category-j-code-rules-compliance.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-j-code-rules-compliance.md`) |
-| K | Codebase conflicts (incomplete propagation) | `<managed-root>/audit-rubrics/category_rubrics/category-k-codebase-conflicts.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-k-codebase-conflicts.md`) |
-| L | Behavior-equivalence for refactors | `<managed-root>/audit-rubrics/category_rubrics/category-l-behavior-equivalence.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-l-behavior-equivalence.md`) |
-| M | Producer/consumer cardinality vs collection-type contract | `<managed-root>/audit-rubrics/category_rubrics/category-m-producer-consumer-cardinality.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-m-producer-consumer-cardinality.md`) |
-| N | Test-name scenario verifier | `<managed-root>/audit-rubrics/category_rubrics/category-n-test-name-scenario-verifier.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-n-test-name-scenario-verifier.md`) |
+| A | API contract verification | `<managed-root>/audit-rubrics/category_rubrics/category-a-api-contracts.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-a-api-contracts.md`) |
+| B | Selector / query / engine compatibility | `<managed-root>/audit-rubrics/category_rubrics/category-b-selector-engine-compat.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-b-selector-engine-compat.md`) |
+| C | Resource cleanup and lifecycle | `<managed-root>/audit-rubrics/category_rubrics/category-c-resource-cleanup.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-c-resource-cleanup.md`) |
+| D | Variable scoping, ordering, and unbound references | `<managed-root>/audit-rubrics/category_rubrics/category-d-scoping-and-ordering.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-d-scoping-and-ordering.md`) |
+| E | Dead code and unused imports | `<managed-root>/audit-rubrics/category_rubrics/category-e-dead-code.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-e-dead-code.md`) |
+| F | Silent failures | `<managed-root>/audit-rubrics/category_rubrics/category-f-silent-failures.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-f-silent-failures.md`) |
+| G | Off-by-one, bounds, integer overflow | `<managed-root>/audit-rubrics/category_rubrics/category-g-bounds-and-overflow.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-g-bounds-and-overflow.md`) |
+| H | Security boundaries | `<managed-root>/audit-rubrics/category_rubrics/category-h-security-boundaries.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-h-security-boundaries.md`) |
+| I | Concurrency hazards | `<managed-root>/audit-rubrics/category_rubrics/category-i-concurrency.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-i-concurrency.md`) |
+| J | CODE_RULES.md compliance | `<managed-root>/audit-rubrics/category_rubrics/category-j-code-rules-compliance.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-j-code-rules-compliance.md`) |
+| K | Codebase conflicts (incomplete propagation) | `<managed-root>/audit-rubrics/category_rubrics/category-k-codebase-conflicts.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-k-codebase-conflicts.md`) |
+| L | Behavior-equivalence for refactors | `<managed-root>/audit-rubrics/category_rubrics/category-l-behavior-equivalence.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-l-behavior-equivalence.md`) |
+| M | Producer/consumer cardinality vs collection-type contract | `<managed-root>/audit-rubrics/category_rubrics/category-m-producer-consumer-cardinality.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-m-producer-consumer-cardinality.md`) |
+| N | Test-name scenario verifier | `<managed-root>/audit-rubrics/category_rubrics/category-n-test-name-scenario-verifier.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-n-test-name-scenario-verifier.md`) |
 | O | Docstring / fixture-prose vs implementation drift | `<managed-root>/audit-rubrics/category_rubrics/category-o-docstring-vs-impl-drift.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-o-docstring-vs-impl-drift.md`) |
-| P | Name / regex / word-list vs behavior-contract precision | `<managed-root>/audit-rubrics/category_rubrics/category-p-name-vs-behavior-contract.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-p-name-vs-behavior-contract.md`) |
-| Q | Cross-surface claim consistency (terminology, PR-description claims, message-vs-guard) | `<managed-root>/audit-rubrics/category_rubrics/category-q-cross-surface-claims.md` (source fallback: `packages/claude-dev-env/audit-rubrics/category_rubrics/category-q-cross-surface-claims.md`) |
+| P | Name / regex / word-list vs behavior-contract precision | `<managed-root>/audit-rubrics/category_rubrics/category-p-name-vs-behavior-contract.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-p-name-vs-behavior-contract.md`) |
+| Q | Cross-surface claim consistency (terminology, PR-description claims, message-vs-guard) | `<managed-root>/audit-rubrics/category_rubrics/category-q-cross-surface-claims.md` (source fallback: `packages/claude-dev-env/audit-rubrics-archived/category_rubrics/category-q-cross-surface-claims.md`) |
 
