claude-dev-env 8.46.6 → 8.46.7

package/.agents/agents-archived/clean-coder.md

@@ -22,7 +22,7 @@ Before writing a single line — **task-local discovery only** (no project-wide
 1. **Load scoped repository instructions first.** Starting at the repository root, read every applicable `AGENTS.md` on the path to the task file. Then read the applicable `CLAUDE.md` files. Apply nearer instructions after broader ones; the closest file wins.
 2. **Read the file you are about to edit** (when editing existing code). Note every existing comment so you can leave each one untouched on lines that remain otherwise unchanged.
 3. **Discover config only next to the task files.** From each file you will write or edit, walk up to the nearest package or repo root and inspect the target package's existing constants layout — such as `config/` or a sibling `*_constants` package. Keep this task-local constants search. Do **not** force a generic `config/` layout. Do **not** glob the whole tree for every config file. Do **not** glob or open `.env`, `.env.*`, or other secret files.
-4. **Reuse constants from that local table.** Reuse first: exact value match → import the existing name. Semantic match → reuse it. Add a shared constant only when the value is shared policy or has multiple consumers. When no match exists, use the target package's existing constants layout, and keep a one-use value in the scope that reads it rather than making it a new shared constant.
+4. **Reuse constants from that local table.** Reuse first: exact value match → import the existing name. Semantic match → reuse it. Add a shared constant only when the value is shared policy or has multiple consumers. When no match exists, use the target package's existing constants layout, and keep a one-use value in the scope that reads it.
 5. **Search callers.** When a symbol, name, or signature changes, search its full caller boundary and update every consumer. This search may be wider than the constants search.
 
 ## Generation mindset (9 laws)

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

@@ -210,7 +210,7 @@ Every Shape A finding cites a file path and a line number. The offending line is
 Do not infer missing context. If the diff and allowed checks cannot confirm a
 claim, use an open question or an evidence gap.
 
-When the diff alone lacks the context to confirm a finding, list the item under an "Open questions" section rather than asserting it as a Shape A finding. Each open question names the file and line where uncertainty arose and states what additional context would resolve it.
+When the diff alone lacks the context to confirm a finding, list the item under an "Open questions" section and keep it out of the Shape A findings. Each open question names the file and line where uncertainty arose and states what additional context would resolve it.
 
 ```json
 {

package/.agents/skills/grok-spawn/reference/worker-briefs.md

@@ -150,7 +150,7 @@ For each acceptance line from the brief:
 1. Keep task-specific detail in its own part file so the brief templates stay
    reusable.
 2. Absolute paths only in `prompt_parts` — the launcher reads them as given.
-3. One worker, one closed scope. Split large work into more workers rather than
-   one long brief.
+3. One worker, one closed scope. Split large work into more workers, each with a
+   short brief.
 4. The lead session fills bracketed fields before launch; workers never see the
    skill folder unless you copy text into their part files.

package/hooks/blocking/code_rules_comments.py

@@ -50,11 +50,11 @@ def check_comments_python(content: str) -> list[str]:
     Hash characters that appear inside string literals (hex color codes,
     URL fragments, and the hash inside an f-string interpolation pattern)
     are correctly skipped because the tokenizer recognizes them as parts
-    of string tokens rather than comment tokens.
+    of string tokens.
 
     When the tokenizer cannot parse the file (partial content during
-    Edit, invalid syntax), the check returns no findings rather than
-    falling back to a line-walker scan — false negatives on
+    Edit, invalid syntax), the check returns no findings and does not
+    fall back to a line-walker scan — false negatives on
     syntactically-invalid drafts are preferable to false positives that
     mis-classify string-interior hash characters as comments.
     """

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "claude-dev-env",
-    "version": "8.46.6",
+    "version": "8.46.7",
     "description": "Claude Code development standards — rules, hooks, agents, commands, and skills",
     "type": "module",
     "bin": {