lazycodex-ai 5.1.62 → 5.1.64

package/packages/omo-codex/plugin/skills/programming/SKILL.md

@@ -78,7 +78,7 @@ Apply unless the per-language reference overrides with something stricter.
 | Exhaustive variant matching | `match` + `assert_never` | `match` (compiler-enforced) | `switch` + `assertNever` | sealed interface + type switch + **`exhaustive` linter** (the compiler will not help) |
 | No untyped escape hatches | no `Any` in public sigs, no `cast`, no `# type: ignore` | no `unwrap`/`expect` outside tests (invariant `expect` only behind `#[expect(clippy::expect_used, reason)]`), no numeric `as`, no `#[allow]` (silence with `#[expect(lint, reason)]`) | no `any`, no `as` (except `as const`, `satisfies`), no `!`, no `@ts-ignore`, no `@ts-expect-error` | no `interface{}` / bare `any` in domain sigs; no `_ = err`; no `//nolint` without reason |
 | No bare error strings | typed exception dataclass with `__str__` | `thiserror` enum (lib) or `anyhow` with `.context(...)` (app) | `Error` subclass with typed fields | sentinel `errors.New` + typed `*XError` struct; wrap with `%w`; check via `errors.Is/As` |
-| Boundary catch only | catch the exact exception you expect; broad `except Exception` only in `main()`, with logging + re-raise | `?` everywhere; never `panic!` in library code | `catch` must narrow with `instanceof` and re-throw or convert; no empty catch | every `(T, error)` checked; `panic` only in `main`/tests; one `httperr.Write` funnel in handlers |
+| Boundary catch only | catch the exact exception you expect; broad `except Exception` only at a top-level boundary (`main()`/CLI entry, HTTP handler), with logging + re-raise | `?` everywhere; never `panic!` in library code | `catch` must narrow with `instanceof` and re-throw or convert; no empty catch | every `(T, error)` checked; `panic` only in `main`/tests; one `httperr.Write` funnel in handlers |
 | Resources via RAII | `with` (sync) / `async with` (async) | `Drop` impl or RAII guard | `using`/`await using` (TC39 explicit resource management) | `defer x.Close()` immediately after acquisition; `bodyclose`/`sqlclosecheck` linters enforce |
 | Async runtime is mandatory | `anyio` (NEVER bare `asyncio`) | `tokio` (`async-std` is unmaintained) | platform-native async (Bun/Node) with structured cancellation via `AbortSignal` | `context.Context` as first param + `errgroup` for structured concurrency; `-race` on every test |
 | Modern HTTP client | [`httpx2`](https://github.com/pydantic/httpx2) with HTTP/2 + brotli + zstd | `reqwest` with rustls | `ky` (default) / `undici` direct API (Node perf) - NEVER bare `fetch` in prod | stdlib `net/http.Client` with tuned `Transport` + `go-retryablehttp` for retry/backoff |
@@ -140,13 +140,13 @@ Full rationale, measurement methods, workaround detection, and split examples: *
 
 A source file past 250 non-blank, non-comment lines has outgrown a single reviewer's working memory. The module is almost certainly doing more than one thing. Measure: `awk '!/^[[:space:]]*$/ && !/^[[:space:]]*(\/\/|#|--)/' <file> | wc -l`.
 
-**When detected:** Name what the file owns in one short noun phrase. If the answer needs "and", the file needs splitting. Load `/refactor` and split by responsibility. If the file genuinely cannot be split (generated parser, indivisible state machine), mark with `// allow: SIZE_OK — <reason>`.
+**When detected:** Name what the file owns in one short noun phrase. If the answer needs "and", the file needs splitting. Load `/refactor` and split by responsibility. If the file genuinely cannot be split (generated parser, indivisible state machine), mark it in the first 10 lines with `# noqa: SIZE_OK — <reason>` in Python (the form `scripts/python/check-no-excuse-rules.py` reads) or `// allow: SIZE_OK — <reason>` in `//`-comment languages.
 
 ### Smell 2 — Function with more than 3 parameters
 
 More than 3 arguments signals the function is doing too much, or that related parameters belong in a typed struct. **Workarounds count as the same smell** — passing `dict`/`Record<string, unknown>`/`map[string]any`/`**kwargs`/`...args` to smuggle parameters through one argument, or a throwaway "config" object with 6+ fields that exists solely to wrap what would otherwise be positional args (genuine reusable domain types like `HttpClientConfig` are fine).
 
-**When detected:** Group related parameters into a typed value object with a domain name. If 4+ independent inputs are genuinely required, the justification must be SPECIFIC. See [`references/code-smells.md` Smell 2](references/code-smells.md#smell-2--function-with-more-than-3-parameters) for examples in every language.
+**When detected:** Group related parameters into a typed value object with a domain name. If 4+ independent inputs are genuinely required, the justification must be SPECIFIC. See [`references/code-smells.md` Smell 2](references/code-smells.md#smell-2--function-with-more-than-3-parameters) for Python, TypeScript, and Go examples.
 
 ### Smell 3 — Redundant verification after a destructive action
 
@@ -242,9 +242,9 @@ These two skills are not optional cosmetics. They are the recovery path for the
 
