oh-my-customcodex 0.3.2 → 0.3.4
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 +16 -16
- package/dist/cli/index.js +1 -1
- package/dist/index.js +1 -1
- package/package.json +1 -1
- package/templates/.claude/hooks/scripts/adaptive-harness-scan.sh +3 -3
- package/templates/.claude/rules/MUST-continuous-improvement.md +1 -1
- package/templates/.claude/rules/MUST-sync-verification.md +3 -3
- package/templates/.claude/rules/SHOULD-wiki-sync.md +6 -6
- package/templates/.claude/skills/adaptive-harness/SKILL.md +11 -11
- package/templates/.claude/skills/agora/SKILL.md +5 -5
- package/templates/.claude/skills/analysis/SKILL.md +3 -3
- package/templates/.claude/skills/audit-agents/SKILL.md +1 -1
- package/templates/.claude/skills/claude-native/SKILL.md +5 -5
- package/templates/.claude/skills/create-agent/SKILL.md +1 -1
- package/templates/.claude/skills/dev-refactor/SKILL.md +3 -3
- package/templates/.claude/skills/evaluator-optimizer/SKILL.md +1 -1
- package/templates/.claude/skills/fix-refs/SKILL.md +1 -1
- package/templates/.claude/skills/harness-eval/SKILL.md +4 -4
- package/templates/.claude/skills/help/SKILL.md +1 -1
- package/templates/.claude/skills/lists/SKILL.md +1 -1
- package/templates/.claude/skills/monitoring-setup/SKILL.md +1 -1
- package/templates/.claude/skills/npm-audit/SKILL.md +1 -1
- package/templates/.claude/skills/npm-publish/SKILL.md +1 -1
- package/templates/.claude/skills/npm-version/SKILL.md +1 -1
- package/templates/.claude/skills/omcodex-auto-improve/SKILL.md +4 -4
- package/templates/.claude/skills/omcodex-feedback/SKILL.md +10 -10
- package/templates/.claude/skills/omcodex-improve-report/SKILL.md +2 -2
- package/templates/.claude/skills/omcodex-loop/SKILL.md +4 -4
- package/templates/.claude/skills/omcodex-release-notes/SKILL.md +5 -5
- package/templates/.claude/skills/omcodex-takeover/SKILL.md +4 -4
- package/templates/.claude/skills/omcodex-web/SKILL.md +4 -4
- package/templates/.claude/skills/sauron-watch/SKILL.md +1 -1
- package/templates/.claude/skills/scout/SKILL.md +1 -1
- package/templates/.claude/skills/status/SKILL.md +1 -1
- package/templates/.claude/skills/update-docs/SKILL.md +1 -1
- package/templates/.claude/skills/update-external/SKILL.md +1 -1
- package/templates/.claude/skills/wiki/SKILL.md +9 -9
- package/templates/.claude/skills/wiki-rag/SKILL.md +6 -6
- package/templates/AGENTS.md.en +22 -22
- package/templates/AGENTS.md.ko +22 -22
- package/templates/CLAUDE.md +12 -12
- package/templates/CLAUDE.md.en +22 -22
- package/templates/CLAUDE.md.ko +22 -22
- package/templates/manifest.json +2 -2
package/README.md
CHANGED
|
@@ -175,29 +175,29 @@ All commands are invoked inside the oh-my-customcodex GPT Codex + OMX session.
|
|
|
175
175
|
|
|
176
176
|
| Command | What it does |
|
|
177
177
|
|---------|-------------|
|
|
178
|
-
| `/
|
|
179
|
-
| `/
|
|
180
|
-
| `/
|
|
178
|
+
| `/omcustomcodex:analysis` | Analyze project, auto-configure agents and skills |
|
|
179
|
+
| `/omcustomcodex:create-agent` | Create a new agent |
|
|
180
|
+
| `/omcustomcodex:takeover` | Extract canonical spec from existing agent or skill |
|
|
181
181
|
| `/idea` | Turn a natural-language idea into structured issue specs |
|
|
182
|
-
| `/
|
|
183
|
-
| `/
|
|
184
|
-
| `/
|
|
185
|
-
| `/
|
|
182
|
+
| `/omcustomcodex:audit-agents` | Audit agent dependencies |
|
|
183
|
+
| `/omcustomcodex:update-docs` | Sync project structure and documentation |
|
|
184
|
+
| `/omcustomcodex:sauron-watch` | Full structural verification (5+3 rounds) |
|
|
185
|
+
| `/omcustomcodex:feedback` | Submit feedback as GitHub issue |
|
|
186
186
|
|
|
187
187
|
### Web UI
|
|
188
188
|
|
|
189
189
|
| Command | What it does |
|
|
190
190
|
|---------|-------------|
|
|
191
|
-
| `/
|
|
191
|
+
| `/omcustomcodex:web` | Control built-in Web UI (start, stop, status, open) |
|
|
192
192
|
|
|
193
193
|
### Package & Release
|
|
194
194
|
|
|
195
195
|
| Command | What it does |
|
|
196
196
|
|---------|-------------|
|
|
197
|
-
| `/
|
|
198
|
-
| `/
|
|
199
|
-
| `/
|
|
200
|
-
| `/
|
|
197
|
+
| `/omcustomcodex:npm-publish` | Publish to npm |
|
|
198
|
+
| `/omcustomcodex:npm-version` | Semantic versioning |
|
|
199
|
+
| `/omcustomcodex:npm-audit` | Dependency security audit |
|
|
200
|
+
| `/omcustomcodex-release-notes` | Generate release notes from git history |
|
|
201
201
|
|
|
202
202
|
### Memory & System
|
|
203
203
|
|
|
@@ -205,11 +205,11 @@ All commands are invoked inside the oh-my-customcodex GPT Codex + OMX session.
|
|
|
205
205
|
|---------|-------------|
|
|
206
206
|
| `/memory-save` | Save session context |
|
|
207
207
|
| `/memory-recall` | Search and recall memories |
|
|
208
|
-
| `/
|
|
208
|
+
| `/omcustomcodex:monitoring-setup` | OTel monitoring toggle |
|
|
209
209
|
| `/token-efficiency-audit` | Audit and tune token-efficiency settings |
|
|
210
|
-
| `/
|
|
211
|
-
| `/
|
|
212
|
-
| `/
|
|
210
|
+
| `/omcustomcodex:loop` | Auto-continue background agent workflows (3-continue safety limit) |
|
|
211
|
+
| `/omcustomcodex:lists` | Show all commands |
|
|
212
|
+
| `/omcustomcodex:status` | System health check |
|
|
213
213
|
|
|
214
214
|
---
|
|
215
215
|
|
package/dist/cli/index.js
CHANGED
package/dist/index.js
CHANGED
package/package.json
CHANGED
|
@@ -13,14 +13,14 @@ if [ -f "$PROJECT_ROOT/.codex/skills/adaptive-harness/SKILL.md" ] && \
|
|
|
13
13
|
grep -q "oh-my-customcodex" "$PROJECT_ROOT/AGENTS.md" 2>/dev/null; then
|
|
14
14
|
# Only check if profile exists for the meta-project
|
|
15
15
|
if [ ! -f "$PROFILE" ]; then
|
|
16
|
-
echo "[adaptive-harness] No project profile found. Run /
|
|
16
|
+
echo "[adaptive-harness] No project profile found. Run /omcustomcodex:adaptive-harness --scan to generate." >&2
|
|
17
17
|
fi
|
|
18
18
|
exit 0
|
|
19
19
|
fi
|
|
20
20
|
|
|
21
21
|
# For non-omcodex projects
|
|
22
22
|
if [ ! -f "$PROFILE" ]; then
|
|
23
|
-
echo "[adaptive-harness] No project profile found. Run /
|
|
23
|
+
echo "[adaptive-harness] No project profile found. Run /omcustomcodex:adaptive-harness --scan to auto-configure harness." >&2
|
|
24
24
|
exit 0
|
|
25
25
|
fi
|
|
26
26
|
|
|
@@ -39,7 +39,7 @@ for indicator in package.json go.mod Cargo.toml requirements.txt pyproject.toml
|
|
|
39
39
|
done
|
|
40
40
|
|
|
41
41
|
if [ "$STALE" = true ]; then
|
|
42
|
-
echo "[adaptive-harness] Project profile may be stale. Consider running /
|
|
42
|
+
echo "[adaptive-harness] Project profile may be stale. Consider running /omcustomcodex:adaptive-harness --scan" >&2
|
|
43
43
|
fi
|
|
44
44
|
|
|
45
45
|
exit 0
|
|
@@ -43,7 +43,7 @@ When CI failure, process gap, or repeatable system defect is found:
|
|
|
43
43
|
|
|
44
44
|
When repeating agent failures or suboptimal routing is detected:
|
|
45
45
|
1. Record as feedback memory (immediate session defense)
|
|
46
|
-
2. Run `/
|
|
46
|
+
2. Run `/omcustomcodex:adaptive-harness --learn` to update project profile with failure patterns
|
|
47
47
|
3. Profile updates improve future agent selection and harness optimization
|
|
48
48
|
|
|
49
49
|
This connects R016's continuous improvement loop with the adaptive-harness skill's learning capability.
