azclaude-copilot 0.4.23 → 0.4.24
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 +2 -2
- package/package.json +1 -1
- package/templates/agents/milestone-builder.md +9 -5
- package/templates/commands/audit.md +7 -1
- package/templates/commands/blueprint.md +7 -1
- package/templates/commands/doc.md +12 -0
- package/templates/commands/refactor.md +7 -2
- package/templates/commands/setup.md +13 -2
- package/templates/commands/test.md +12 -0
package/README.md
CHANGED
|
@@ -807,11 +807,11 @@ Run `/level-up` at any time to see your current level and build the next one.
|
|
|
807
807
|
|
|
808
808
|
## Verified
|
|
809
809
|
|
|
810
|
-
|
|
810
|
+
1421 tests. Every template, command, capability, agent, hook, and CLI feature verified.
|
|
811
811
|
|
|
812
812
|
```bash
|
|
813
813
|
bash tests/test-features.sh
|
|
814
|
-
# Results:
|
|
814
|
+
# Results: 1421 passed, 0 failed, 1421 total
|
|
815
815
|
```
|
|
816
816
|
|
|
817
817
|
---
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "azclaude-copilot",
|
|
3
|
-
"version": "0.4.
|
|
3
|
+
"version": "0.4.24",
|
|
4
4
|
"description": "AI coding environment — 34 commands, 9 skills, 15 agents, memory, reflexes, evolution. Install: npx azclaude-copilot@latest, then open Claude Code.",
|
|
5
5
|
"bin": {
|
|
6
6
|
"azclaude": "bin/cli.js",
|
|
@@ -40,15 +40,19 @@ If any item is missing → ask orchestrator before proceeding.
|
|
|
40
40
|
|
|
41
41
|
Read every file in the pre-read list. Order matters:
|
|
42
42
|
1. `.claude/constitution.md` — non-negotiables (if present — read FIRST, constraints before code)
|
|
43
|
-
2.
|
|
44
|
-
3.
|
|
45
|
-
4. Related
|
|
46
|
-
5.
|
|
47
|
-
6.
|
|
43
|
+
2. `.claude/code-rules.md` — coding standards contract (if present — read SECOND, style rules before code)
|
|
44
|
+
3. Schema / config files (structural constraints)
|
|
45
|
+
4. Related source files (existing patterns to match)
|
|
46
|
+
5. Related test files (test framework + naming conventions)
|
|
47
|
+
6. patterns.md entries for this area
|
|
48
|
+
7. antipatterns.md entries for this area
|
|
48
49
|
|
|
49
50
|
If constitution.md exists: keep its Non-Negotiables visible throughout implementation.
|
|
50
51
|
Flag any implementation choice that would violate them BEFORE writing — do not discover violations after the fact.
|
|
51
52
|
|
|
53
|
+
If code-rules.md exists: apply the relevant sections (naming, language, framework, testing) throughout implementation.
|
|
54
|
+
Flag any implementation choice that would violate a rule BEFORE writing the code.
|
|
55
|
+
|
|
52
56
|
Do NOT skip pre-reads. Context-blind implementation is the most common failure mode.
|
|
53
57
|
|
|
54
58
|
---
|
|
@@ -121,8 +121,14 @@ Report violations only — no code quality feedback until spec is clean.
|
|
|
121
121
|
If unavailable or empty: skip — proceed to manual checks.
|
|
122
122
|
If returns results: include errors and warnings in the report.
|
|
123
123
|
|
|
124
|
+
```bash
|
|
125
|
+
[ -f .claude/code-rules.md ] && echo "code-rules=found" || echo "no code-rules"
|
|
126
|
+
```
|
|
127
|
+
|
|
128
|
+
**If code-rules found:** read `.claude/code-rules.md` — use it as the primary convention checklist for this step (naming, style, testing, git). It overrides generic CLAUDE.md conventions for style questions.
|
|
129
|
+
|
|
124
130
|
Check:
|
|
125
|
-
- Follows project conventions from CLAUDE.md
|
|
131
|
+
- Follows project conventions from CLAUDE.md (and code-rules.md if present)
|
|
126
132
|
- No security anti-patterns (see shared/security.md)
|
|
127
133
|
- If developer domain: tests exist for new behavior (TDD Iron Law)
|
|
128
134
|
- Minimum necessary complexity — no over-engineering
|
|
@@ -101,11 +101,12 @@ State the risk level. If risk = high → recommend `EnterWorktree` during implem
|
|
|
101
101
|
|
|
102
102
|
---
|
|
103
103
|
|
|
104
|
-
## Step 3b: Constitution Check + Task Graph
|
|
104
|
+
## Step 3b: Constitution + Code Rules Check + Task Graph
|
|
105
105
|
|
|
106
106
|
After writing the plan (Step 3), check:
|
|
107
107
|
```bash
|
|
108
108
|
[ -f .claude/constitution.md ] && echo "constitution=found" || echo "no constitution"
|
|
109
|
+
[ -f .claude/code-rules.md ] && echo "code-rules=found" || echo "no code-rules"
|
|
109
110
|
```
|
|
110
111
|
|
|
111
112
|
If constitution found → scan plan steps against non-negotiables:
|
|
@@ -113,6 +114,11 @@ If constitution found → scan plan steps against non-negotiables:
|
|
|
113
114
|
- Flag any plan step that could violate a rule
|
|
114
115
|
- Add a note to flagged steps: `⚠ Constitution check: may conflict with "{rule}" — verify before implementing`
|
|
115
116
|
|
|
117
|
+
If code-rules found → read `## Architecture` section:
|
|
118
|
+
- The plan must respect the declared architecture pattern (Clean Architecture / DDD / MVC / etc.)