 | Trigger | Skill to load | Why |
 |---|---|---|
-| Any [code smell](#code-smells--automatic-review-triggers) fires (250+ LOC, >3 params, redundant verification), OR the post-write loop surfaces 2+ issues, OR the user says "reshape this", "extract this", "clean this up" | `refactor` | Safe codemap-driven multi-step refactor with LSP + tests after each step. Never improvise a structural change. |
+| Any [code smell](#code-smells--automatic-review-triggers) fires (250+ LOC, >3 params, redundant verification, negative naming), OR the post-write loop surfaces more than two issues, OR the user says "reshape this", "extract this", "clean this up" | `refactor` | Safe codemap-driven multi-step refactor with LSP + tests after each step. Never improvise a structural change. |
 | Recent branch contains AI-authored patterns (broad except, dead helpers, vague comments, oversized files, redundant post-action verification, junk tests), OR the user says "remove slop", "clean AI code", "deslop" | `remove-ai-slops` | Behavior locked by gate-passing tests FIRST, then categorized parallel cleanup (junk tests included, each cut proven by a mutation), then quality gates. Behavior-preserving. |
-| Rust code touches `unsafe`, `*mut`, `*const`, `MaybeUninit`, FFI, `unsafe impl Send/Sync`, or a custom lock-free primitive | `references/rust-ub/` | Full UB taxonomy + Miri strictness escalation. Every `unsafe` block must survive Miri Level 3 (strict provenance + symbolic alignment + preemption) before it ships. |
+| Rust code touches `unsafe`, `*mut`, `*const`, `MaybeUninit`, FFI, `unsafe impl Send/Sync`, or a custom lock-free primitive | `references/rust-ub/` | Full UB taxonomy + Miri strictness escalation. Every `unsafe` block must survive Miri Level 3 (strict provenance + symbolic alignment + preemption) and the Level 4 Tree Borrows pass before it ships. |
 
 ---
 

package/packages/omo-codex/plugin/skills/programming/references/code-smells.md

@@ -48,10 +48,10 @@ cloc --by-file <file>   # the "code" column is the number
 
 A file may legitimately exceed 250 pure LOC if **and only if** it is:
 
-- A truly indivisible single-responsibility unit (e.g., a generated parser table, a state machine whose states share a single closure). Mark with `// allow: SIZE_OK — <reason>`.
+- A truly indivisible single-responsibility unit (e.g., a generated parser table, a state machine whose states share a single closure). Mark it in the first 10 lines with `# noqa: SIZE_OK — <reason>` in Python (the form `scripts/python/check-no-excuse-rules.py` reads) or `// allow: SIZE_OK — <reason>` in `//`-comment languages.
 - A pure data table (translation strings, error code lookup, brand color palette).
 
-`// allow: SIZE_OK` without a justifying comment is itself slop.
+A SIZE_OK marker without a justifying comment is itself slop.
 
 ### Concrete split examples
 

package/packages/omo-codex/plugin/skills/programming/references/go/README.md

@@ -66,9 +66,9 @@ Read these per-file references for the canonical patterns:
 - **HTTP backend** → `backend-stack.md` — `gin` server skeleton, middleware ordering, SSE/streaming with `http.Flusher`, structured slog logging, graceful shutdown — distilled from the CLIProxyAPI codebase (a real proxy serving OpenAI/Gemini/Claude APIs).
 - **RPC** → `grpc-connect.md` — when to pick Connect vs grpc-go, codegen pipeline, protovalidate, streaming.
 - **DB** → `sqlc-pgx.md` — compile-time-safe SQL via sqlc + pgx connection pool + migrations via goose + testcontainers in CI.
-- **CLI** → `cobra-stack.md` — cobra layout, slog integration, graceful shutdown on signals, fang-style colored help.
+- **CLI** → `cobra-stack.md` — cobra layout, slog integration, graceful shutdown on signals, shell completions, `huh` prompts styled with `lipgloss`.
 - **TUI** → `bubbletea-v2.md` — v2 model, `SetVirtualCursor(false)` + `tea.View{Cursor}` for CJK IME, why v1 was broken for Korean/Japanese/Chinese input.
-- **Testing** → `testing.md` — table-driven tests, `require` vs `assert`, `autogold` snapshots, `gopter` property tests, `testcontainers` for integration, `goleak` for goroutine leaks.
+- **Testing** → `testing.md` — table-driven tests, `require` vs `assert`, `autogold` snapshots, `rapid` property tests, `testcontainers` for integration, `goleak` for goroutine leaks.
 - **Bootstrap** → `bootstrap.md` — `scripts/go/new-project.ts` invocation, project layout (`cmd/`, `internal/`, `pkg/`), Taskfile, CI.
 - **Strict config** → `golangci-strict.md` — the canonical `.golangci.yml` with the full linter whitelist and per-linter rationale.
 - **One-liners** → `one-liners.md` — `go run` scripts with `//go:build ignore`, `gorun`-style invocation.
@@ -81,7 +81,7 @@ The `cmd/server/main.go` is the most common violator. Refactor it: `main.go` onl
 
 ## Existing codebases — non-strict project
 
-When editing an existing `.go` file that doesn't follow these rules: **write new code in strict style, don't refactor existing code in the same change.** Use the `remove-ai-slops` skill for branch-scope cleanup.
+When editing an existing `.go` file that doesn't follow these rules: **write new code in strict style, don't refactor existing code in the same change.** The one exception is the 250 pure-LOC ceiling: if your edit adds lines to a file already over it, split the unit you are touching into its own file first (see [`../code-smells.md`](../code-smells.md) Smell 1); everything else waits for a separate change. Use the `remove-ai-slops` skill for branch-scope cleanup.
 
 ## Activation
 

package/packages/omo-codex/plugin/skills/programming/references/python/README.md

@@ -41,7 +41,7 @@ These are deliberate project choices. Violations are always wrong, not "style pr
 11. **No Any, no object** — both are banned as type annotations. `object` erases all structural information (zero callable attributes, zero narrowing). Use `Protocol` (structural typing), `TypeVar` (generic pass-through), explicit union (known variants), or `TypedDict` (dict shapes).
 12. **No cast** — `cast()` is banned. Redesign the types.
 13. **No type: ignore** — fix the type error. The checker is right; you are wrong.
-14. **No broad except** — `except Exception` and `except BaseException` are banned. Catch the **specific** exception you expect. A broad catch swallows bugs you need to see — `KeyError`, `AttributeError`, `TypeError` all vanish silently. If you genuinely need a catch-all at a top-level boundary (CLI entry, HTTP handler), use `# noqa: BROAD_EXCEPT_OK` and log + re-raise.
+14. **No broad except** — `except Exception` and `except BaseException` are banned. Catch the **specific** exception you expect. A broad catch swallows bugs you need to see — `KeyError`, `AttributeError`, `TypeError` all vanish silently. If you genuinely need a catch-all at a top-level boundary (CLI entry, HTTP handler), put `# noqa: BROAD_EXCEPT_OK` on the `except` line and log + re-raise.
 