|
|
@@ -32,9 +32,9 @@ Also run: mgr-claude-code-bible:verify (official spec compliance)
|
|
|
32
32
|
|
|
33
33
|
| Check | Action |
|
|
34
34
|
|-------|--------|
|
|
35
|
-
| Missing pages | Source entities without wiki pages → run `/
|
|
36
|
-
| Stale pages | Source modification date newer than wiki `updated` field → run `/
|
|
37
|
-
| Broken cross-refs | Wiki links pointing to non-existent pages → run `/
|
|
35
|
+
| Missing pages | Source entities without wiki pages → run `/omcustomcodex:wiki` |
|
|
36
|
+
| Stale pages | Source modification date newer than wiki `updated` field → run `/omcustomcodex:wiki ingest <path>` |
|
|
37
|
+
| Broken cross-refs | Wiki links pointing to non-existent pages → run `/omcustomcodex:wiki lint` |
|
|
38
38
|
| index.md accuracy | Wiki index page count matches actual page count |
|
|
39
39
|
|
|
40
40
|
Wiki verification is also enforced by CI (`.github/workflows/wiki-sync.yml`).
|
|
@@ -17,15 +17,15 @@ When agents, skills, rules, or guides are created or modified, corresponding wik
|
|
|
17
17
|
| Rule created/modified | Update wiki/rules/r{nnn}.md |
|
|
18
18
|
| Guide created/modified | Update wiki/guides/{name}.md |
|
|
19
19
|
| Architecture change | Update wiki/architecture/ pages |
|
|
20
|
-
| Multiple changes | Run `/
|
|
20
|
+
| Multiple changes | Run `/omcustomcodex:wiki` for full update |
|
|
21
21
|
|
|
22
22
|
## How to Sync
|
|
23
23
|
|
|
24
24
|
| Method | When |
|
|
25
25
|
|--------|------|
|
|
26
|
-
| `/
|
|
27
|
-
| `/
|
|
28
|
-
| `/
|
|
26
|
+
| `/omcustomcodex:wiki ingest <path>` | Single file/directory changed |
|
|
27
|
+
| `/omcustomcodex:wiki` | Multiple files changed or periodic refresh |
|
|
28
|
+
| `/omcustomcodex:wiki lint` | After major structural changes |
|
|
29
29
|
| Automatic (CI) | `.github/workflows/wiki-sync.yml` checks on PR |
|
|
30
30
|
|
|
31
31
|
## Delegation — All wiki writes via wiki-curator agent (R010). See workflow via Read tool.
|
|
@@ -59,7 +59,7 @@ Orchestrator
|
|
|
59
59
|
|
|
60
60
|
## CI Enforcement
|
|
61
61
|
|
|
62
|
-
`.github/workflows/wiki-sync.yml` checks for missing wiki pages on every PR. Missing pages cause CI failure with guidance to run `/
|
|
62
|
+
`.github/workflows/wiki-sync.yml` checks for missing wiki pages on every PR. Missing pages cause CI failure with guidance to run `/omcustomcodex:wiki`.
|
|
63
63
|
|
|
64
64
|
## Self-Check — 3 checks: wiki pages updated, index refreshed, lint passed. See details via Read tool.
|
|
65
65
|
|
|
@@ -69,5 +69,5 @@ Before completing a session that modified agents/skills/rules/guides:
|
|
|
69
69
|
2. Was index.md refreshed?
|
|
70
70
|
3. Did wiki lint pass?
|
|
71
71
|
|
|
72
|
-
If any NO → run `/
|
|
72
|
+
If any NO → run `/omcustomcodex:wiki ingest` for affected paths.
|
|
73
73
|
-->
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:adaptive-harness
|
|
3
3
|
description: Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile
|
|
4
4
|
scope: harness
|
|
5
5
|
version: 1.0.0
|
|
@@ -15,13 +15,13 @@ Automatically detects project context and optimizes the oh-my-customcodex harnes
|
|
|
15
15
|
## Usage
|
|
16
16
|
|
|
17
17
|
```
|
|
18
|
-
/
|
|
19
|
-
/
|
|
20
|
-
/
|
|
21
|
-
/
|
|
22
|
-
/
|
|
23
|
-
/
|
|
24
|
-
/
|
|
18
|
+
/omcustomcodex:adaptive-harness # Full scan + optimize
|
|
19
|
+
/omcustomcodex:adaptive-harness --scan # Scan only (generate/update project profile)
|
|
20
|
+
/omcustomcodex:adaptive-harness --optimize # Deactivate unused, suggest missing
|
|
21
|
+
/omcustomcodex:adaptive-harness --learn # Analyze failure patterns, update profile
|
|
22
|
+
/omcustomcodex:adaptive-harness --export # Export profile as portable bundle
|
|
23
|
+
/omcustomcodex:adaptive-harness --import <path> # Import profile from another project
|
|
24
|
+
/omcustomcodex:adaptive-harness --dry-run # Show what would change without modifying
|
|
25
25
|
```
|
|
26
26
|
|
|
27
27
|
Default (no flag): runs `--scan` then `--optimize` in sequence.
|
|
@@ -234,7 +234,7 @@ Analyzes session history and eval-core data to populate `usage_stats` and `failu
|
|
|
234
234
|
|
|
235
235
|
- `.codex/outputs/` — session artifacts and eval results
|
|
236
236
|
- `.codex/agent-memory/` — agent memory files with usage patterns
|
|
237
|
-
- Any harness eval output from `/
|
|
237
|
+
- Any harness eval output from `/omcustomcodex:harness-eval`
|
|
238
238
|
|
|
239
239
|
### Step 2: Extract Patterns
|
|
240
240
|
|
|
@@ -301,7 +301,7 @@ Output: `.codex/outputs/harness-bundle-YYYY-MM-DD.json`
|
|
|
301
301
|
### Import
|
|
302
302
|
|
|
303
303
|
```
|
|
304
|
-
/
|
|
304
|
+
/omcustomcodex:adaptive-harness --import .codex/outputs/harness-bundle-2026-04-12.json
|
|
305
305
|
```
|
|
306
306
|
|
|
307
307
|
Reads the bundle and applies the `active_agents` list to the current project by running `--optimize` with the imported profile. Does not overwrite `usage_stats` or `failure_patterns` from the current project.
