claude-dev-env 1.95.0 → 2.0.0

package/agents/code-verifier.md

@@ -33,7 +33,7 @@ On Windows the same file sits at %USERPROFILE%\.claude\hooks\blocking\verificati
 
 The printed hash commits to every changed and untracked file's content in the verified work tree, so it names that surface no matter which directory you or the committer run from. If the CLI prints an empty-surface or wrong-work-tree error and no hash, you are pointed at a work tree with no changes versus origin/main — re-run with the branch mode to locate the correct work tree.
 
-As the last step before the verdict, put your draft verdict through one best-effort strongest-tier validation pass. Spawn a single validation subagent through the Task tool as the `Explore` agent type at the strongest reachable tier: set the Task `subagent_type` to `Explore`, detect the host profile first per `~/.claude/_shared/advisor/advisor-protocol.md` — the source of truth for host detection, the ladder, and its aliases — then on a Claude host pick the strongest reachable tier on the Fable → Opus → Sonnet → Haiku ladder and on a Grok host use the single Grok tier, and set the Task `model:` field to that tier's alias. The `Explore` type carries no Edit or Write tools and cannot spawn further agents, so the harness itself holds the validator to the no-edit, no-spawn contract the next paragraph names. Hand it the draft verdict together with your evidence — every command you ran with its output, and your two-way diff-to-task mapping — and state that its task is adversarial verification of that supplied draft verdict: refute it against the supplied evidence rather than discover code, naming any gate you misread, any task item you mapped wrong, or any finding that does not hold. When the spawn is unavailable — a Task tool error, an unreachable tier at every rung, or this subagent being barred from spawning further agents — skip the validation pass and emit the draft verdict as it stands, noting the skip in your final message; a spawn failure never blocks the verdict fence from being emitted.
+As the last step before the verdict, put your draft verdict through one best-effort strongest-tier validation pass. Spawn a single validation subagent through the Task tool as the `Explore` agent type at the strongest reachable tier: set the Task `subagent_type` to `Explore`, detect the host profile first per `~/.claude/_shared/advisor/advisor-protocol.md` — the source of truth for host detection, the ladder, and its aliases — then on a Claude host pick the strongest reachable tier on the Fable → Opus → Sonnet → Haiku ladder and on a third-party host use the single third-party tier, and set the Task `model:` field to that tier's alias. The `Explore` type carries no Edit or Write tools and cannot spawn further agents, so the harness itself holds the validator to the no-edit, no-spawn contract the next paragraph names. Hand it the draft verdict together with your evidence — every command you ran with its output, and your two-way diff-to-task mapping — and state that its task is adversarial verification of that supplied draft verdict: refute it against the supplied evidence rather than discover code, naming any gate you misread, any task item you mapped wrong, or any finding that does not hold. When the spawn is unavailable — a Task tool error, an unreachable tier at every rung, or this subagent being barred from spawning further agents — skip the validation pass and emit the draft verdict as it stands, noting the skip in your final message; a spawn failure never blocks the verdict fence from being emitted.
 
 This validation pass is terminal: the `Explore` type gives the validation subagent no way to spawn a further agent or edit a file, so it answers with prose only. When it refutes any part, re-check that part yourself against the commands and the diff, and correct the verdict before you emit it. When it refutes nothing, the draft verdict stands. Then emit the fenced verdict block below — it stays the last thing in your message so the verifier_verdict_minter hook reads it.
 

package/bin/ever-shipped-skills.mjs

@@ -24,7 +24,9 @@ export const EVER_SHIPPED_SKILL_NAMES = new Set([
     'bg-agent',
     'bugteam',
     'caveman',
+    'closeout',
     'code',
+    'codex-review',
     'copilot-finding-triage',
     'copilot-review',
     'deep-research',
@@ -34,6 +36,7 @@ export const EVER_SHIPPED_SKILL_NAMES = new Set([
     'fresh-branch',
     'gh-paginate',
     'gotcha',
+    'grok-spawn',
     'grokify',
     'implement',
     'log-audit',