 ### Typing and safety
 
@@ -147,19 +147,19 @@ except Exception:
 # GOOD — catch what you expect
 try:
     result = api.fetch(url)
-except httpx.HTTPStatusError as e:
+except httpx2.HTTPStatusError as e:
     logger.error("API %d: %s", e.response.status_code, e.request.url)
     return None
-except httpx.ConnectError:
+except httpx2.ConnectError:
     raise ServiceUnavailableError(service="api") from None
 
-# GOOD — top-level boundary (only place broad catch is acceptable)
-def main() -> int:  # noqa: BROAD_EXCEPT_OK
+# GOOD — top-level boundary (CLI entry or HTTP handler: the only places a broad catch is acceptable)
+def main() -> int:
     try:
         return run()
-    except Exception:
+    except Exception:  # noqa: BROAD_EXCEPT_OK
         logger.exception("unhandled error")
-        return 1
+        raise
 ```
 
 ### Async
@@ -307,7 +307,7 @@ Tests still follow the iron list — frozen dataclasses, typed errors, exhaustiv
 
 ## Existing codebases
 
-When editing an existing file that doesn't follow these rules: **write new code in strict style, don't refactor existing code in the same change.** Mixing feature work with style migration makes reviews harder and bugs likelier.
+When editing an existing file that doesn't follow these rules: **write new code in strict style, don't refactor existing code in the same change.** The one exception is the 250 pure-LOC ceiling: if your edit adds lines to a file already over it, split the unit you are touching into its own file first (see [`../code-smells.md`](../code-smells.md) Smell 1); everything else waits for a separate change. Mixing feature work with style migration makes reviews harder and bugs likelier.
 
 ## Activation
 

package/packages/omo-codex/plugin/skills/programming/references/python/data-processing.md

@@ -10,16 +10,16 @@ NEVER pandas. Polars (with numpy) plus DuckDB. Pandas is 10-50x slower, has weak
 |---|---|---|
 | `.csv` / `.parquet` / `.json` direct query | DuckDB | Zero memory load, SQL ergonomics |
 | `.duckdb` file | DuckDB | Native format |
-| Filter (any size) | Polars | 128x faster than DuckDB for filtering |
-| Sort | Polars | 12x faster |
-| Multi-table join | DuckDB | 3x faster, more join types |
-| Heavy GROUP BY aggregation | DuckDB | 4x faster on large datasets |
-| Window function | Polars | 3-5x faster |
-| Pivot / melt / string ops | Polars | 2x faster |
+| Filter (any size) | Polars | row-wise filtering, low setup cost |
+| Sort | Polars | in-memory sorting |
+| Multi-table join | DuckDB | more join types, out-of-core joins |
+| Heavy GROUP BY aggregation | DuckDB | large grouped aggregation |
+| Window function | Polars | window expressions |
+| Pivot / melt / string ops | Polars | reshape and string expressions |
 | Larger than RAM | Polars streaming or DuckDB out-of-core | Both handle OOM |
 | Mixed pipeline | Hybrid (zero-copy via Arrow) | Use each tool's strengths |
 
-For the deep version (per-operation benchmarks, OOM strategies, full execution templates), load the **`data-scientist`** skill - it lives in this same skill set and is the source of truth for performance numbers.
+For the deep version (engine choice, placement, OOM strategies, execution templates), load the **`data-scientist`** skill - it lives in this same skill set; when the engine choice matters, measure on the actual data, as that skill says.
 
 ## Standard imports
 
@@ -69,7 +69,7 @@ result = (
         pl.len().alias("count"),
         pl.sum("amount").alias("total"),
     ])
-    .collect(streaming=True)
+    .collect(engine="streaming")
 )
 ```
 
@@ -84,7 +84,7 @@ joined = duckdb.sql("""
     JOIN 'products.parquet'  p ON o.product_id  = p.id
 """).pl()
 
-# Phase 2: Polars for filtering and transformation (128x + 2x faster)
+# Phase 2: Polars for filtering and transformation
 processed = (
     joined
     .filter(pl.col("amount") > 100)

package/packages/omo-codex/plugin/skills/programming/references/rust-ub/README.md

@@ -98,7 +98,7 @@ MIRIFLAGS="\
 **Interpret results:**
 - Fails at Level 1 → Definite UB. Fix immediately.
 - Passes Level 1, fails Level 2 → Provenance or alignment UB. Fix.
-- Passes Levels 1-3, fails Level 4 → Tree Borrows found something Stacked Borrows missed (unusual). Investigate — may be a Tree Borrows false positive, but usually indicates fragile aliasing.
+- Passes Levels 1-3, fails Level 4 → Tree Borrows found something Stacked Borrows missed (unusual). Investigate — may be a Tree Borrows false positive, but usually indicates fragile aliasing. It does not ship until the aliasing is fixed or the false positive is proven and recorded with the Miri output.
 - Passes all 4 → Miri-clean. Proceed to supplementary tools.
 