|
|
@@ -319,7 +319,7 @@ Reads the bundle and applies the `active_agents` list to the current project by
|
|
|
319
319
|
|
|
320
320
|
| Component | Interaction |
|
|
321
321
|
|-----------|-------------|
|
|
322
|
-
| `/
|
|
322
|
+
| `/omcustomcodex:analysis` | Calls adaptive-harness `--scan` after initial tech stack detection to persist the profile |
|
|
323
323
|
| `SessionStart` hook | Lightweight profile existence check only — no full scan at startup |
|
|
324
324
|
| `mgr-creator` | Invoked when gaps are detected during `--optimize` to create missing agent files |
|
|
325
325
|
| `R016` (Continuous Improvement) | Failure patterns from `--learn` may trigger rule updates |
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:agora
|
|
3
3
|
description: "Multi-LLM adversarial consensus loop — 3+ LLMs compete to find flaws in designs/specs until unanimous agreement is reached"
|
|
4
4
|
user-invocable: true
|
|
5
5
|
argument-hint: "<document-path> [--rounds N] [--severity-threshold HIGH]"
|
|
@@ -26,10 +26,10 @@ source:
|
|
|
26
26
|
## Usage
|
|
27
27
|
|
|
28
28
|
```
|
|
29
|
-
/
|
|
30
|
-
/
|
|
31
|
-
/
|
|
32
|
-
/
|
|
29
|
+
/omcustomcodex:agora docs/design.md # Default: 3 LLMs, unlimited rounds
|
|
30
|
+
/omcustomcodex:agora docs/design.md --rounds 10 # Max 10 rounds
|
|
31
|
+
/omcustomcodex:agora docs/design.md --severity-threshold HIGH # Exit when no HIGH+ findings
|
|
32
|
+
/omcustomcodex:agora docs/design.md --models claude,codex # 2 LLMs only
|
|
33
33
|
```
|
|
34
34
|
|
|
35
35
|
## Workflow
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:analysis
|
|
3
3
|
description: Analyze project and auto-configure agents, skills, rules, and guides
|
|
4
4
|
scope: harness
|
|
5
5
|
argument-hint: "[target-dir] [--interview]"
|
|
@@ -193,8 +193,8 @@ After analysis completes, offer adaptive-harness optimization:
|
|
|
193
193
|
|
|
194
194
|
```
|
|
195
195
|
[Analysis Complete] Tech stack detected. Optimize harness for this project?
|
|
196
|
-
├── Yes → Run /
|
|
197
|
-
├── Dry-run → Run /
|
|
196
|
+
├── Yes → Run /omcustomcodex:adaptive-harness --optimize (deactivate unused, suggest missing)
|
|
197
|
+
├── Dry-run → Run /omcustomcodex:adaptive-harness --optimize --dry-run (show changes only)
|
|
198
198
|
└── Skip → Keep current harness configuration
|
|
199
199
|
```
|
|
200
200
|
|
|
@@ -105,7 +105,7 @@ Issue body format (matching the pattern established by issue #683):
|
|
|
105
105
|
|
|
106
106
|
---
|
|
107
107
|
|
|
108
|
-
_This issue was created by the `/
|
|
108
|
+
_This issue was created by the `/omcustomcodex:claude-native` skill._
|
|
109
109
|
```
|
|
110
110
|
|
|
111
111
|
**Notes:**
|
|
@@ -171,9 +171,9 @@ Semver comparison: major → minor → patch (all numeric). Pre-release suffixes
|
|
|
171
171
|
### Manual
|
|
172
172
|
|
|
173
173
|
```
|
|
174
|
-
/
|
|
175
|
-
/
|
|
176
|
-
/
|
|
174
|
+
/omcustomcodex:claude-native
|
|
175
|
+
/omcustomcodex:claude-native --backfill
|
|
176
|
+
/omcustomcodex:claude-native --dry-run
|
|
177
177
|
```
|
|
178
178
|
|
|
179
179
|
### Automatic (SessionStart Hook)
|
|
@@ -197,7 +197,7 @@ A lightweight wrapper script can run a `--dry-run` check and notify if new relea
|
|
|
197
197
|
Can be set up as a scheduled remote agent using `/schedule`:
|
|
198
198
|
|
|
199
199
|
```
|
|
200
|
-
/schedule "daily at 9am: /
|
|
200
|
+
/schedule "daily at 9am: /omcustomcodex:claude-native"
|
|
201
201
|
```
|
|
202
202
|
|
|
203
203
|
Or via CronCreate MCP tool for programmatic scheduling.
|
|
@@ -206,8 +206,8 @@ When the `--spec` flag is present, refactoring is guided by the target's canonic
|
|
|
206
206
|
|
|
207
207
|
### Workflow
|
|
208
208
|
|
|
209
|
-
1. **Load spec**: Read `.codex/specs/<agent-name>.spec.md` (generated by `/
|
|
210
|
-
- If spec doesn't exist, run takeover first: `/
|
|
209
|
+
1. **Load spec**: Read `.codex/specs/<agent-name>.spec.md` (generated by `/omcustomcodex:takeover`)
|
|
210
|
+
- If spec doesn't exist, run takeover first: `/omcustomcodex:takeover <name>`
|
|
211
211
|
2. **Extract invariants**: Parse the spec's `## Invariants` section as pre-flight guard constraints
|
|
212
212
|
3. **Refactor**: Perform normal refactoring (per existing workflow)
|
|
213
213
|
4. **Verify invariants**: After refactoring, check each invariant still holds:
|
|
@@ -217,7 +217,7 @@ When the `--spec` flag is present, refactoring is guided by the target's canonic
|
|
|
217
217
|
├── ✓ Invariant 2: {description} — PASS
|
|
218
218
|
└── ✗ Invariant 3: {description} — FAIL (reason)
|
|
219
219
|
```
|
|
220
|
-
5. **Regenerate spec**: If refactoring changed the contract, run `/
|
|
220
|
+
5. **Regenerate spec**: If refactoring changed the contract, run `/omcustomcodex:takeover <name>` to update
|
|
221
221
|
|
|
222
222
|
### When to Use
|
|
223
223
|
|
|
@@ -418,4 +418,4 @@ Integration: Works with [impeccable-design](/skills/impeccable-design) skill for
|
|
|
418
418
|
|
|
419
419
|
### Harness Eval Preset
|
|
420
420
|
|
|
421
|
-
The `harness-eval` skill provides a structured 15-task SE benchmark rubric that can be used as a preset for the evaluator-optimizer pipeline. When invoked via `/
|
|
421
|
+
The `harness-eval` skill provides a structured 15-task SE benchmark rubric that can be used as a preset for the evaluator-optimizer pipeline. When invoked via `/omcustomcodex:harness-eval`, the harness rubric dimensions (Test Coverage 30%, Architecture 25%, Error Handling 25%, Extensibility 20%) are loaded as the sprint contract criteria.
|
|
@@ -17,9 +17,9 @@ Evaluate agent quality using 15 structured software engineering task definitions
|
|
|
17
17
|
## Usage
|
|
18
18
|
|
|
19
19
|
```
|
|
20
|
-
/
|
|
21
|
-
/
|
|
22
|
-
/
|
|
20
|
+
/omcustomcodex:harness-eval # Run all 15 benchmarks
|
|
21
|
+
/omcustomcodex:harness-eval --preset quick # Run top 5 high-impact benchmarks
|
|
22
|
+
/omcustomcodex:harness-eval --task api-design # Run specific task benchmark
|
|
23
23
|
```
|
|
24
24
|
|
|
25
25
|
## Quality Dimensions
|
|
@@ -81,7 +81,7 @@ Run top 5 high-impact tasks (1, 3, 4, 5, 12). Quick evaluation ~15 minutes.
|
|
|
81
81
|
This skill provides preset rubrics for the evaluator-optimizer pipeline:
|
|
82
82
|
|
|
83
83
|
```
|
|
84
|
-
/
|
|
84
|
+
/omcustomcodex:harness-eval → loads rubric → evaluator-optimizer executes → scoring → report
|
|
85
85
|
```
|
|
86
86
|
|
|
87
87
|
The evaluator-optimizer skill's `pre_negotiation` phase accepts harness-eval rubric dimensions as sprint contract criteria.