 Test files use the same no-new-comment policy. The exempt path families documented in the J reference still opt out of the constants-location sub-item.
 

package/.agents/skills/_shared/end-of-run-gotcha-recommendations.md

@@ -25,11 +25,11 @@ Keep only items that **bit this run**:
 
 ## What to produce
 
-**Order (hard):**
+**Order:**
 
 1. Show findings in chat; categorize as P0-P3.
 2. Then `AskUserQuestion`.
-3. On confirm only, ask `pstack:poteto-agent` to load `issue-tracker` and file the issue.
+3. On confirm only, load `issue-tracker` and file the issue.
 
 ### Cold-reader frame
 
@@ -42,7 +42,7 @@ Assume zero context.
 
 ### 1. Chat findings (always first)
 
-#### Sentence law (HARD)
+#### Sentence law
 
 | Rule | Required |
 |---|---|
@@ -53,11 +53,7 @@ Assume zero context.
 | **One idea** | If you can split it, split it |
 | **Heavy detail** | Prefer an **ASCII infographic** over a stack of sentences |
 
-**Self-check before send:** paste the chat into a viewer that collapses soft breaks.
-
-If two periods appear on one visual line, **split or diagram**.
-
-#### Per gotcha (HARD shape)
+#### Per gotcha shape
 
 | Part | Form |
 |---|---|
@@ -126,24 +122,12 @@ Only after the chat block.
 
 Detail and ASCII stay in chat.
 
-**On confirm:** ask `pstack:poteto-agent` to load `issue-tracker` and file the issue.
+**On confirm:** load `issue-tracker` and file the issue.
 
 Cold-reader issue body.
 
 Clean run: skip.
 
-## Built-in skill gotcha
-
-**Two sentences on one rendered line.**
-
-Markdown soft-breaks join prose.
-
-Review the close-out before send.
-
-Split with a blank line or a list item.
-
-Or move the detail into an ASCII infographic.
-
 ## Rules
 
 - Cold-reader first.

package/.agents/skills/e-code-review/SKILL.md

@@ -3,9 +3,7 @@ name: e-code-review
 description: >-
   Code review at one of five effort levels that match the built-in
   /code-review recipes step for step: low, medium, high, xhigh, max.
-  Triggers: /e-code-review, /e-code-review low, /e-code-review medium,
-  /e-code-review high, /e-code-review xhigh, /e-code-review max, and any
-  level with --fix.
+  Triggers: /e-code-review with an optional level and an optional --fix.
 ---
 
 # e-code-review

package/.agents/skills/e-simplify/SKILL.md

@@ -8,7 +8,7 @@ description: >-
 
 # e-simplify
 
-**Core principle:** Four parallel cleanup angles (reuse, simplification, efficiency, altitude) over the current diff, applied directly — not a bug hunt, and not a report.
+**Core principle:** Four cleanup angles (reuse, simplification, efficiency, altitude) over the current diff, applied directly — not a bug hunt, and not a report.
 
 ## Gotchas
 
@@ -25,7 +25,7 @@ Triggers: `/e-simplify` on the current diff (or a PR/branch/path passed as an ar
 
 ## The process
 
-`/simplify → up to 4 cleanup agents in parallel → apply the fixes`
+`/simplify → 4 cleanup angles in this context → apply the fixes`
 
 You are improving the quality of the changed code, not hunting for bugs. Review
 it for reuse, simplification, efficiency, and altitude issues, then fix what you
@@ -40,10 +40,10 @@ include the working-tree changes in scope — the review often runs before the
 commit. If a PR number, branch name, or file path was passed as an argument,
 review that target instead. Treat this diff as the review scope.
 