 ### Phase 3: Supplementary Scans
@@ -159,11 +159,11 @@ Is there unsafe code in the changeset?
   │       NO  → Run Miri Level 2 (strict provenance).
   │             Miri fails?
   │               YES → Stop. Classify. Fix. Prove. Then continue.
-  │               NO  → Proceed with the original task.
+  │               NO  → Proceed with the original task; run Levels 3 and 4 before it ships.
   NO → Proceed normally.
 ```
 
-This is not optional. **Every `unsafe` block gets Miri'd before it ships.**
+This is not optional. **Every `unsafe` block passes Miri Levels 3 and 4 before it ships.**
 
 ## SAFETY Comment Standard
 

package/packages/omo-codex/plugin/skills/programming/references/typescript/README.md

@@ -16,7 +16,7 @@ These are deliberate project choices. Violations are always wrong, not "style pr
 | Category | Use | Never |
 |---|---|---|
 | Runtime | Bun (native TS, single binary) | ts-node, tsx |
-| Package manager | `pnpm` | npm, yarn (unless workspace requires it) |
+| Package manager | Bun (`bun install`); `pnpm` only when Node is forced | npm, yarn (unless workspace requires it) |
 | Linter + formatter | **oxlint + oxfmt**, with both local copy rules | New ESLint, Prettier, or Biome setups; retain them only in repositories already using them |
 | Type checker | `tsc --noEmit` with strict config | skip type checking |
 | Web framework | Hono | Express |
@@ -39,7 +39,7 @@ These are deliberate project choices. Violations are always wrong, not "style pr
 11. **as const for constants** — module-level constant objects and arrays use `as const`.
 12. **import type** — type-only imports use `import type`. Enforced by `verbatimModuleSyntax`.
 13. **Named exports only** — no `export default`. Exception: framework requirement (Next.js pages, etc.).
-14. **No empty catch, no catch-and-swallow** — every `catch` block must either (a) narrow the error with `instanceof` and handle each case, or (b) re-throw. Empty catch blocks and `catch (e) { console.error(e) }` without narrowing or re-throw are banned — they hide bugs. At top-level boundaries (CLI entry, HTTP handler), opt out with `// no-excuse-ok: catch`.
+14. **No empty catch, no catch-and-swallow** — every `catch` block must either (a) narrow the error with `instanceof` and handle each case, or (b) re-throw. Empty catch blocks and `catch (e) { console.error(e) }` without narrowing or re-throw are banned — they hide bugs. At top-level boundaries (CLI entry, HTTP handler), opt out with `// no-excuse-ok: catch` on the `catch` line.
 
 ### Data modeling — which construct, when
 
@@ -91,10 +91,10 @@ try {
 }
 
 // GOOD — top-level boundary (only place catch-all is acceptable)
-async function main(): Promise<void> {  // no-excuse-ok: catch
+async function main(): Promise<void> {
   try {
     await run()
-  } catch (e) {
+  } catch (e) {  // no-excuse-ok: catch
     console.error("unhandled:", e)
     process.exit(1)
   }
@@ -190,7 +190,7 @@ Tests still follow the iron list — branded types, typed errors, exhaustive swi
 
 ## Existing codebases
 
-When editing an existing file that doesn't follow these rules: **write new code in strict style, don't refactor existing code in the same change.**
+When editing an existing file that doesn't follow these rules: **write new code in strict style, don't refactor existing code in the same change.** The one exception is the 250 pure-LOC ceiling: if your edit adds lines to a file already over it, split the unit you are touching into its own file first (see [`../code-smells.md`](../code-smells.md) Smell 1); everything else waits for a separate change.
 
 ## Activation
 

package/packages/omo-codex/plugin/skills/programming/scripts/typescript/new-project.ts

@@ -77,7 +77,7 @@ const pkg = {
   },
   dependencies: {
     hono: "^4.12.5",
-    zod: "^3.24.0",
+    zod: "^4.0.0",
   },
   devDependencies: {
     "@types/bun": "latest",

package/packages/omo-codex/plugin/skills/refactor/SKILL.md

@@ -106,17 +106,15 @@ Should I proceed with [recommendation], or would you prefer differently?
 
 ## Step 0.3: Create Initial Todos
 
-**IMMEDIATELY after understanding the request, create todos:**
+**IMMEDIATELY after understanding the request, create these todos with the session's todo tool (all pending):**
 
 \`\`\`
-TodoWrite([
-  {"id": "phase-1", "content": "PHASE 1: Codebase Analysis - launch parallel explore agents", "status": "pending", "priority": "high"},
-  {"id": "phase-2", "content": "PHASE 2: Build Codemap - map dependencies and impact zones", "status": "pending", "priority": "high"},
-  {"id": "phase-3", "content": "PHASE 3: Test Assessment - analyze test coverage and verification strategy", "status": "pending", "priority": "high"},
-  {"id": "phase-4", "content": "PHASE 4: Plan Generation - invoke Plan agent for detailed refactoring plan", "status": "pending", "priority": "high"},
-  {"id": "phase-5", "content": "PHASE 5: Execute Refactoring - step-by-step with continuous verification", "status": "pending", "priority": "high"},
-  {"id": "phase-6", "content": "PHASE 6: Final Verification - full test suite and regression check", "status": "pending", "priority": "high"}
-])
+- phase-1: PHASE 1: Codebase Analysis - launch parallel explore agents
+- phase-2: PHASE 2: Build Codemap - map dependencies and impact zones
+- phase-3: PHASE 3: Test Assessment - analyze test coverage and verification strategy
+- phase-4: PHASE 4: Plan Generation - invoke Plan agent for detailed refactoring plan
+- phase-5: PHASE 5: Execute Refactoring - step-by-step with continuous verification
+- phase-6: PHASE 6: Final Verification - full test suite and regression check
 \`\`\`
 
 ---
@@ -179,14 +177,14 @@ While background agents are running, use direct tools:
 
 \`\`\`typescript
 // Find definition(s)
-LspGotoDefinition(filePath, line, character)  // Where is it defined?
+lsp_goto_definition(filePath, line, character)  // Where is it defined?
 
 // Find ALL usages across workspace
-LspFindReferences(filePath, line, character, includeDeclaration=true)
+lsp_find_references(filePath, line, character, includeDeclaration=true)
 
 // Get file structure
-LspDocumentSymbols(filePath)  // Hierarchical outline
-LspWorkspaceSymbols(filePath, query="[target_symbol]")  // Search by name
+lsp_symbols(filePath, scope="document")  // Hierarchical outline
+lsp_symbols(filePath, scope="workspace", query="[target_symbol]")  // Search by name
 
 // Get current diagnostics
 lsp_diagnostics(filePath)  // Errors, warnings before we start
@@ -195,8 +193,8 @@ lsp_diagnostics(filePath)  // Errors, warnings before we start
 ### AST-Grep Skill for Pattern Analysis:
 
 \`\`\`bash
-// Find structural patterns
-python3 scripts/ast_grep_helper.py search 'function $NAME($$$) { $$$ }' --lang ts src/
+// Find structural patterns — run this from the ast-grep skill's directory; this skill ships no scripts/
+python3 scripts/ast_grep_helper.py search 'function $NAME($$$) { $$$ }' src/ --lang ts
 
 # Preview refactoring first
 sg --pattern '[old_pattern]' --rewrite '[new_pattern]' --lang ts src/
@@ -205,7 +203,7 @@ sg --pattern '[old_pattern]' --rewrite '[new_pattern]' --lang ts src/
 ### Grep for Text Patterns:
 
 \`\`\`
-grep(pattern="[search_term]", path="src/", include="*.ts")
+grep(pattern="[search_term]", path="src/")  // narrow to *.ts with the grep tool's file-filter parameter
 \`\`\`
 
 ## 1.3: Collect Background Results
@@ -342,6 +340,11 @@ Which approach do you prefer?
 - Unit: \`bun test\` / \`npm test\` / \`pytest\` / etc.
 - Integration: [command if exists]
 - Type check: \`tsc --noEmit\` / \`pyright\` / etc.
+- Lint: [project's linter command, the one Phase 6.3 runs]
+
+### Baseline (before any change)
+- Pass counts: [X/Y passing per test command above]
+- lsp_diagnostics: [pre-existing diagnostics recorded in Phase 1.2]
 
 ### Verification Checkpoints
 After each refactoring step:
@@ -405,17 +408,14 @@ After receiving plan from Plan agent:
 
 ## 4.3: Register Detailed Todos
 
-Convert Plan agent output into granular todos:
+Convert Plan agent output into granular todos with the session's todo tool (each step from the plan becomes a todo, followed by its verify todo):
 
 \`\`\`
-TodoWrite([
-  // Each step from the plan becomes a todo
-  {"id": "refactor-1", "content": "Step 1: [description]", "status": "pending", "priority": "high"},
-  {"id": "verify-1", "content": "Verify Step 1: run tests", "status": "pending", "priority": "high"},
-  {"id": "refactor-2", "content": "Step 2: [description]", "status": "pending", "priority": "medium"},
-  {"id": "verify-2", "content": "Verify Step 2: run tests", "status": "pending", "priority": "medium"},
-  // ... continue for all steps
-])
+- refactor-1: Step 1: [description]
+- verify-1: Verify Step 1: run tests
+- refactor-2: Step 2: [description]
+- verify-2: Verify Step 2: run tests
+- ... continue for all steps
 \`\`\`
 
 **Mark phase-4 as completed.**
@@ -449,8 +449,8 @@ lsp_rename(filePath, line, character, newName)  // Execute rename
 // Preview first
 sg --pattern '[pattern]' --rewrite '[rewrite]' --lang ts path/to/file.ts
 
-// If preview looks good, execute
-python3 scripts/ast_grep_helper.py replace '[pattern]' '[rewrite]' --lang ts path/to/file.ts --apply
+// If preview looks good, execute (from the ast-grep skill's directory)
+python3 scripts/ast_grep_helper.py replace '[pattern]' '[rewrite]' path/to/file.ts --lang ts --apply
 \`\`\`
 
 **For Structural Changes:**
@@ -543,7 +543,7 @@ bun run build  # or npm run build, etc.
 \`\`\`typescript
 // Check all changed files
 for (file of changedFiles) {
-  lsp_diagnostics(file)  // Must all be clean
+  lsp_diagnostics(file)  // Must be clean or same as the Phase 1 baseline: zero new diagnostics
 }
 \`\`\`
 
@@ -609,8 +609,8 @@ You already know these tools. Use them intelligently:
 
 ## LSP Tools
 Leverage LSP tools for precision analysis. Key patterns:
-- **Understand before changing**: \`LspGotoDefinition\` to grasp context