|
|
@@ -1,12 +1,12 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:auto-improve
|
|
3
3
|
description: Apply verified improvement suggestions from eval-core analysis to omcodex configuration
|
|
4
4
|
scope: harness
|
|
5
5
|
user-invocable: true
|
|
6
6
|
effort: high
|
|
7
7
|
---
|
|
8
8
|
|
|
9
|
-
# /
|
|
9
|
+
# /omcustomcodex:auto-improve — Automated Improvement Workflow
|
|
10
10
|
|
|
11
11
|
## Purpose
|
|
12
12
|
|
|
@@ -15,12 +15,12 @@ Reads improvement suggestions from eval-core analysis, lets the user select whic
|
|
|
15
15
|
## Usage
|
|
16
16
|
|
|
17
17
|
```
|
|
18
|
-
/
|
|
18
|
+
/omcustomcodex:auto-improve # Interactive selection from pending suggestions
|
|
19
19
|
```
|
|
20
20
|
|
|
21
21
|
## Prerequisites
|
|
22
22
|
|
|
23
|
-
- eval-core analysis data exists (run `/
|
|
23
|
+
- eval-core analysis data exists (run `/omcustomcodex:improve-report` first if empty)
|
|
24
24
|
- Pending improvement suggestions in `proposed` status
|
|
25
25
|
|
|
26
26
|
## Workflow
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:feedback
|
|
3
3
|
description: Submit feedback about oh-my-customcodex (supports anonymous submission)
|
|
4
4
|
scope: harness
|
|
5
5
|
user-invocable: true
|
|
@@ -19,13 +19,13 @@ Lowers the barrier for submitting feedback by allowing users to create GitHub is
|
|
|
19
19
|
|
|
20
20
|
```
|
|
21
21
|
# Inline feedback
|
|
22
|
-
/
|
|
22
|
+
/omcustomcodex:feedback HUD display is missing during parallel agent spawn
|
|
23
23
|
|
|
24
24
|
# Anonymous submission
|
|
25
|
-
/
|
|
25
|
+
/omcustomcodex:feedback --anonymous Something feels off with the routing
|
|
26
26
|
|
|
27
27
|
# Interactive (no arguments)
|
|
28
|
-
/
|
|
28
|
+
/omcustomcodex:feedback
|
|
29
29
|
```
|
|
30
30
|
|
|
31
31
|
## Workflow
|
|
@@ -109,7 +109,7 @@ For anonymous submissions, do NOT include the project name. Offer to include pro
|
|
|
109
109
|
|
|
110
110
|
4. Ensure labels exist (defensive):
|
|
111
111
|
```bash
|
|
112
|
-
gh label create feedback --description "User feedback via /
|
|
112
|
+
gh label create feedback --description "User feedback via /omcustomcodex:feedback" --color 0E8A16 --repo baekenough/oh-my-customcodex 2>/dev/null || true
|
|
113
113
|
# If anonymous, ensure the anonymous label exists
|
|
114
114
|
if [ "$ANONYMOUS" = "true" ]; then
|
|
115
115
|
gh label create anonymous --description "Anonymous feedback submission" --color C5DEF5 --repo baekenough/oh-my-customcodex 2>/dev/null || true
|
|
@@ -119,7 +119,7 @@ For anonymous submissions, do NOT include the project name. Offer to include pro
|
|
|
119
119
|
5. Create the issue using `--body-file` for safe markdown handling:
|
|
120
120
|
```bash
|
|
121
121
|
# Write body to temp file to avoid shell escaping issues
|
|
122
|
-
cat > /tmp/
|
|
122
|
+
cat > /tmp/omcustomcodex-feedback-body.md << 'FEEDBACK_EOF'
|
|
123
123
|
## Feedback
|
|
124
124
|
|
|
125
125
|
**Category**: {category}
|
|
@@ -135,7 +135,7 @@ For anonymous submissions, do NOT include the project name. Offer to include pro
|
|
|
135
135
|
- Project: {project_name}
|
|
136
136
|
|
|
137
137
|
---
|
|
138
|
-
*Submitted via `/
|
|
138
|
+
*Submitted via `/omcustomcodex:feedback`*
|
|
139
139
|
FEEDBACK_EOF
|
|
140
140
|
|
|
141
141
|
# Build label string
|
|
@@ -149,10 +149,10 @@ For anonymous submissions, do NOT include the project name. Offer to include pro
|
|
|
149
149
|
--repo baekenough/oh-my-customcodex \
|
|
150
150
|
--title "{title}" \
|
|
151
151
|
--label "$LABELS" \
|
|
152
|
-
--body-file /tmp/
|
|
152
|
+
--body-file /tmp/omcustomcodex-feedback-body.md
|
|
153
153
|
|
|
154
154
|
# Clean up
|
|
155
|
-
rm -f /tmp/
|
|
155
|
+
rm -f /tmp/omcustomcodex-feedback-body.md
|
|
156
156
|
```
|
|
157
157
|
|
|
158
158
|
6. If label creation fails AND issue creation fails due to labels, retry without labels as fallback
|
|
@@ -183,7 +183,7 @@ Inform the user:
|
|
|
183
183
|
[Saved] Feedback saved locally to ~/.omcodex/feedback/{timestamp}.json
|
|
184
184
|
Submit manually when connectivity is available:
|
|
185
185
|
- GitHub Issues: https://github.com/baekenough/oh-my-customcodex/issues/new
|
|
186
|
-
- Or run /
|
|
186
|
+
- Or run /omcustomcodex:feedback again when gh is available
|
|
187
187
|
```
|
|
188
188
|
|
|
189
189
|
### Category-to-Label Mapping
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:improve-report
|
|
3
3
|
description: Read-only report of improvement suggestions from eval-core analysis engine
|
|
4
4
|
scope: harness
|
|
5
5
|
user-invocable: true
|
|
@@ -16,7 +16,7 @@ Surface actionable improvement suggestions gathered by the eval-core analysis en
|
|
|
16
16
|
## Usage
|
|
17
17
|
|
|
18
18
|
```
|
|
19
|
-
/
|
|
19
|
+
/omcustomcodex:improve-report
|
|
20
20
|
```
|
|
21
21
|
|
|
22
22
|
## Workflow
|
|
@@ -1,12 +1,12 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:loop
|
|
3
3
|
description: Prevent session idle during background agent work via SubagentStop prompt hook auto-continuation
|
|
4
4
|
scope: core
|
|
5
5
|
version: 1.0.0
|
|
6
6
|
user-invocable: true
|
|
7
7
|
---
|
|
8
8
|
|
|
9
|
-
# /
|
|
9
|
+
# /omcustomcodex:loop — Session Auto-Continuation
|
|
10
10
|
|
|
11
11
|
## Overview
|
|
12
12
|
|
|
@@ -38,8 +38,8 @@ The hook is configured in `.codex/hooks/hooks.json` under `SubagentStop`. It wor
|
|
|
38
38
|
## Usage
|
|
39
39
|
|
|
40
40
|
```bash
|
|
41
|
-
/
|
|
42
|
-
/
|
|
41
|
+
/omcustomcodex:loop # Show current auto-continuation status
|
|
42
|
+
/omcustomcodex:loop status # Same as above
|
|
43
43
|
```
|
|
44
44
|
|
|
45
45
|
The feature is active by default via hooks.json. No explicit activation needed.
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex-release-notes
|
|
3
3
|
description: Generate structured release notes from git history and closed issues within the GPT Codex + OMX session
|
|
4
4
|
scope: harness
|
|
5
5
|
user-invocable: true
|
|
@@ -17,8 +17,8 @@ Replaces the CI-based `release-notes.yml` workflow that previously used Claude A
|
|
|
17
17
|
## Usage
|
|
18
18
|
|
|
19
19
|
```
|
|
20
|
-
/
|
|
21
|
-
/
|
|
20
|
+
/omcustomcodex-release-notes 0.36.0
|
|
21
|
+
/omcustomcodex-release-notes 0.36.0 --previous-tag v0.35.3
|
|
22
22
|
```
|
|
23
23
|
|
|
24
24
|
## Workflow
|
|
@@ -104,8 +104,8 @@ The generated notes can be:
|
|
|
104
104
|
This skill is designed to be used during the release process:
|
|
105
105
|
|
|
106
106
|
```
|
|
107
|
-
/
|
|
108
|
-
/
|
|
107
|
+
/omcustomcodex:npm-version patch|minor|major -> version bump
|
|
108
|
+
/omcustomcodex-release-notes {version} -> generate notes
|
|
109
109
|
mgr-gitnerd: gh release create -> create release with notes
|
|
110
110
|
```
|
|
111
111
|
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:takeover
|
|
3
3
|
description: Extract canonical spec from existing agent or skill files
|
|
4
4
|
scope: harness
|
|
5
5
|
user-invocable: true
|
|
@@ -17,8 +17,8 @@ When an agent or skill has evolved organically without a formal spec, `omcodex:t
|
|
|
17
17
|
## Usage
|
|
18
18
|
|
|
19
19
|
```
|
|
20
|
-
/
|
|
21
|
-
/
|
|
20
|
+
/omcustomcodex:takeover <agent-name>
|
|
21
|
+
/omcustomcodex:takeover <skill-name>
|
|
22
22
|
```
|
|
23
23
|
|
|
24
24
|
## Workflow
|
|
@@ -110,6 +110,6 @@ generated: <ISO-8601 timestamp>
|
|
|
110
110
|
## Notes
|
|
111
111
|
|
|
112
112
|
- Specs are git-untracked (under `.codex/`)
|
|
113
|
-
- Regenerate anytime with `/
|
|
113
|
+
- Regenerate anytime with `/omcustomcodex:takeover <name>`
|
|
114
114
|
- Used by `/dev-refactor --spec` for invariant-preserving refactoring
|
|
115
115
|
- Advisory output — human review recommended before using as contract
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:web
|
|
3
3
|
description: Control and inspect the built-in Web UI (packages/serve) — start, stop, status, open
|
|
4
4
|
scope: harness
|
|
5
5
|
argument-hint: "[start|stop|status|open]"
|
|
@@ -89,7 +89,7 @@ If occupied by a non-serve process, warn the user and suggest `--port` option.