package/bin/expand_home_directory_tokens.mjs

@@ -1,7 +1,7 @@
 /**
  * Install-time expansion of $HOME / ${HOME} / ~/ in settings.json commands.
  *
- * Hosts that require referenced env vars at hook load time (for example Grok)
+ * Hosts that require referenced env vars at hook load time (for example a third-party host)
  * skip the hook when HOME is unset — common on Windows — so the installer
  * rewrites residual tokens to absolute home paths.
  */

package/bin/install.mjs

@@ -177,6 +177,7 @@ const INSTALL_GROUPS = {
         description: 'Development standards, hooks, agents, commands',
         skills: [
             'orchestrator', 'orchestrator-refresh', 'team-advisor', 'grokify',
+            'grok-spawn',
             'anthropic-plan', 'everything-search',
             'privacy-hygiene',
             'recall', 'remember', 'task-build'
@@ -535,7 +536,7 @@ function pruneManagedHooksFromEvent(settings, eventType, managedHookRelativePath
  * a new matcher group does not double-run. User-authored hooks are preserved as
  * entries, but residual $HOME / ${HOME} / ~/ tokens in every hook and statusLine
  * command are expanded to absolute home paths so hosts that require referenced
- * env vars at load time (Grok on Windows) can execute them.
+ * env vars at load time (a third-party host on Windows) can execute them.
  *
  * @param {object} settings The parsed settings.json object (mutated in place).
  * @param {{hooks: object}} hooksConfig Parsed hooks.json.
@@ -821,6 +822,7 @@ function install(selectedGroups, options = {}) {
     let skillsUpdated = 0;
     const skillPaths = [];
     const installedSkillNames = new Set();
+    const copiedSkillNames = new Set();
     for (const sourceRoot of allSourceRoots) {
         const skillsSource = join(sourceRoot, 'skills');
         if (!existsSync(skillsSource)) continue;
@@ -831,6 +833,7 @@ function install(selectedGroups, options = {}) {
             skillsCreated += stats.created;
             skillsUpdated += stats.updated;
             skillPaths.push(...stats.paths);
+            copiedSkillNames.add(skillDir.name);
             if (existsSync(join(skillsSource, skillDir.name, SKILL_MANIFEST_FILENAME))) {
                 installedSkillNames.add(skillDir.name);
             }
@@ -930,7 +933,7 @@ function install(selectedGroups, options = {}) {
                 + 'A skill that migrated to a dependency package would look retired and be moved to backup, so the prune is held until every dependency resolves.',
             );
         } else {
-            pruneRetiredSkills(installedSkillNames, priorManifestSkills);
+            pruneRetiredSkills(copiedSkillNames, priorManifestSkills);
         }
         manifestSkillNames = [...installedSkillNames].sort();
     }

package/hooks/advisory/refactor_guard.py

@@ -8,7 +8,6 @@ functions, restructuring) rather than writing new code or replacing wholesale.
 Only fires for Edit operations (not Write, which creates/replaces entire files).
 """
 import json
-import os
 import re
 import subprocess
 import sys
@@ -24,7 +23,7 @@ def get_git_diff_added_lines(file_path: str) -> set[str]:
     try:
         result = subprocess.run(
             ["git", "diff", "HEAD", "--", file_path],
-            capture_output=True,
+            check=False, capture_output=True,
             text=True,
             timeout=5,
         )
@@ -34,7 +33,7 @@ def get_git_diff_added_lines(file_path: str) -> set[str]:
 
         staged_result = subprocess.run(
             ["git", "diff", "--staged", "--", file_path],
-            capture_output=True,
+            check=False, capture_output=True,
             text=True,
             timeout=5,
         )
@@ -51,7 +50,7 @@ def is_new_file(file_path: str) -> bool:
     try:
         result = subprocess.run(
             ["git", "ls-files", "--others", "--exclude-standard", "--", file_path],
-            capture_output=True,
+            check=False, capture_output=True,
             text=True,
             timeout=5,
         )