-- **Impact analysis**: \`LspFindReferences\` to map all usages before modification
+- **Understand before changing**: \`lsp_goto_definition\` to grasp context
+- **Impact analysis**: \`lsp_find_references\` to map all usages before modification
 - **Safe refactoring**: \`lsp_prepare_rename\` → \`lsp_rename\` for symbol renames
 - **Continuous verification**: \`lsp_diagnostics\` after every change
 
@@ -674,7 +674,7 @@ Then choose the path:
 - **Team path (5.1-T)**: when the plan recommends \`team\` AND \`file_independent_steps >= 3\`. Members execute in parallel, Lead orchestrates, a \`deep-high\` verifier lives outside the team.
 - **Legacy path (5.1-L)**: otherwise. Use the original 5.1 / 5.2 / 5.3 flow from above.
 
-Record the chosen path in the TodoWrite list.
+Record the chosen path in the todo list.
 
 ## Phase 5.1-T: \`refactor-squad\` team execution
 
@@ -682,9 +682,9 @@ Record the chosen path in the TodoWrite list.
 
 1. When the session lists the \`team-mode\` skill, load it for lifecycle, message protocol, and limits.
 2. Call \`team_list\` and verify no active \`refactor-squad\` run exists; if one does, shutdown + delete the orphan before proceeding.
-3. If \`~/.omo/teams/refactor-squad/config.json\` is missing, write it using the spec below.
+3. If the project-level spec \`.omo/teams/refactor-squad/config.json\` (under the project root) is missing, write it using the spec below.
 
-**Team spec** (\`~/.omo/teams/refactor-squad/config.json\`):
+**Team spec** (\`<project root>/.omo/teams/refactor-squad/config.json\`):
 
 \`\`\`json
 {
@@ -748,7 +748,7 @@ While any team task is \`pending | claimed | in_progress\`:
     prompt=<files touched + verify-spec commands + instruction to return "PASS" or "FAIL:<failing test + specific error + suggested revert hunks>">
   )
   \`\`\`
-  If \`deep\` is unavailable, fall back to \`category="unspecified-high"\`. Do not create a commit checkpoint until the verifier returns PASS.
+  If \`deep-high\` is unavailable, fall back to \`category="unspecified-high"\`. Do not create a commit checkpoint until the verifier returns PASS.
 - On a verifier PASS: make the commit checkpoint for that step (see original 5.3). Proceed.
 - On a verifier FAIL: Lead decides:
   - **Retry with fix hint**: \`team_task_update(status=pending)\` on the original step + \`team_send_message(teamRunId=<id>, to=<original member>, summary="retry", body=<specific failure from verifier>)\`. Runtime reassigns.
@@ -765,7 +765,7 @@ If Phase 5 used the team path, dismantle \`refactor-squad\` BEFORE producing the
 2. \`team_delete(teamRunId=<id>)\`.
 3. \`team_list\` to confirm no residual \`refactor-squad\` run.
 
-The \`~/.omo/teams/refactor-squad/config.json\` declaration stays on disk; next session reuses it.
+The \`.omo/teams/refactor-squad/config.json\` declaration stays on disk in the project; next session reuses it.
 
 Append to the 6.6 summary a "Dispatch path" line and, when team path was used, team metrics (teamRunId, tasks created, verifier runs, team lifetime).
 

package/packages/omo-codex/plugin/skills/remove-ai-slops/SKILL.md

@@ -96,12 +96,12 @@ The agent looks for these ten categories. The first three are stylistic, the nex
 10. **Oversized modules** — any source file exceeding **250 pure LOC** (non-blank, non-comment lines). This is an architectural defect, not a style preference. Measure: `awk '!/^[[:space:]]*$/ && !/^[[:space:]]*(#|\/\/)/' <file> | wc -l`.
 
    **When found, do NOT just flag it. Execute a full modular refactoring:**
-   1. Run `check-no-excuse-rules.py` recursively on scope to list all violations.
+   1. List every oversized file in scope: run the `awk` measure above on each source file. For `.py` files you may instead run the `programming` skill's Python checker (`uv run <programming skill dir>/scripts/python/check-no-excuse-rules.py <paths>`, rule `oversized-module`); it scans only `.py` files, so it never covers another language.
    2. For each oversized file, identify distinct responsibilities (single-responsibility principle).
    3. Plan the split: name each new file after the concept it owns (never `utils.py`, `helpers.py`, `common.py`, `part_1.py`).
    4. Present the split plan to the user before executing.
    5. Extract into clean modules with explicit `__init__.py` re-exports (re-exports ONLY, no logic in `__init__.py`).
-   6. Verify: run `check-no-excuse-rules.py` again — every file must be ≤250 pure LOC. Run tests, typecheck, lint.
+   6. Verify: re-measure exactly as in step 1 — every file must be ≤250 pure LOC. Run tests, typecheck, lint.
 
    **Forbidden escapes**:
    - Counting blanks/comments toward budget.
@@ -110,7 +110,7 @@ The agent looks for these ten categories. The first three are stylistic, the nex
    - "It's generated" — only valid if the file lives in a build output directory.
    - "230 LOC, close enough" — a 230-LOC file about to grow is already over. Split now.
 
-   KEEP: genuinely self-contained single-responsibility scripts (e.g., a standalone CLI checker). Opt out with `# noqa: SIZE_OK` in first 5 lines and a comment explaining why.
+   KEEP: genuinely self-contained single-responsibility scripts (e.g., a standalone CLI checker). Opt out with the language's SIZE_OK marker in the first 10 lines (`# noqa: SIZE_OK` in Python, the form the Python checker reads; `// allow: SIZE_OK` in `//`-comment languages) and a comment explaining why.
 
 ---
 
@@ -130,7 +130,7 @@ A pass is complete only when all applicable gates are green. Skip gates that are
 
 ## Process
 
-### Phase 0: Plan with TodoWrite
+### Phase 0: Plan with the todo tool
 
 Create todos for all phases below. Mark `in_progress` one at a time.
 
@@ -270,8 +270,8 @@ If any gate fails or any checklist item flips:
 
 1. Identify the specific change that caused the failure.
 2. Explain why it broke things.
-3. `git checkout` the affected file (or use `git diff` + targeted `Edit` to revert just the problematic hunk).
-4. If genuine slop remains after revert, edit the file directly yourself — in parallel per file via multiple Edit calls — applying only the changes you can prove are safe.
+3. `git checkout` the affected file (or use `git diff` + targeted `edit` to revert just the problematic hunk).
+4. If genuine slop remains after revert, edit the file directly yourself — in parallel per file via multiple `edit` calls — applying only the changes you can prove are safe.
 5. Re-run the failing gate and re-walk the checklist for the affected file.
 6. Repeat until all gates green AND checklist clean.
 

package/packages/omo-codex/plugin/skills/review-work/SKILL.md

@@ -163,7 +163,7 @@ For GOAL, CONSTRAINTS, BACKGROUND - review the full conversation history. The us
 
 ## Phase 1: Manual QA (you run it)
 
-You are the QA lane. Do not delegate hands-on QA to a sub-agent: the orchestrator owns the real-surface proof, exactly as the ulw-loop final gate records `manualQa` under the main session.
+You are the QA lane. Do not delegate hands-on QA to a sub-agent: the orchestrator owns the real-surface proof, exactly as the ulw-loop final gate records `manualQa` under the main session. One exception: inside a `ulw-execute` run, whose root never runs QA itself, dispatch these scenarios to one QA worker and build the matrix from the artifacts it captures.
 
 1. **Reuse first.** If this session already captured real-surface evidence for the FINAL tree (an ultrawork or ulw-loop evidence directory, a `visual-qa` verdict on this same build), consume it as QA rows instead of re-running. A fix committed after a capture stales that capture: re-run the rows it covered.
 2. **Pick the channel that faithfully exercises the surface** and capture the artifact:
@@ -282,7 +282,7 @@ Store the lane verdicts independently:
 | Manual QA (Phase 1) | PASS/FAIL | rows, artifact paths |
 | Gate review | pending/APPROVE/REJECT/INCONCLUSIVE | - |
 
-If the reviewer stays silent after the reliability followup, record the lane INCONCLUSIVE and respawn one smaller reviewer scoped to the same inputs. If that retry also ends without a verdict, close the still-running agent if safe, keep the lane INCONCLUSIVE, and emit the final result naming the incomplete lane. Do not spin in repeated wait/followup cycles, and do not use a queued followup as a cancellation.
+If the reviewer ends without a verdict (it completed without one, answered ack-only to one follow-up, or reported `BLOCKED:`), record the lane INCONCLUSIVE and respawn one smaller reviewer scoped to the same inputs. A reviewer that is still running is alive, not silent. If that retry also ends without a verdict, close the still-running agent if safe, keep the lane INCONCLUSIVE, and emit the final result naming the incomplete lane. Do not spin in repeated wait/followup cycles, and do not use a queued followup as a cancellation.
 
 After the lane reaches a terminal state and before delivering the verdict, tear down the review worktree: run `git worktree unlock <path>` followed by `git worktree remove <path>`. The reviewer runs inside that worktree, so removing it earlier destroys its working directory; a crashed review leaves the locked tree as a recoverable marker for manual cleanup.
 

package/packages/omo-codex/plugin/skills/ultimate-browsing/SKILL.md

@@ -22,7 +22,7 @@ User request
   +- archive snapshot of a dead or changed page ------- TIER 1  insane-search (surrogates, provenance-tagged)
   |
   +- Chinese platform (xhs/douyin/weibo/bilibili/v2ex/wechat)  TIER 1.5 agent-reach
-  +- podcast transcript / stock forum ----------------- TIER 1.5 agent-reach
+  +- podcast transcript ------------------------------- TIER 1.5 agent-reach
   +- Twitter feed / LinkedIn profile / GitHub via CLI - TIER 1.5 agent-reach
   |
   +- Tier 1/1.5 returned empty or partial ------------- TIER 2  2a owned engine (stealth)
@@ -71,8 +71,8 @@ The full engine harness (rules R1-R7, the Phase 0 official-API index, the no-sit
 | search | Exa AI | [references/agent-reach/search.md](references/agent-reach/search.md) |
 
