azclaude-copilot 0.4.7 → 0.4.9

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -477,11 +477,11 @@ See [SECURITY.md](SECURITY.md) for full details.
477
477
 
478
478
  ## Verified
479
479
 
480
- 1197 tests. Every template, command, capability, agent, hook, and CLI feature verified.
480
+ 1196 tests. Every template, command, capability, agent, hook, and CLI feature verified.
481
481
 
482
482
  ```bash
483
483
  bash tests/test-features.sh
484
- # Results: 1197 passed, 0 failed, 1197 total
484
+ # Results: 1196 passed, 0 failed, 1196 total
485
485
  ```
486
486
 
487
487
  ---
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "azclaude-copilot",
3
- "version": "0.4.7",
3
+ "version": "0.4.9",
4
4
  "description": "AI coding environment — 26 commands, 8 skills, 10 agents, memory, reflexes, evolution. Install: npm install -g azclaude-copilot@latest, then in Claude Code: azclaude-copilot setup --full",
5
5
  "bin": {
6
6
  "azclaude": "bin/cli.js",
@@ -30,13 +30,8 @@ ls .claude/agents/security-auditor.md 2>/dev/null && echo "agent=found" || echo
30
30
  ```
31
31
 
32
32
  If `agent=found`:
33
- ```
34
- Spawn security-auditor agent with:
35
- Task: Full security scan — all 5 categories, 102 rules
36
- Scope: $ARGUMENTS (default: --all)
37
- Return: Security Report in standard format
38
- ```
39
- Display the returned Security Report and **ExitPlanMode**. Done — do not run layers below.
33
+ Read `.claude/agents/security-auditor.md` and execute the full scan inline using the agent's instructions and rule set. This gives the full 102-rule scan without requiring a subprocess.
34
+ Display the Security Report and **ExitPlanMode**. Done — do not run layers below.
40
35
 
41
36
  If `agent=missing`: continue with manual layers below.
42
37
 
@@ -63,7 +58,12 @@ Check if hooks were modified outside of AZCLAUDE.
63
58
 
64
59
  ```bash
65
60
  INTEGRITY="$HOME/.claude/.azclaude-integrity"
66
- SETTINGS="$HOME/.claude/settings.json"
61
+ # Windows stores settings at %APPDATA%\Claude\settings.json, Unix/Mac at ~/.claude/settings.json
62
+ if [ -n "$APPDATA" ]; then
63
+ SETTINGS="$APPDATA/Claude/settings.json"
64
+ else
65
+ SETTINGS="$HOME/.claude/settings.json"
66
+ fi
67
67
  [ -f "$INTEGRITY" ] && echo "integrity_file=found" || echo "integrity_file=missing"
68
68
  [ -f "$SETTINGS" ] && echo "settings_file=found" || echo "settings_file=missing"
69
69
  ```
@@ -95,7 +95,10 @@ For each `.js` / `.sh` hook found, flag:
95
95
  Check Claude Code settings for over-permissioned configurations.
96
96
 
97
97
  ```bash
98
- cat "$HOME/.claude/settings.json" 2>/dev/null | head -80
98
+ # Windows: %APPDATA%\Claude\settings.json — Unix/Mac: ~/.claude/settings.json
99
+ SETTINGS="${APPDATA:+$APPDATA/Claude/settings.json}"
100
+ SETTINGS="${SETTINGS:-$HOME/.claude/settings.json}"
101
+ cat "$SETTINGS" 2>/dev/null | head -80
99
102
  cat .claude/settings.local.json 2>/dev/null
100
103
  ```
101
104
 
@@ -219,5 +219,5 @@ let editCount = 1;
219
219
  try { editCount = parseInt(fs.readFileSync(counterPath, 'utf8'), 10) + 1; } catch (_) {}
220
220
  try { fs.writeFileSync(counterPath, String(editCount)); } catch (_) {}
221
221
  if (editCount > 0 && editCount % 15 === 0) {
222
- process.stderr.write(`\n⚠ ${editCount} edits this session — run /snapshot before context compaction loses your reasoning\n`);
222
+ process.stdout.write(`\n⚠ ${editCount} edits this session — run /snapshot before context compaction loses your reasoning\n`);
223
223
  }