|
|
119
|
+
- If a plan step would introduce a pattern that conflicts with the architecture rule — flag it
|
|
120
|
+
- Add note: `⚠ Code rules: this step should follow {architecture pattern} — verify approach before implementing`
|
|
121
|
+
|
|
116
122
|
Then run `/tasks` to show dependency waves:
|
|
117
123
|
```
|
|
118
124
|
Next: Run /tasks to see which plan steps can run in parallel
|
|
@@ -16,6 +16,18 @@ $ARGUMENTS
|
|
|
16
16
|
|
|
17
17
|
---
|
|
18
18
|
|
|
19
|
+
## Pre-Flight: Code Rules Check
|
|
20
|
+
|
|
21
|
+
```bash
|
|
22
|
+
[ -f .claude/code-rules.md ] && echo "code-rules=found" || echo "no code-rules"
|
|
23
|
+
```
|
|
24
|
+
|
|
25
|
+
If code-rules found: read the `## Documentation` section.
|
|
26
|
+
It defines the required doc style (JSDoc on all public functions / inline comments only / none).
|
|
27
|
+
This overrides inferred style — code-rules is the authoritative answer for this project.
|
|
28
|
+
|
|
29
|
+
---
|
|
30
|
+
|
|
19
31
|
## Phase 1: Detect Scope
|
|
20
32
|
|
|
21
33
|
If $ARGUMENTS is blank, use **AskUserQuestion**:
|
|
@@ -18,16 +18,21 @@ Load: shared/completion-rule.md
|
|
|
18
18
|
|
|
19
19
|
---
|
|
20
20
|
|
|
21
|
-
## Pre-Flight: Constitution Check
|
|
21
|
+
## Pre-Flight: Constitution + Code Rules Check
|
|
22
22
|
|
|
23
23
|
```bash
|
|
24
24
|
[ -f .claude/constitution.md ] && echo "constitution=found" || echo "no constitution"
|
|
25
|
+
[ -f .claude/code-rules.md ] && echo "code-rules=found" || echo "no code-rules"
|
|
25
26
|
```
|
|
26
27
|
|
|
27
|
-
If found: read `## Architectural Commitments` and `## Required Patterns`.
|
|
28
|
+
If constitution found: read `## Architectural Commitments` and `## Required Patterns`.
|
|
28
29
|
Refactoring often changes structure — ensure the refactor moves TOWARD required patterns, not away from them.
|
|
29
30
|
If the refactor would conflict with an architectural commitment → flag before starting Phase 1. Do not proceed silently.
|
|
30
31
|
|
|
32
|
+
If code-rules found: read `.claude/code-rules.md` — the refactor must move code TOWARD these rules, not away from them.
|
|
33
|
+
The style, naming, and architecture sections define the TARGET state. Use them as the direction of the refactor.
|
|
34
|
+
If the current code violates a rule, the refactor is an opportunity to fix it — note the correction explicitly.
|
|
35
|
+
|
|
31
36
|
---
|
|
32
37
|
|
|
33
38
|
## Pre-Flight Analysis (intelligent-dispatch)
|
|
@@ -185,6 +185,17 @@ If constitution missing:
|
|
|
185
185
|
Copilot checks this before every milestone implementation.
|
|
186
186
|
```
|
|
187
187
|
|
|
188
|
+
If no coding rules found:
|
|
189
|
+
```bash
|
|
190
|
+
[ -f .claude/code-rules.md ] && echo "code-rules=found" || echo "code-rules=missing"
|
|
191
|
+
```
|
|
192
|
+
```
|
|
193
|
+
· No coding rules contract found.
|
|
194
|
+
Run: /driven
|
|
195
|
+
Why: generates .claude/code-rules.md — your project's coding standards.
|
|
196
|
+
Every /add, /fix, /refactor, /audit, /test, /doc, /blueprint reads this before writing code.
|
|
197
|
+
```
|
|
198
|
+
|
|
188
199
|
If no specs found:
|
|
189
200
|
```
|
|
190
201
|
· No feature specs found.
|
|
@@ -193,9 +204,9 @@ If no specs found:
|
|
|
193
204
|
Spec-first workflow: /spec → /clarify → /blueprint → /copilot
|
|
194
205
|
```
|
|
195
206
|
|
|
196
|
-
If
|
|
207
|
+
If all three exist:
|
|
197
208
|
```
|
|
198
|
-
✓ Constitution and specs found. Ready for /copilot.
|
|
209
|
+
✓ Constitution, coding rules, and specs found. Ready for /copilot.
|
|
199
210
|
```
|
|
200
211
|
|
|
201
212
|
---
|
|
@@ -16,6 +16,18 @@ $ARGUMENTS
|
|
|
16
16
|
|
|
17
17
|
---
|
|
18
18
|
|
|
19
|
+
## Pre-Flight: Code Rules Check
|
|
20
|
+
|
|
21
|
+
```bash
|
|
22
|
+
[ -f .claude/code-rules.md ] && echo "code-rules=found" || echo "no code-rules"
|
|
23
|
+
```
|
|
24
|
+
|
|
25
|
+
If code-rules found: read the `## Testing` section before writing or interpreting any tests.
|
|
26
|
+
Apply: TDD philosophy (mandatory / optional / test-after), test naming convention, coverage targets.
|
|
27
|
+
If writing new tests: follow the naming pattern from code-rules, not generic conventions.
|
|
28
|
+
|
|
29
|
+
---
|
|
30
|
+
|
|
19
31
|
## Step 1: IDE Diagnostics First
|
|
20
32
|
|
|
21
33
|
Use `mcp__ide__getDiagnostics` if available.
|