|
|
|
89
89
|
|
|
90
90
|
## No Argument Behavior
|
|
91
91
|
|
|
92
|
-
When called without arguments (`/
|
|
92
|
+
When called without arguments (`/omcustomcodex:web`):
|
|
93
93
|
1. Show status
|
|
94
|
-
2. If stopped, suggest: "Run `/
|
|
95
|
-
3. If running, suggest: "Run `/
|
|
94
|
+
2. If stopped, suggest: "Run `/omcustomcodex:web start` to start the server"
|
|
95
|
+
3. If running, suggest: "Run `/omcustomcodex:web open` to open in browser"
|
|
@@ -234,7 +234,7 @@ When verdict is `INTERNALIZE` and integration effort is M or L:
|
|
|
234
234
|
| Scenario | Better Alternative |
|
|
235
235
|
|----------|--------------------|
|
|
236
236
|
| Deep multi-source research | `/research <url>` |
|
|
237
|
-
| Internal project analysis | `/
|
|
237
|
+
| Internal project analysis | `/omcustomcodex:analysis` |
|
|
238
238
|
| Known tool evaluation | Direct agent conversation |
|
|
239
239
|
| Bulk URL analysis (5+) | `/research` with URL list |
|
|
240
240
|
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:wiki
|
|
3
3
|
description: Generate and maintain a persistent codebase wiki — LLM-built interlinked markdown knowledge base (Karpathy LLM Wiki pattern)
|
|
4
4
|
scope: core
|
|
5
5
|
version: 1.0.0
|
|
@@ -20,11 +20,11 @@ Builds and maintains a persistent, interlinked markdown wiki for the project cod
|
|
|
20
20
|
## Usage
|
|
21
21
|
|
|
22
22
|
```
|
|
23
|
-
/
|
|
24
|
-
/
|
|
25
|
-
/
|
|
26
|
-
/
|
|
27
|
-
/
|
|
23
|
+
/omcustomcodex:wiki # Full wiki generation / incremental update
|
|
24
|
+
/omcustomcodex:wiki ingest <path> # Ingest a specific file or directory
|
|
25
|
+
/omcustomcodex:wiki ingest .codex/agents/ # Ingest all agent definitions
|
|
26
|
+
/omcustomcodex:wiki query <question> # Query the wiki with natural language
|
|
27
|
+
/omcustomcodex:wiki lint # Health check — orphans, broken refs, stale pages
|
|
28
28
|
```
|
|
29
29
|
|
|
30
30
|
## Wiki Directory Structure
|
|
@@ -48,7 +48,7 @@ wiki/
|
|
|
48
48
|
|
|
49
49
|
### Default — Full Wiki Generation / Incremental Update
|
|
50
50
|
|
|
51
|
-
Invoked with `/
|
|
51
|
+
Invoked with `/omcustomcodex:wiki` (no arguments).
|
|
52
52
|
|
|
53
53
|
**Step 1 — Scan codebase structure**
|
|
54
54
|
|
|
@@ -188,7 +188,7 @@ If yes, delegate to the subagent to create the page in `wiki/concepts/`.
|
|
|
188
188
|
|
|
189
189
|
**Step 4 — Suggest fixes**
|
|
190
190
|
|
|
191
|
-
For each category: suggest the command to fix (e.g., `/
|
|
191
|
+
For each category: suggest the command to fix (e.g., `/omcustomcodex:wiki ingest .codex/agents/new-agent.md`).
|
|
192
192
|
|
|
193
193
|
**Step 5 — Insert into log.duckdb**
|
|
194
194
|
|
|
@@ -255,7 +255,7 @@ Example: `[[mgr-creator]]` and `[mgr-creator](../agents/mgr-creator.md)`
|
|
|
255
255
|
|
|
256
256
|
```yaml
|
|
257
257
|
# wiki/index.yaml — Machine-parseable wiki page index
|
|
258
|
-
# Updated by /
|
|
258
|
+
# Updated by /omcustomcodex:wiki after every operation
|
|
259
259
|
|
|
260
260
|
meta:
|
|
261
261
|
updated: "2026-04-12"
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
---
|
|
2
|
-
name:
|
|
2
|
+
name: omcustomcodex:wiki-rag
|
|
3
3
|
description: Use the project wiki as RAG knowledge source — search wiki pages to answer codebase questions before exploring raw files
|
|
4
4
|
scope: core
|
|
5
5
|
version: 1.0.0
|
|
@@ -15,9 +15,9 @@ Query the project wiki to answer questions about the codebase. The wiki is a pre
|
|
|
15
15
|
## Usage
|
|
16
16
|
|
|
17
17
|
```
|
|
18
|
-
/
|
|
19
|
-
/
|
|
20
|
-
/
|
|
18
|
+
/omcustomcodex:wiki-rag "how does orchestration work?"
|
|
19
|
+
/omcustomcodex:wiki-rag "what agents handle database tasks?"
|
|
20
|
+
/omcustomcodex:wiki-rag "explain the compilation metaphor"
|
|
21
21
|
```
|
|
22
22
|
|
|
23
23
|
Also triggered automatically by intent-detection when a user asks about project architecture, agent roles, skill purposes, or rule behavior.
|
|
@@ -29,7 +29,7 @@ Also triggered automatically by intent-detection when a user asks about project
|
|
|
29
29
|
Read and parse `wiki/index.yaml` to get the full page catalog. If `wiki/index.yaml` does not exist, report:
|
|
30
30
|
|
|
31
31
|
```
|
|
32
|
-
[wiki-rag] Wiki not initialized. Run /
|
|
32
|
+
[wiki-rag] Wiki not initialized. Run /omcustomcodex:wiki first to create wiki/index.yaml.
|
|
33
33
|
```
|
|
34
34
|
|
|
35
35
|
Then abort.
|
|
@@ -132,7 +132,7 @@ For partial and miss cases: always acknowledge what the wiki covered before pivo
|
|
|
132
132
|
- **Acknowledges gaps honestly** — never hallucinate content not found in the wiki
|
|
133
133
|
- **Offers to improve wiki coverage** when gaps are found — compounding the knowledge base over time
|
|
134
134
|
|
|
135
|
-
## Integration with /
|
|
135
|
+
## Integration with /omcustomcodex:wiki
|
|
136
136
|
|
|
137
137
|
| Skill | Role |
|
|
138
138
|
|-------|------|
|
package/templates/AGENTS.md.en
CHANGED
|
@@ -94,33 +94,33 @@ NO EXCEPTIONS. NO EXCUSES.