-### Phase 1 — Review (up to 4 cleanup agents in parallel)
+### Phase 1 — Review (four cleanup angles, in this context)
 
-Launch all four review agents via the Agent tool in one message so they run concurrently. Pass each agent the diff and one angle below. Each
-returns its findings with `file`, `line`, a one-line `summary`, and the
+Run the four angles below yourself, in sequence, in this context. Each angle
+yields findings with `file`, `line`, a one-line `summary`, and the
 concrete cost (what is duplicated, wasted, or harder to maintain).
 
 #### Reuse
@@ -77,7 +77,7 @@ special cases.
 
 ### Phase 2 — Apply the fixes
 
-Wait for every launched agent to complete, dedup findings that point at the same
+Pool the findings from all four angles, dedup findings that point at the same
 line or mechanism, and fix each remaining one directly. Skip any finding whose
 fix would change intended behavior, require changes well outside the reviewed
 diff, or that you judge to be a false positive — note the skip rather than

package/.agents/skills/eli5/SKILL.md

@@ -39,11 +39,6 @@ capability-specific artifact. Raw tool output, machine payloads, code, and
 native repository artifacts retain their required formats. Present their human
 explanation inside the HTML presentation envelope when the response is user-facing.
 
-### First-match refusal condition
-
-Evaluate this condition before task seeding. When no task tool is available,
-reply exactly: `ELI5 requires a session task tool. The artifact flow is paused.`
-
 ## Skill classification
 
 **Dominant type:** Business Process & Team Automation.
@@ -83,11 +78,9 @@ keep ownership of their native artifact rules while ELI5 supplies the global
 
 ## Task seeding
 
-At skill start, register every item in `reference/task-seeds.md` as a session
-task through `TaskCreate`, `TodoWrite`, or the host task equivalent. Work from
-that task list. Mark each item complete with `PASS`, `FAIL` plus file evidence,
-or `N/A` plus the reason. When no task tool is available, use the exact refusal
-under [When this applies](#when-this-applies) before authoring the artifact.
+When the session exposes a task tool, register the items in
+`reference/task-seeds.md` as session tasks. Otherwise work through the
+Process steps in order.
 
 ## Process
 
@@ -99,10 +92,7 @@ under [When this applies](#when-this-applies) before authoring the artifact.
    `~/.claude/rules/asd-ste100-language.md` to every sentence. Frame the topic
    for a beginner, use a large useful visual, keep the text minimal, and update
    the same artifact in place.
-3. **Judgment — share the updated artifact with the user.** Review technical meaning,
-   terminology, safety, confidentiality, accessibility, browser readiness, and
-   visual legibility. When a check reports a defect, repair the artifact, repeat
-   the review, and share after all checks pass.
+3. **Judgment — share the updated artifact with the user.**
 
 ### Examples
 

package/.agents/skills/eli5/reference/task-seeds.md

@@ -1,11 +1,10 @@
 # ELI5 task seeds
 
-Register each item as a session task at the start of the ELI5 process. Complete
-each task with `PASS`, `FAIL` plus file evidence, or `N/A` plus the reason.
+When the session exposes a task tool, register each item as a session task at
+the start of the ELI5 process.
 
 1. Resolve the active HTML artifact path and preserve the stable path.
 2. Create the artifact when no active path exists and keep it self-contained.
 3. Apply the ASD-STE100 rule to page and response sentences.
 4. Add the concise beginner explanation and useful large visual in place.
-5. Review accuracy, terminology, safety, confidentiality, accessibility, and legibility.
-6. Share the updated artifact with the user.
+5. Share the updated artifact with the user.

package/.agents/skills/everything-search/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: everything-search
-description: Fast file search on Windows using Everything (voidtools) es.exe command-line tool. Use when searching for files by extension, name, date modified, size, or path. Triggers on "find files", "search for files", "locate files", or when user asks to use Everything.
+description: Fast file search on Windows using Everything (voidtools) es.exe command-line tool. Use when searching for files by extension, name, date modified, size, or path, or when the user asks to use Everything.
 ---
 
 # Everything Search
@@ -43,7 +43,7 @@ Path and operator searches run when the registry file is missing. Malformed regi
 **Path (Windows):** `"C:/Program Files/Everything/es.exe"`
 