 ```bash
-mcporter call 'douyin.parse_douyin_video_info(url: "<URL>")'   # douyin, zero-config
-curl -s "https://r.jina.ai/https://weibo.com/<uid>/<pid>"      # weibo via Jina
+mcporter call 'douyin.parse_douyin_video_info(share_link: "<URL>")'   # douyin, zero-config
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://weibo.com/<uid>/<pid>"   # weibo via Jina (key required)
 yt-dlp --dump-json "<bilibili-url>"                            # Bilibili (overseas: add --cookies-from-browser)
 curl -s "https://www.v2ex.com/api/topics/hot.json"            # V2EX public API
 ```
@@ -115,17 +115,19 @@ When the blocked flow needs the user's account, drive the browser they are alrea
 
 ### Cookie login (cross-platform)
 
-`scripts/extract_cookies.py` reads cookies from a local Chromium-family or Firefox-family browser and optionally injects them into the running CDP session. It resolves browser profile paths and decrypts cookie values per-OS (macOS Keychain, Linux libsecret, Windows DPAPI):
+A login the user holds goes through Tier 2b, never through their cookies: the `browser` skill forbids copying a session out of the user's real browser profile (`references/owned-engine/network.md`, Cookies).
+
+`scripts/extract_cookies.py` reads cookies from the default profile store of a local Chromium-family or Firefox-family browser and optionally injects them over CDP. It resolves browser profile paths and decrypts cookie values per-OS (macOS Keychain, Linux libsecret, Windows DPAPI). Because it always reads that default store, run it only where that browser profile is not the user's live profile (for example a dedicated automation account whose browser the task owns); on the user's own machine it would copy their session, so use Tier 2b instead.
 