package/hooks/blocking/CLAUDE.md

@@ -7,6 +7,12 @@ PreToolUse hooks that deny (block) tool calls when a rule is violated. The main
 | Directory | Role |
 |---|---|
 | `config/` | Shared constants for the verified-commit gate family (`verified_commit_constants.py`) |
+| `tdd_enforcer_parts/` | Concern modules the `tdd_enforcer.py` entry hook wires together: path classification, content analysis, candidate-path resolution, freshness, git-tracking restore detection, decisions, and constants |
+| `claude_md_orphan_file_blocker_parts/` | Concern modules the `claude_md_orphan_file_blocker.py` entry hook wires together: reference extraction, subtree scan, scan plan, decision, and constants |
+| `package_inventory_stale_blocker_parts/` | Concern modules the `package_inventory_stale_blocker.py` entry hook wires together: inventory detection, decision, and constants |
+| `inventory_intent_records/` | The shared per-session pending-intent store both inventory blockers read to break the file/row add-order deadlock |
+| `pii_prevention_blocker_parts/` | Concern modules the `pii_prevention_blocker.py` entry hook wires together: per-repository scan exemption, the per-repository allowlist of exact values a commit may carry, and resolving the repository a commit command targets (with `config/` for the resolution deny-message constants) |
+| `tests/` | pytest suite for `pii_prevention_blocker.py` repository resolution and the `pii_prevention_blocker_parts` modules |
 
 ## Core enforcer
 
@@ -83,7 +89,7 @@ The check modules it calls are the `code_rules_<concern>.py` files below.
 | `package_inventory_stale_blocker.py` | PreToolUse (Write) | A new production code file created in a directory whose `README.md`/`CLAUDE.md` inventory (or a parent skill's `SKILL.md` Layout table mapping the `scripts/` subdirectory) names two or more sibling files but no entry for the new file |
 | `pii_commit_command.py` | library | Token-aware git-commit detection reused by `pii_prevention_blocker.py` |
 | `pii_payload_scan.py` | library | Write/Edit and durable post-body PII evaluation reused by `pii_prevention_blocker.py` |
-| `pii_prevention_blocker.py` | PreToolUse (Write/Edit/MultiEdit/Bash/PowerShell/MCP GitHub) | Content that carries high-confidence personal data or secrets (real emails, home-dir paths, private IPs, credential material) on write, durable GitHub posts, or staged commit paths |
+| `pii_prevention_blocker.py` | PreToolUse (Write/Edit/MultiEdit/Bash/PowerShell/MCP GitHub) | Entry hook — content that carries high-confidence personal data or secrets (real emails, home-dir paths, private IPs, credential material) on write, durable GitHub posts, or staged commit paths; resolves the staged-commit repository from the command it gates (via `pii_prevention_blocker_parts`), not the session working directory |
 | `pii_scanner.py` | library | Pure text scanners shared by `pii_prevention_blocker.py` |
 | `plain_language_blocker.py` | PreToolUse (Write/Edit/AskUserQuestion) | Heavy or jargon words in user-facing prose |
 | `pr_converge_bugteam_enforcer.py` | PreToolUse | Enforces that bugteam runs in parallel with bugbot in pr-converge loops |

package/hooks/blocking/block_main_commit.py

@@ -80,7 +80,7 @@ def get_branch_at_directory(working_dir: str | None = None) -> str | None:
     try:
         completed_process = subprocess.run(
             ["git", "rev-parse", "--abbrev-ref", "HEAD"],
-            capture_output=True,
+            check=False, capture_output=True,
             text=True,
             timeout=GIT_COMMAND_TIMEOUT_SECONDS,
             cwd=working_dir,
@@ -99,7 +99,7 @@ def is_protected_repo(working_dir: str | None = None) -> bool:
     try:
         completed_process = subprocess.run(
             ["git", "remote", "get-url", "origin"],
-            capture_output=True,
+            check=False, capture_output=True,
             text=True,
             timeout=GIT_COMMAND_TIMEOUT_SECONDS,
             cwd=working_dir,