 Syntax:
-- Search terms are SPACE-SEPARATED, not quoted together
+- Separate search terms with spaces. Quotes hold one exact filename or path; a quoted group of terms breaks parsing.
 - When searching a path, use backslashes inside quotes: `"Y:\\path\\to\\folder"`
 
 ```bash

package/.agents/skills/fresh-branch/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: fresh-branch
 description: >-
-  Fresh git branch from origin/main in an isolated worktree under a configured root (default: <repo>/.claude/worktrees/<agent>/; never checkout -b in the caller tree).
-  Triggers: fresh branch, new branch from main, /fresh-branch, start fresh, clean branch off main,
-  worktree branch, branch in temp.
+  Fresh git branch from origin/main in an isolated worktree under a configured root, leaving the caller's tree untouched.
+  Use when the user or a calling skill needs a new branch off main.
 ---
 
 # fresh-branch

package/.agents/skills/grok-spawn/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: grok-spawn
 description: >-
-  Spawn headless grok worker fleets via preflight and spawn_grok_batch.
-  Triggers: /grok-spawn, spawn grok workers, grok worker fleet, run this with
-  grok workers, headless grok batch.
+  Spawn headless grok worker fleets via preflight and spawn_grok_batch. Use
+  when the user asks to run work on a fleet or batch of headless grok workers.
 ---
 
 # Grok Spawn
@@ -46,8 +45,6 @@ Good fits:
 - Claude-only tools (Agent tool, warm advisor, Claude MCP surfaces the
   grok CLI does not load the same way)
 
-For a single interactive Grok Build handoff paste, use `/grokify` instead.
-
 **Refusal:** no concrete worker tasks — reply `What should the grok workers do?
 List each role in one line.` and stop.
 
@@ -220,8 +217,6 @@ Build workers stop at stage-ready edits and a written report. They do not run
 | `spawn_grok_batch.py` | Batch launch, stagger, report collect |
 | `grok_headless_runner.py` | One-worker runner (called by the batch launcher) |
 
-Sibling skill: `/grokify` for a single paste-ready interactive Grok Build handoff.
-
 ## File index
 
 | File | Purpose |
@@ -238,4 +233,4 @@ Sibling skill: `/grokify` for a single paste-ready interactive Grok Build handof
 
 ## Worker advisors
 
-Each grok worker binds a unique Opus-high dvisor_session_id through the lead-supplied dvisor.launcher in the batch spec (committed default is a placeholder). Reports require the same handle\'s ENDORSE (or bounded CORRECTION/PLAN then ENDORSE); STOP or malformed signals end as advisor_blocked.
+Each grok worker binds a unique Opus-high `advisor_session_id` through the lead-supplied `advisor.launcher` in the batch spec (the committed default is a placeholder). Reports require the same handle's ENDORSE (or bounded CORRECTION/PLAN then ENDORSE); STOP or malformed signals end as `advisor_blocked`.

package/.agents/skills/issue-tracker/SKILL.md

@@ -1,11 +1,9 @@
 ---
 name: issue-tracker
 description: >-
-  File, update, and close GitHub work as one epic with native sub-issues.
-  Dedup open and closed issues first. Edit status only inside marker sections.
-  Refresh the epic checklist so it matches its children. Triggers: issue tracker,
-  file an issue, track this issue, open an epic, update the epic, close the issue,
-  refresh the epic checklist, attach a sub-issue.
+  File, update, and close GitHub work as one epic with native sub-issues. Use
+  when the user asks to file, track, update, or close a GitHub issue, or to open,
+  update, or refresh an epic and its sub-issues.
 argument-hint: "[issue action - file | update | close | refresh-epic | full handoff]"
 ---
 
@@ -15,7 +13,7 @@ argument-hint: "[issue action - file | update | close | refresh-epic | full hand
 
 **dedup -> do the work -> markers only -> numbers + URLs**
 
-Run every step the ask needs in one go (file, label, attach, refresh, and so on). `pstack:poteto-agent` is the primary handler for one action per turn when it loads this skill; this skill is the session path when the agent is unavailable or the ask spans several steps.
+Run every step the ask needs in one go (file, label, attach, refresh, and so on).
 
 Prefer the **same warm** `pstack:poteto-agent` for follow-ups on the same issue or a related issue on the same epic. Spawn a new agent only for an unrelated work-stream or when the warm agent is gone.
 

package/.agents/skills/orchestrator-refresh/SKILL.md

@@ -1,11 +1,9 @@
 ---
 name: orchestrator-refresh
 description: >-
-  Re-assert orchestrator discipline on a one-shot delayed wake: ledger
-  reconcile, executor consult routing to this session, warm executor
-  reuse, single-pending re-arm via status_gate. Terminates when the
-  gate says stop. Triggers: '/orchestrator-refresh', orchestrator-refresh,
-  refresh the orchestrator loop, re-arm orchestrator.
+  Refresh a running orchestrator loop when its one-shot delayed wake fires,
+  or when the user asks to refresh or re-arm the orchestrator. Terminates
+  when the status gate says stop.
 ---
 
 # Orchestrator Refresh
@@ -65,13 +63,15 @@ reports and adds nothing further.
 
 ## Discipline steps
 
-1. **Reconcile the task ledger first.** Call `TaskList` after the gate.
+1. **Reconcile the task ledger first.** Read the ledger after the gate.
+   Use `TaskList` when the host exposes task tools, and the file-backed