 ```bash
 # Extract cookies to a file:
 mkdir -p ~/.local/state/omo-cookies
 python3 -B scripts/extract_cookies.py --browser chrome --domain youtube.com --output ~/.local/state/omo-cookies/youtube.cookies.json
-# Extract and inject into the running CDP session:
+# Extract and inject over CDP (needs a browser started with --remote-debugging-port=9242; connectPipe opens no port):
 python3 -B scripts/extract_cookies.py --browser chrome --domain youtube.com --inject --cdp 9242
 ```
 
-Cookie export files are written with owner-only `0600` permissions. Do not place live auth cookies in shared temp directories or commit them to a repo. Cookie injection sends values to CDP over stdin rather than argv. Cookies apply on next navigation — reload after injecting. Google services use fingerprint-bound tokens that may not transfer across browser profiles. Limits in [references/chrome-stealth.md](references/chrome-stealth.md).
+For a Tier 2a owned page, load the exported file and call `omowright.injectCookies(page, cookies)` instead (see [references/chrome-stealth.md](references/chrome-stealth.md)). Cookie export files are written with owner-only `0600` permissions. Do not place live auth cookies in shared temp directories or commit them to a repo. Cookie injection sends values to CDP over stdin rather than argv. Cookies apply on next navigation — reload after injecting. Google services use fingerprint-bound tokens that may not transfer across browser profiles. Limits in [references/chrome-stealth.md](references/chrome-stealth.md).
 
 ## Reference docs
 
@@ -139,7 +141,8 @@ Cookie export files are written with owner-only `0600` permissions. Do not place
 