|
|
|
94
94
|
|
|
95
95
|
| Command | Description |
|
|
96
96
|
|---------|-------------|
|
|
97
|
-
| `/
|
|
98
|
-
| `/
|
|
99
|
-
| `/
|
|
100
|
-
| `/
|
|
101
|
-
| `/
|
|
102
|
-
| `/
|
|
103
|
-
| `/
|
|
97
|
+
| `/omcustomcodex:analysis` | Analyze project and auto-configure customizations |
|
|
98
|
+
| `/omcustomcodex:create-agent` | Create a new agent |
|
|
99
|
+
| `/omcustomcodex:update-docs` | Sync documentation with project structure |
|
|
100
|
+
| `/omcustomcodex:update-external` | Update agents from external sources |
|
|
101
|
+
| `/omcustomcodex:audit-agents` | Audit agent dependencies |
|
|
102
|
+
| `/omcustomcodex:fix-refs` | Fix broken references |
|
|
103
|
+
| `/omcustomcodex-takeover` | Extract canonical spec from existing agent/skill |
|
|
104
104
|
| `/dev-review` | Review code for best practices |
|
|
105
105
|
| `/dev-refactor` | Refactor code |
|
|
106
106
|
| `/memory-save` | Save session context to omx-memory |
|
|
107
107
|
| `/memory-recall` | Search and recall memories |
|
|
108
|
-
| `/
|
|
109
|
-
| `/
|
|
110
|
-
| `/
|
|
111
|
-
| `/
|
|
112
|
-
| `/
|
|
108
|
+
| `/omcustomcodex:monitoring-setup` | Enable/disable OTel console monitoring |
|
|
109
|
+
| `/omcustomcodex:npm-publish` | Publish package to npm registry |
|
|
110
|
+
| `/omcustomcodex:npm-version` | Manage semantic versions |
|
|
111
|
+
| `/omcustomcodex:npm-audit` | Audit dependencies |
|
|
112
|
+
| `/omcustomcodex-release-notes` | Generate release notes from git history |
|
|
113
113
|
| `/codex-exec` | Execute Codex CLI prompts |
|
|
114
114
|
| `/optimize-analyze` | Analyze bundle and performance |
|
|
115
115
|
| `/optimize-bundle` | Optimize bundle size |
|
|
116
116
|
| `/optimize-report` | Generate optimization report |
|
|
117
117
|
| `/research` | 10-team parallel deep analysis and cross-verification |
|
|
118
118
|
| `/deep-plan` | Research-validated planning (research → plan → verify) |
|
|
119
|
-
| `/
|
|
119
|
+
| `/omcustomcodex:sauron-watch` | Full R017 verification |
|
|
120
120
|
| `/structured-dev-cycle` | 6-stage structured development cycle (Plan → Verify → Implement → Verify → Compound → Done) |
|
|
121
|
-
| `/
|
|
122
|
-
| `/
|
|
123
|
-
| `/
|
|
121
|
+
| `/omcustomcodex:lists` | Show all available commands |
|
|
122
|
+
| `/omcustomcodex:status` | Show system status |
|
|
123
|
+
| `/omcustomcodex:help` | Show help information |
|
|
124
124
|
|
|
125
125
|
## Project Structure
|
|
126
126
|
|
|
@@ -195,15 +195,15 @@ Task tool + routing skills remain the fallback for simple/cost-sensitive tasks.
|
|
|
195
195
|
|
|
196
196
|
```bash
|
|
197
197
|
# Project analysis
|
|
198
|
-
/
|
|
198
|
+
/omcustomcodex:analysis
|
|
199
199
|
|
|
200
200
|
# Show all commands
|
|
201
|
-
/
|
|
201
|
+
/omcustomcodex:lists
|
|
202
202
|
|
|
203
203
|
# Agent management
|
|
204
|
-
/
|
|
205
|
-
/
|
|
206
|
-
/
|
|
204
|
+
/omcustomcodex:create-agent my-agent
|
|
205
|
+
/omcustomcodex:update-docs
|
|
206
|
+
/omcustomcodex:audit-agents
|
|
207
207
|
|
|
208
208
|
# Code review
|
|
209
209
|
/dev-review src/main.go
|
|
@@ -213,7 +213,7 @@ Task tool + routing skills remain the fallback for simple/cost-sensitive tasks.
|
|
|
213
213
|
/memory-recall authentication
|
|
214
214
|
|
|
215
215
|
# Verification
|
|
216
|
-
/
|
|
216
|
+
/omcustomcodex:sauron-watch
|
|
217
217
|
```
|
|
218
218
|
|
|
219
219
|
## External Dependencies
|
package/templates/AGENTS.md.ko
CHANGED
|
@@ -94,33 +94,33 @@ oh-my-customcodex로 구동됩니다.
|
|
|
94
94
|
|
|
95
95
|
| 커맨드 | 설명 |
|
|
96
96
|
|--------|------|
|
|
97
|
-
| `/
|
|
98
|
-
| `/
|
|
99
|
-
| `/
|
|
100
|
-
| `/
|
|
101
|
-
| `/
|
|
102
|
-
| `/
|
|
103
|
-
| `/
|
|
97
|
+
| `/omcustomcodex:analysis` | 프로젝트 분석 및 자동 커스터마이징 |
|
|
98
|
+
| `/omcustomcodex:create-agent` | 새 에이전트 생성 |
|
|
99
|
+
| `/omcustomcodex:update-docs` | 프로젝트 구조와 문서 동기화 |
|
|
100
|
+
| `/omcustomcodex:update-external` | 외부 소스에서 에이전트 업데이트 |
|
|
101
|
+
| `/omcustomcodex:audit-agents` | 에이전트 의존성 감사 |
|
|
102
|
+
| `/omcustomcodex:fix-refs` | 깨진 참조 수정 |
|
|
103
|
+
| `/omcustomcodex-takeover` | 기존 에이전트/스킬에서 canonical spec 추출 |
|
|
104
104
|
| `/dev-review` | 코드 베스트 프랙티스 리뷰 |
|
|
105
105
|
| `/dev-refactor` | 코드 리팩토링 |
|
|
106
106
|
| `/memory-save` | 세션 컨텍스트를 omx-memory에 저장 |
|
|
107
107
|
| `/memory-recall` | 메모리 검색 및 리콜 |
|
|
108
|
-
| `/
|
|
109
|
-
| `/
|
|
110
|
-
| `/
|
|
111
|
-
| `/
|
|
112
|
-
| `/
|
|
108
|
+
| `/omcustomcodex:monitoring-setup` | OTel 콘솔 모니터링 활성화/비활성화 |
|
|
109
|
+
| `/omcustomcodex:npm-publish` | npm 레지스트리에 패키지 배포 |
|
|
110
|
+
| `/omcustomcodex:npm-version` | 시맨틱 버전 관리 |
|
|
111
|
+
| `/omcustomcodex:npm-audit` | 의존성 감사 |
|
|
112
|
+
| `/omcustomcodex-release-notes` | 릴리즈 노트 생성 (git 히스토리 기반) |
|
|
113
113
|
| `/codex-exec` | Codex CLI 프롬프트 실행 |
|
|
114
114
|
| `/optimize-analyze` | 번들 및 성능 분석 |
|
|
115
115
|
| `/optimize-bundle` | 번들 크기 최적화 |
|
|
116
116
|
| `/optimize-report` | 최적화 리포트 생성 |
|
|
117
117
|
| `/research` | 10-team 병렬 딥 분석 및 교차 검증 |
|
|
118
118
|
| `/deep-plan` | 연구 검증 기반 계획 수립 (research → plan → verify) |
|
|
119
|
-
| `/
|
|
119
|
+
| `/omcustomcodex:sauron-watch` | 전체 R017 검증 |
|
|
120
120
|
| `/structured-dev-cycle` | 6단계 구조적 개발 사이클 (Plan → Verify → Implement → Verify → Compound → Done) |
|
|
121
|
-
| `/
|
|
122
|
-
| `/
|
|
123
|
-
| `/
|
|
121
|
+
| `/omcustomcodex:lists` | 모든 사용 가능한 커맨드 표시 |
|
|
122
|
+
| `/omcustomcodex:status` | 시스템 상태 표시 |
|
|
123
|
+
| `/omcustomcodex:help` | 도움말 표시 |
|
|
124
124
|
|
|
125
125
|
## 프로젝트 구조
|
|
126
126
|
|
|
@@ -195,15 +195,15 @@ Codex CLI의 Agent Teams 기능이 활성화되어 있으면 (`OMCODEX_AGENT_TEA
|
|
|
195
195
|
|
|
196
196
|
```bash
|
|
197
197
|
# 프로젝트 분석
|
|
198
|
-
/
|
|
198
|
+
/omcustomcodex:analysis
|
|
199
199
|
|
|
200
200
|
# 모든 커맨드 표시
|
|
201
|
-
/
|
|
201
|
+
/omcustomcodex:lists
|
|
202
202
|
|
|
203
203
|
# 에이전트 관리
|
|
204
|
-
/
|
|
205
|
-
/
|
|
206
|
-
/
|
|
204
|
+
/omcustomcodex:create-agent my-agent
|
|
205
|
+
/omcustomcodex:update-docs
|
|
206
|
+
/omcustomcodex:audit-agents
|
|
207
207
|
|
|
208
208
|
# 코드 리뷰
|
|
209
209
|
/dev-review src/main.go
|
|
@@ -213,7 +213,7 @@ Codex CLI의 Agent Teams 기능이 활성화되어 있으면 (`OMCODEX_AGENT_TEA
|
|
|
213
213
|
/memory-recall authentication
|
|
214
214
|
|
|
215
215
|
# 검증
|
|
216
|
-
/
|
|
216
|
+
/omcustomcodex:sauron-watch
|
|
217
217
|
```
|
|
218
218
|
|
|
219
219
|
## 외부 의존성
|
package/templates/CLAUDE.md
CHANGED
|
@@ -97,16 +97,16 @@ oh-my-customcodex로 구동됩니다.