+   `scripts/grok_run_ledger.py` ledger the orchestrator skill names otherwise.
    The ledger is stale when any of these holds: a running or finished
    executor has no `in_progress` task naming it as owner; a finished
    executor's task is still open (or was closed without its result
    merged); the next phase you will dispatch has no pending task; a
    `blockedBy` link contradicts the run order. Fix every mismatch
-   with TaskCreate / TaskUpdate in this same firing — never defer.
+   in that same ledger during this firing.
 2. **You are the orchestrator.** Orchestrate and hold the user
    conversation; spawn executor subagents for every code edit and build
    or test run.

package/.agents/skills/plugin-eval-standalone-skill/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: plugin-eval-standalone-skill
 description: >-
-  Run `claude plugin eval` against a standalone skill that is not a plugin, by wrapping the skill in a plugin folder, writing trigger and must-not-trigger cases, and reading the with-skill minus without-skill delta. Triggers: eval a skill, plugin eval, claude plugin eval, test my skill, skill eval, eval a standalone skill.
+  Run `claude plugin eval` against a standalone skill that is not a plugin, by wrapping the skill in a plugin folder, writing trigger and must-not-trigger cases, and reading the with-skill minus without-skill delta. Use when the user asks to eval or test a skill.
 ---
 
 # Plugin eval for a standalone skill
@@ -54,8 +54,8 @@ behavior. It needs Claude Code 2.1.269 or later. Source doc: https://code.claude
 
 ## Process
 
-Register one session task per numbered step through the host task tool. Use `TaskCreate`, else
-`TodoWrite`. Where the host has no task tool, say so and work the steps in order.
+When the host exposes a task tool, register one session task per numbered step.
+Otherwise work the steps in order.
 
 1. Run `claude --version` and confirm 2.1.269 or later.
 2. Create the wrapper folder outside every skills directory:

package/.agents/skills/privacy-hygiene/SKILL.md

@@ -1,20 +1,20 @@
 ---
 name: privacy-hygiene
-description: Full-repo sweep for personal data and secrets before commit or durable GitHub post. Use when preparing a PR or cleaning a leak. Triggers on "privacy hygiene", "personal data", "secret sweep", "sanitize repository", "/privacy-hygiene".
+description: Full-repo sweep for personal data and secrets before commit or durable GitHub post. Use when preparing a PR, cleaning a leak, or when the user asks for a privacy or secret sweep of a repository.
 ---
 
 # privacy-hygiene
 
 ## Overview
 
-Find and remove personal data and high-confidence secrets before they land in git history or a durable GitHub post. No write-time hook scans for these; `pii_prevention_blocker` was retired. This skill is the sweep.
+Find and remove personal data and high-confidence secrets before they land in git history or a durable GitHub post. No write-time hook scans for these. This skill is the sweep.
 
 **Announce at start:** "Running privacy-hygiene sweep."
 
 ## When to run a full sweep
 
 - Before the first push of a branch that touched logs, screenshots, config samples, or machine-local paths
-- After a hook block on email, home path, LAN address, or secret material
+- After a `tracked-secrets` or gitleaks finding on email, home path, LAN address, or secret material
 - Before opening a PR to a repository that is public (or will be made public)
 - After pasting support tickets, env dumps, or terminal transcripts into the tree
 
@@ -29,10 +29,8 @@ Find and remove personal data and high-confidence secrets before they land in gi
 
 Surfaces:
 
-1. **Write / Edit / MultiEdit** — payload text about to land on disk (via PreToolUse dispatcher)
-2. **Durable posts** — `gh pr/issue create|comment|edit|review` bodies and GitHub MCP body/comment fields (Bash and PowerShell)
-3. **git commit** — staged blob text (non-exempt paths) on Bash and PowerShell, including `git.exe` and flag forms (`--no-verify`, `-c`, `-C`). Commit message bodies (`-m` / `-F`) are out of scope for the automated gate
-4. **CI** — the `committed-tree` job in `.github/workflows/ci-tests.yml` runs [gitleaks](https://github.com/gitleaks/gitleaks) over every commit the pull request adds, test files included. The repository-root `.gitleaks.toml` adds three rules to the gitleaks defaults: a user folder path that names a person, an RFC 1918 address, and an email other than a noreply or example address. To clear a fixture that must stay, add its gitleaks fingerprint to `.gitleaksignore`
+1. **Committed tree.** `scripts/repository_policy.py` runs its `tracked-secrets` check over every tracked file with this scanner, and CI runs the same command
+2. **CI** — the `committed-tree` job in `.github/workflows/ci-tests.yml` runs [gitleaks](https://github.com/gitleaks/gitleaks) over every commit the pull request adds, test files included. The repository-root `.gitleaks.toml` adds three rules to the gitleaks defaults: a user folder path that names a person, an RFC 1918 address, and an email other than a noreply or example address. To clear a fixture that must stay, add its gitleaks fingerprint to `.gitleaksignore`
 
 ## Sweep procedure
 
@@ -52,17 +50,15 @@ cd packages/claude-dev-env
 node bin/install.mjs
 ```
 