 ```bash
 # agent-reach auth: set the channel-specific env vars from each tool's docs only if you have access
-# insane-search needs no env vars — it auto-installs deps on first run
+# insane-search: JINA_API_KEY only for the Jina Reader route (the engine skips that surrogate without it)
+# insane-search Python deps: the install one-liner in references/insane-search/README.md
 ```
 
 ## Anti-patterns

package/packages/omo-codex/plugin/skills/ultimate-browsing/engine/AGENTS.md

@@ -61,7 +61,7 @@ is a regression, not an upgrade:
 - **Module split of the fetch chain** — `curl_probe` / `referers` / `url_transforms` /
   `waf_detector` / `validators` / `executor` / `summary` as separate modules rather than
   one monolith.
-- **The Python test suite** under `engine/tests/` with its HTML/JSON fixtures.
+- **The Python test suite** under `engine/tests/` with its HTML/JSON fixtures (source checkout only: the skill copy filter drops `engine/tests/` from every shipped edition).
 - **De-personalization** — no personal absolute paths, no personal auth token literals,
   no personal browser choice; enforced by `depersonalization-gate.test.ts`.
 - **Skill-level layering** — the engine is Tier 1 under a router that also owns Tier 1.5
@@ -115,7 +115,7 @@ Any future upstream sync preserves BOTH sides. Concretely:
 
 ## OVERVIEW
 
-A 17-module Python package embedded in the `ultimate-browsing` skill: a site-agnostic fetch chain that escalates from a cheap curl probe to a real browser, with declarative WAF and surrogate registries. Not "optional scripts" — it has its own CLI entry (`python3 -B -m engine URL`; `-B` keeps bytecode caches out of a signed app bundle, #11373), two YAML config schemas, a 4-file test suite, and a standalone CI guard. Package exports (`__init__.py`): `fetch`, `FetchResult`, `Attempt`, `Verdict`, `ValidationResult`, `validate`, `CHALLENGE_MARKERS`, `detect`, `TRANSFORMS`, `apply_transform`.
+A 13-file Python package (`__init__.py`, `__main__.py` and 11 modules) embedded in the `ultimate-browsing` skill: a site-agnostic fetch chain that escalates from a cheap curl probe to a real browser, with declarative WAF and surrogate registries. Not "optional scripts" — it has its own CLI entry (`python3 -B -m engine URL`; `-B` keeps bytecode caches out of a signed app bundle, #11373), two YAML config schemas, a 6-file test suite (source checkout only), and a standalone CI guard. Package exports (`__init__.py`): `fetch`, `FetchResult`, `Attempt`, `Verdict`, `ValidationResult`, `validate`, `CHALLENGE_MARKERS`, `detect`, `TRANSFORMS`, `apply_transform`.
 
 ## THE NO-SITE-NAME RULE (enforced in CI)
 
@@ -170,11 +170,11 @@ python3 -B -m engine URL [--selector S] [--device auto|desktop|mobile]
 
 ## TESTS
 
-`tests/` — `test_surrogate.py` (staleness, proxy gating, short-circuit), `test_surrogate_validators.py`, `test_fetch_chain.py`, `test_playwright_templates.py`, plus HTML/JSON fixtures under `tests/fixtures/`.
+`tests/` (source checkout only; not shipped with the skill) — `test_surrogate.py` (staleness, proxy gating, short-circuit), `test_surrogate_validators.py`, `test_fetch_chain.py`, `test_playwright_templates.py`, `test_playwright_stealth.py`, `test_executor_timeout.py`, plus HTML/JSON fixtures under `tests/fixtures/`.
 
 ## NOTES
 
 - `summary.py` emits an **R7 API-first hint** after >=3 challenge verdicts against a known WAF profile: look for `/api/`, `/graphql`, or `.json` endpoints, which usually carry weaker WAF protection than the HTML surface.
 - `templates/` holds the Playwright JS templates (`playwright_real_chrome.js`, `playwright_mobile_chrome.js`) the executor drives.
 - `url_transforms.py` transforms stay domain-agnostic (`mobile_subdomain`, `am_prefix`, `drop_www`).
-- Parent: [`packages/shared-skills/AGENTS.md`](../../../AGENTS.md).
+- Parent (source checkout only; not shipped with the skill): `packages/shared-skills/AGENTS.md`.

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/agent-reach/README.md

@@ -25,13 +25,13 @@
 mcporter call 'exa.web_search_exa(query: "query", numResults: 5)'
 
 # 通用网页阅读
-curl -s "https://r.jina.ai/URL"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/URL"
 
 # GitHub 搜索
 gh search repos "query" --sort stars --limit 10
 
 # Twitter 搜索
-twitter search "query" --limit 10
+twitter search "query" -n 10
 
 # YouTube/B站字幕
 yt-dlp --write-sub --skip-download -o "/tmp/%(id)s" "URL"

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/agent-reach/career.md

@@ -25,5 +25,5 @@ mcporter call 'linkedin-scraper.search_jobs(keyword: "software engineer", limit:
 如果 MCP 不可用，可以用 Jina Reader：
 
 ```bash
-curl -s "https://r.jina.ai/https://linkedin.com/in/username"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://linkedin.com/in/username"
 ```

package/packages/omo-codex/plugin/skills/ultimate-browsing/references/agent-reach/social.md

@@ -105,7 +105,7 @@ twitter likes
 
 ```bash
 # 使用 Jina Reader 读取
-curl -s "https://r.jina.ai/https://weibo.com/USER_ID/POST_ID"
+curl -s -H "Authorization: Bearer ${JINA_API_KEY}" "https://r.jina.ai/https://weibo.com/USER_ID/POST_ID"
 ```
 
 > 微博主要通过网页抓取，推荐使用通用网页读取方式。