|
|
|
97
97
|
|
|
98
98
|
| 카테고리 | 대표 커맨드 | 설명 |
|
|
99
99
|
|----------|------------|------|
|
|
100
|
-
| 프로젝트 관리 | `/
|
|
100
|
+
| 프로젝트 관리 | `/omcustomcodex:analysis`, `/omcustomcodex:create-agent`, `/omcustomcodex:audit-agents` | 분석, 에이전트/스킬 생성, 감사 |
|
|
101
101
|
| 아이디어 | `/idea` | 자연어 아이디어를 구조화된 이슈 스펙으로 변환 |
|
|
102
102
|
| 개발 | `/dev-review`, `/dev-refactor`, `/sdd-dev`, `/structured-dev-cycle` | 코드 리뷰, 리팩토링, SDD |
|
|
103
|
-
| 검증 | `/
|
|
104
|
-
| 릴리즈 | `/pipeline auto-dev`, `/
|
|
105
|
-
| 리서치 | `/research`, `/scout`, `/deep-plan`, `/
|
|
103
|
+
| 검증 | `/omcustomcodex:sauron-watch`, `/deep-verify`, `/adversarial-review` | R017 검증, 릴리즈 품질, 보안 리뷰 |
|
|
104
|
+
| 릴리즈 | `/pipeline auto-dev`, `/omcustomcodex-release-notes`, `/release-plan` | 자동 개발, 릴리즈 노트 |
|
|
105
|
+
| 리서치 | `/research`, `/scout`, `/deep-plan`, `/omcustomcodex:agora` | 병렬 분석, URL 평가, 연구 계획 |
|
|
106
106
|
| 메모리 | `/memory-save`, `/memory-recall` | 세션 메모리 관리 |
|
|
107
|
-
| 시스템 | `/token-efficiency-audit`, `/pre-generation-arch-check`, `/
|
|
107
|
+
| 시스템 | `/token-efficiency-audit`, `/pre-generation-arch-check`, `/omcustomcodex:lists`, `/omcustomcodex:status`, `/omcustomcodex:help` | 토큰 효율/아키텍처 감사, 전체 목록, 상태, 도움말 |
|
|
108
108
|
|
|
109
|
-
> 전체 커맨드 목록 (60+ 커맨드): `/
|
|
109
|
+
> 전체 커맨드 목록 (60+ 커맨드): `/omcustomcodex:lists` 실행
|
|
110
110
|
|
|
111
111
|
## 프로젝트 구조
|
|
112
112
|
|
|
@@ -197,15 +197,15 @@ Codex CLI의 Agent Teams 기능이 활성화되어 있으면 (`OMCODEX_AGENT_TEA
|
|
|
197
197
|
|
|
198
198
|
```bash
|
|
199
199
|
# 프로젝트 분석
|
|
200
|
-
/
|
|
200
|
+
/omcustomcodex:analysis
|
|
201
201
|
|
|
202
202
|
# 모든 커맨드 표시
|
|
203
|
-
/
|
|
203
|
+
/omcustomcodex:lists
|
|
204
204
|
|
|
205
205
|
# 에이전트 관리
|
|
206
|
-
/
|
|
207
|
-
/
|
|
208
|
-
/
|
|
206
|
+
/omcustomcodex:create-agent my-agent
|
|
207
|
+
/omcustomcodex:update-docs
|
|
208
|
+
/omcustomcodex:audit-agents
|
|
209
209
|
|
|
210
210
|
# 코드 리뷰
|
|
211
211
|
/dev-review src/main.go
|
|
@@ -215,7 +215,7 @@ Codex CLI의 Agent Teams 기능이 활성화되어 있으면 (`OMCODEX_AGENT_TEA
|
|
|
215
215
|
/memory-recall authentication
|
|
216
216
|
|
|
217
217
|
# 검증
|
|
218
|
-
/
|
|
218
|
+
/omcustomcodex:sauron-watch
|
|
219
219
|
```
|
|
220
220
|
|
|
221
221
|
## 외부 의존성
|
package/templates/CLAUDE.md.en
CHANGED
|
@@ -94,24 +94,24 @@ NO EXCEPTIONS. NO EXCUSES.
|
|
|
94
94
|
|
|
95
95
|
| Command | Description |
|
|
96
96
|
|---------|-------------|
|
|
97
|
-
| `/
|
|
97
|
+
| `/omcustomcodex:analysis` | Analyze project and auto-configure customizations |
|
|
98
98
|
| `/idea` | Turn a natural-language idea into structured issue specs |
|
|
99
|
-
| `/
|
|
100
|
-
| `/
|
|
101
|
-
| `/
|
|
102
|
-
| `/
|
|
103
|
-
| `/
|
|
104
|
-
| `/
|
|
99
|
+
| `/omcustomcodex:create-agent` | Create a new agent |
|
|
100
|
+
| `/omcustomcodex:update-docs` | Sync documentation with project structure |
|
|
101
|
+
| `/omcustomcodex:update-external` | Update agents from external sources |
|
|
102
|
+
| `/omcustomcodex:audit-agents` | Audit agent dependencies |
|
|
103
|
+
| `/omcustomcodex:fix-refs` | Fix broken references |
|
|
104
|
+
| `/omcustomcodex:takeover` | Extract canonical spec from existing agent/skill |
|
|
105
105
|
| `/dev-review` | Review code for best practices |
|
|
106
106
|
| `/dev-refactor` | Refactor code |
|
|
107
107
|
| `/memory-save` | Save session context to omx-memory |
|
|
108
108
|
| `/memory-recall` | Search and recall memories |
|
|
109
|
-
| `/
|
|
109
|
+
| `/omcustomcodex:monitoring-setup` | Enable/disable OTel console monitoring |
|
|
110
110
|
| `/token-efficiency-audit` | Audit and tune token-efficiency settings |
|
|
111
|
-
| `/
|
|
112
|
-
| `/
|
|
113
|
-
| `/
|
|
114
|
-
| `/
|
|
111
|
+
| `/omcustomcodex:npm-publish` | Publish package to npm registry |
|
|
112
|
+
| `/omcustomcodex:npm-version` | Manage semantic versions |
|
|
113
|
+
| `/omcustomcodex:npm-audit` | Audit dependencies |
|
|
114
|
+
| `/omcustomcodex-release-notes` | Generate release notes from git history |
|
|
115
115
|
| `/codex-exec` | Execute Codex CLI prompts |
|
|
116
116
|
| `/optimize-analyze` | Analyze bundle and performance |
|
|
117
117
|
| `/optimize-bundle` | Optimize bundle size |
|
|
@@ -119,11 +119,11 @@ NO EXCEPTIONS. NO EXCUSES.