-Hooks register via `hooks/hooks.json` into `~/.claude/settings.json`. Once installed, the same gates apply in every repository the agent touches — private or public.
+Once installed, this skill is available in every repository the agent touches, private or public. No installed hook scans a write, a commit, or a post.
 
 ## Open knobs
 
 - **NAS / LAN allowlist:** Unlisted private IPs are blocked. The scanner resolves your NAS host from `CLAUDE_NAS_HOST`, then `~/.claude/local-identity.json` (`nas.host`), and allowlists it when it is a private address, so the committed tree holds no host address. `ALL_ALLOWLISTED_PRIVATE_IP_ADDRESSES` in `hooks_constants` holds the static allowlist for any host every machine must share.
-- **Commit-scan exempt repositories:** named owner/repo slugs skip the staged-commit PII scan only. Set `CLAUDE_PII_EXEMPT_REPOS` (comma-separated `owner/repo` values) or list them under `pii_exempt_repositories` in `~/.claude/local-identity.json`. Matching uses the repository's `remote.origin.url` and accepts only the exact host `github.com` (https, ssh scheme, or scp-style). A repository with no readable origin is never exempt (fail-closed to scanning). Write / Edit / MultiEdit and durable post bodies still scan in every repository.
 - **Public maintainer identity:** when an email or name is intentional product surface, keep it and note that in the PR body so reviewers do not treat it as a leak.
 
 ## What this skill does not do
 
 - Does not rewrite git history without explicit user approval
 - Does not rotate credentials for you
-- Does not replace the write-time hook — it complements it
 - Does not scan commit-message text (`-m` / `-F`); keep messages free of secrets yourself

package/.agents/skills/privacy-hygiene/reference/sweep-procedure.md

@@ -49,7 +49,7 @@ Review each hit. Ignore:
 
 - Stage only clean files
 - Prefer `--body-file` for `gh` posts (also required by the gh-cli-conventions rule)
-- No hook re-scans the next Write, commit, or post; `pii_prevention_blocker` was retired. Re-run this sweep before the next commit or post.
+- No hook re-scans the next Write, commit, or post. Re-run this sweep before the next commit or post.
 
 ## Accepted residual (do not over-scrub)
 

package/.agents/skills/pull-request/SKILL.md

@@ -1,9 +1,9 @@
 ---
 name: pull-request
 description: >-
-  Validate and publish GitHub pull request actions. Triggers: create PR, open
-  pull request, edit PR, update PR body, comment on PR, review PR, publish a
-  draft PR, scoped GitHub author.
+  Validate and publish GitHub pull request actions. Use when the user asks to
+  create, edit, comment on, or review a pull request, including under a
+  selected GitHub author.
 ---
 
 # Pull request
@@ -38,9 +38,9 @@ Use this skill for one pull request action:
 - Submit a pull request review.
 - Recover one selected legacy author record before the action.
 
-Send issue create, edit, and comment work to `pstack:poteto-agent` with the
-`issue-tracker` skill and one action. Send review and fix-loop work to
-`e-code-review`. Send commits to `source-command-commit`.
+Send issue create, edit, and comment work to the `issue-tracker` skill, one
+action at a time. Send review and fix-loop work to `e-code-review`. Make
+commits and pushes with Git directly.
 
 Require one repository and one action target. Stop before author lookup or
 network work when the repository, pull request, action, author, or required
@@ -49,7 +49,7 @@ local file is missing or ambiguous.
 Use these exact refusal responses when the request belongs to another skill:
 
 - Issue action: `Use issue-tracker for this GitHub issue action.`
-- Commit or push: `Use source-command-commit for this commit or push.`
+- Commit or push: `Use Git directly for this commit or push.`
 - Missing target: `Provide one repository and one pull request action target.`
 
 ## Constraints
@@ -76,17 +76,14 @@ current process environment.
 |---|---|---|---|
 | `pstack:poteto-agent` with `pull-request` instructions | Create or a full body rewrite, when you want the body drafted for you | A reviewed title and body file | Write the title and body yourself |
 | `privacy-hygiene` | Before any durable GitHub post | A clean body and repository privacy sweep | Stop before publication and report the missing gate |
-| `pstack:poteto-agent` with `issue-tracker` | Issue create, edit, or comment requests | Issue state and issue URLs | Load the skill in this session. |
+| `issue-tracker` | Issue create, edit, or comment requests | Issue state and issue URLs | Route the request there. |
 | `e-code-review` | Review or review/fix loop requests | Structured findings or a clean review result | Route the request there. |
-| `source-command-commit` | Commit or push requests | A verified commit or pushed branch | Route the request there. |
 
 ## Task seeding
 
-At the start of the work, register every item in
-`reference/publication-tasks.md` through `TaskCreate`, `TodoWrite`, or the host
-task equivalent when one is available. If no task tool is available, use the
-catalog and the running work ledger. Mark each task with `PASS`, `FAIL` plus
-file and line evidence, or `N/A` plus a reason for a conditional task.
+When the session exposes a task tool, register the items in
+`reference/publication-tasks.md` as session tasks. Otherwise work through the
+Process steps in order.
 
 ## Process
 

package/.agents/skills/pull-request/reference/publication-tasks.md

@@ -1,9 +1,7 @@
 # Pull request publication tasks
 
-Register each line as one session task before starting the process. Complete
-each task with `PASS`, `FAIL` plus file and line evidence, or `N/A` plus a
-reason when the task is conditional. This file is a task seed catalog, not a
-markdown progress board.
+When the session exposes a task tool, register each line as one session task
+before starting the process. This file is a task seed catalog.
 
 1. Resolve one repository, action, and selected author. For create, resolve the source branch, base, and head. For other actions, resolve one existing pull request target. Create actions publish drafts.
 2. Record the title and body file for create or full body rewrite, written by you or drafted by `pstack:poteto-agent` with a PR-writing brief. Mark `N/A` for comment or review bodies that do not rewrite the pull request description.