|
|
|
119
119
|
| `/research` | 10-team parallel deep analysis and cross-verification |
|
|
120
120
|
| `/deep-plan` | Research-validated planning (research → plan → verify) |
|
|
121
121
|
| `/pre-generation-arch-check` | Check architecture risks before implementation |
|
|
122
|
-
| `/
|
|
122
|
+
| `/omcustomcodex:sauron-watch` | Full R017 verification |
|
|
123
123
|
| `/structured-dev-cycle` | 6-stage structured development cycle (Plan → Verify → Implement → Verify → Compound → Done) |
|
|
124
|
-
| `/
|
|
125
|
-
| `/
|
|
126
|
-
| `/
|
|
124
|
+
| `/omcustomcodex:lists` | Show all available commands |
|
|
125
|
+
| `/omcustomcodex:status` | Show system status |
|
|
126
|
+
| `/omcustomcodex:help` | Show help information |
|
|
127
127
|
|
|
128
128
|
## Project Structure
|
|
129
129
|
|
|
@@ -198,15 +198,15 @@ Task tool + routing skills remain the fallback for simple/cost-sensitive tasks.
|
|
|
198
198
|
|
|
199
199
|
```bash
|
|
200
200
|
# Project analysis
|
|
201
|
-
/
|
|
201
|
+
/omcustomcodex:analysis
|
|
202
202
|
|
|
203
203
|
# Show all commands
|
|
204
|
-
/
|
|
204
|
+
/omcustomcodex:lists
|
|
205
205
|
|
|
206
206
|
# Agent management
|
|
207
|
-
/
|
|
208
|
-
/
|
|
209
|
-
/
|
|
207
|
+
/omcustomcodex:create-agent my-agent
|
|
208
|
+
/omcustomcodex:update-docs
|
|
209
|
+
/omcustomcodex:audit-agents
|
|
210
210
|
|
|
211
211
|
# Code review
|
|
212
212
|
/dev-review src/main.go
|
|
@@ -216,7 +216,7 @@ Task tool + routing skills remain the fallback for simple/cost-sensitive tasks.
|
|
|
216
216
|
/memory-recall authentication
|
|
217
217
|
|
|
218
218
|
# Verification
|
|
219
|
-
/
|
|
219
|
+
/omcustomcodex:sauron-watch
|
|
220
220
|
```
|
|
221
221
|
|
|
222
222
|
## External Dependencies
|
package/templates/CLAUDE.md.ko
CHANGED
|
@@ -94,24 +94,24 @@ oh-my-customcodex로 구동됩니다.
|
|
|
94
94
|
|
|
95
95
|
| 커맨드 | 설명 |
|
|
96
96
|
|--------|------|
|
|
97
|
-
| `/
|
|
97
|
+
| `/omcustomcodex:analysis` | 프로젝트 분석 및 자동 커스터마이징 |
|
|
98
98
|
| `/idea` | 자연어 아이디어를 구조화된 이슈 스펙으로 변환 |
|
|
99
|
-
| `/
|
|
100
|
-
| `/
|
|
101
|
-
| `/
|
|
102
|
-
| `/
|
|
103
|
-
| `/
|
|
104
|
-
| `/
|
|
99
|
+
| `/omcustomcodex:create-agent` | 새 에이전트 생성 |
|
|
100
|
+
| `/omcustomcodex:update-docs` | 프로젝트 구조와 문서 동기화 |
|
|
101
|
+
| `/omcustomcodex:update-external` | 외부 소스에서 에이전트 업데이트 |
|
|
102
|
+
| `/omcustomcodex:audit-agents` | 에이전트 의존성 감사 |
|
|
103
|
+
| `/omcustomcodex:fix-refs` | 깨진 참조 수정 |
|
|
104
|
+
| `/omcustomcodex:takeover` | 기존 에이전트/스킬에서 canonical spec 추출 |
|
|
105
105
|
| `/dev-review` | 코드 베스트 프랙티스 리뷰 |
|
|
106
106
|
| `/dev-refactor` | 코드 리팩토링 |
|
|
107
107
|
| `/memory-save` | 세션 컨텍스트를 omx-memory에 저장 |
|
|
108
108
|
| `/memory-recall` | 메모리 검색 및 리콜 |
|
|
109
|
-
| `/
|
|
109
|
+
| `/omcustomcodex:monitoring-setup` | OTel 콘솔 모니터링 활성화/비활성화 |
|
|
110
110
|
| `/token-efficiency-audit` | 토큰 효율 설정 감사 및 조정 |
|
|
111
|
-
| `/
|
|
112
|
-
| `/
|
|
113
|
-
| `/
|
|
114
|
-
| `/
|
|
111
|
+
| `/omcustomcodex:npm-publish` | npm 레지스트리에 패키지 배포 |
|
|
112
|
+
| `/omcustomcodex:npm-version` | 시맨틱 버전 관리 |
|
|
113
|
+
| `/omcustomcodex:npm-audit` | 의존성 감사 |
|
|
114
|
+
| `/omcustomcodex-release-notes` | 릴리즈 노트 생성 (git 히스토리 기반) |
|
|
115
115
|
| `/codex-exec` | Codex CLI 프롬프트 실행 |
|
|
116
116
|
| `/optimize-analyze` | 번들 및 성능 분석 |
|
|
117
117
|
| `/optimize-bundle` | 번들 크기 최적화 |
|
|
@@ -119,11 +119,11 @@ oh-my-customcodex로 구동됩니다.
|
|
|
119
119
|
| `/research` | 10-team 병렬 딥 분석 및 교차 검증 |
|
|
120
120
|
| `/deep-plan` | 연구 검증 기반 계획 수립 (research → plan → verify) |
|
|
121
121
|
| `/pre-generation-arch-check` | 구현 전 아키텍처 위험 점검 |
|
|
122
|
-
| `/
|
|
122
|
+
| `/omcustomcodex:sauron-watch` | 전체 R017 검증 |
|
|
123
123
|
| `/structured-dev-cycle` | 6단계 구조적 개발 사이클 (Plan → Verify → Implement → Verify → Compound → Done) |
|
|
124
|
-
| `/
|
|
125
|
-
| `/
|
|
126
|
-
| `/
|
|
124
|
+
| `/omcustomcodex:lists` | 모든 사용 가능한 커맨드 표시 |
|
|
125
|
+
| `/omcustomcodex:status` | 시스템 상태 표시 |
|
|
126
|
+
| `/omcustomcodex:help` | 도움말 표시 |
|
|
127
127
|
|
|
128
128
|
## 프로젝트 구조
|
|
129
129
|
|
|
@@ -198,15 +198,15 @@ Codex CLI의 Agent Teams 기능이 활성화되어 있으면 (`OMCODEX_AGENT_TEA
|
|
|
198
198
|
|
|
199
199
|
```bash
|
|
200
200
|
# 프로젝트 분석
|
|
201
|
-
/
|
|
201
|
+
/omcustomcodex:analysis
|
|
202
202
|
|
|
203
203
|
# 모든 커맨드 표시
|
|
204
|
-
/
|
|
204
|
+
/omcustomcodex:lists
|
|
205
205
|
|
|
206
206
|
# 에이전트 관리
|
|
207
|
-
/
|
|
208
|
-
/
|
|
209
|
-
/
|
|
207
|
+
/omcustomcodex:create-agent my-agent
|
|
208
|
+
/omcustomcodex:update-docs
|
|
209
|
+
/omcustomcodex:audit-agents
|
|
210
210
|
|
|
211
211
|
# 코드 리뷰
|
|
212
212
|
/dev-review src/main.go
|
|
@@ -216,7 +216,7 @@ Codex CLI의 Agent Teams 기능이 활성화되어 있으면 (`OMCODEX_AGENT_TEA
|
|
|
216
216
|
/memory-recall authentication
|
|
217
217
|
|
|
218
218
|
# 검증
|
|
219
|
-
/
|
|
219
|
+
/omcustomcodex:sauron-watch
|
|
220
220
|
```
|
|
221
221
|
|
|
222
222
|
## 외부 의존성
|
package/templates/manifest.json
CHANGED