oh-my-customcode 1.1.106 → 2.0.0
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 +8 -9
- package/dist/cli/index.js +188 -178
- package/dist/index.js +181 -125
- package/package.json +1 -1
- package/templates/.claude/hooks/hooks.json +0 -10
- package/templates/.claude/hooks/scripts/cost-cap-advisor.sh +107 -52
- package/templates/.claude/hooks/scripts/session-env-check.sh +0 -8
- package/templates/.claude/rules/MUST-agent-design.md +1 -1
- package/templates/.claude/rules/SHOULD-memory-integration.md +1 -1
- package/templates/.claude/settings.json +0 -10
- package/templates/.claude/skills/intent-detection/patterns/agent-triggers.yaml +0 -8
- package/templates/CLAUDE.md +1 -1
- package/templates/CLAUDE.md.en +1 -1
- package/templates/CLAUDE.md.ko +1 -1
- package/templates/README.md +4 -4
- package/templates/guides/external-tools/ecc-absorption-decisions.md +2 -0
- package/templates/guides/multi-provider-exec/README.md +7 -18
- package/templates/manifest.json +3 -3
- package/templates/.claude/hooks/scripts/rtk-intercept.sh +0 -77
- package/templates/.claude/skills/rtk-exec/SKILL.md +0 -199
- package/templates/.claude/skills/rtk-exec/scripts/rtk-wrapper.cjs +0 -377
package/README.md
CHANGED
|
@@ -13,7 +13,7 @@
|
|
|
13
13
|
|
|
14
14
|
**[한국어 문서 (Korean)](./README_ko.md)**
|
|
15
15
|
|
|
16
|
-
50 agents.
|
|
16
|
+
50 agents. 114 skills. 23 rules. One command.
|
|
17
17
|
|
|
18
18
|
```bash
|
|
19
19
|
npm install -g oh-my-customcode && cd your-project && omcustom init
|
|
@@ -134,7 +134,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
|
|
|
134
134
|
|
|
135
135
|
---
|
|
136
136
|
|
|
137
|
-
### Skills (
|
|
137
|
+
### Skills (114)
|
|
138
138
|
|
|
139
139
|
| Category | Count | Includes |
|
|
140
140
|
|----------|-------|----------|
|
|
@@ -148,7 +148,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
|
|
|
148
148
|
| Optimization | 3 | optimize-analyze, optimize-bundle, optimize-report |
|
|
149
149
|
| Security | 2 | adversarial-review, cve-triage |
|
|
150
150
|
| Consensus | 1 | agora — anonymous multi-round multi-vendor consensus review |
|
|
151
|
-
| Other |
|
|
151
|
+
| Other | 43 | claude-native, vercel-deploy, skills-sh-search, result-aggregation, and ~39 more |
|
|
152
152
|
|
|
153
153
|
Skills use a 3-tier scope system: `core` (universal), `harness` (agent/skill maintenance), `package` (project-specific).
|
|
154
154
|
|
|
@@ -236,7 +236,7 @@ Reference documentation covering best practices, architecture decisions, and int
|
|
|
236
236
|
|
|
237
237
|
## Safety
|
|
238
238
|
|
|
239
|
-
oh-my-customcode ships
|
|
239
|
+
oh-my-customcode ships 41 lifecycle hook scripts covering security, drift detection, and rule reinforcement. A few examples:
|
|
240
240
|
|
|
241
241
|
| Hook | Trigger | Action |
|
|
242
242
|
|------|---------|--------|
|
|
@@ -282,9 +282,9 @@ your-project/
|
|
|
282
282
|
├── CLAUDE.md # Entry point
|
|
283
283
|
├── .claude/
|
|
284
284
|
│ ├── agents/ # 50 agent definitions
|
|
285
|
-
│ ├── skills/ #
|
|
285
|
+
│ ├── skills/ # 114 skill modules
|
|
286
286
|
│ ├── rules/ # 23 governance rules (R000-R023)
|
|
287
|
-
│ ├── hooks/ #
|
|
287
|
+
│ ├── hooks/ # 41 lifecycle hook scripts (hooks.json source; compiled into settings.json)
|
|
288
288
|
│ ├── schemas/ # Tool input validation schemas
|
|
289
289
|
│ ├── specs/ # Extracted canonical specs
|
|
290
290
|
│ ├── contexts/ # 4 shared context files
|
|
@@ -296,11 +296,10 @@ your-project/
|
|
|
296
296
|
|
|
297
297
|
## External Tool Integrations
|
|
298
298
|
|
|
299
|
-
RTK is
|
|
299
|
+
Starting with v2.0.0, project RTK integration is retired: the public `/rtk-exec` skill, automatic installation, doctor integration, and RTK hooks are removed. Separately installed RTK binaries remain on your machine. Updates automatically remove retired managed files only when their hashes match the previous lockfile. Modified files and files with unknown ownership are preserved and reported as conflicts; retained user skill files may still be discovered automatically. Other tools are optional:
|
|
300
300
|
|
|
301
301
|
| Tool | Purpose | Install | Status |
|
|
302
302
|
|------|---------|---------|--------|
|
|
303
|
-
| [RTK](https://github.com/rtk-ai/rtk) | 60-90% token savings on CLI output | Auto-installed via `omcustom init` | **Recommended** |
|
|
304
303
|
| [Codex CLI](https://github.com/openai/codex) | OpenAI Codex hybrid workflows | `npm i -g @openai/codex` | Optional |
|
|
305
304
|
| [Gemini CLI](https://github.com/google-gemini/gemini-cli) | Google Gemini hybrid workflows | `npm i -g @google/gemini-cli` | Optional |
|
|
306
305
|
|
|
@@ -319,7 +318,7 @@ bun run build # Production build
|
|
|
319
318
|
|
|
320
319
|
Requirements: Node.js >= 18.0.0, Claude Code CLI (developed and tested against Claude Code v2.1.277).
|
|
321
320
|
|
|
322
|
-
Releases are two-stage automation: a merged `release/vX.Y.Z` PR triggers `auto-tag.yml`, which creates the git tag; the tag push then triggers `release.yml`, which builds, verifies, and publishes to npm. The project's own contributor knowledge base — the in-repo wiki at `wiki/` (
|
|
321
|
+
Releases are two-stage automation: a merged `release/vX.Y.Z` PR triggers `auto-tag.yml`, which creates the git tag; the tag push then triggers `release.yml`, which builds, verifies, and publishes to npm. The project's own contributor knowledge base — the in-repo wiki at `wiki/` (covering agents, skills, rules, and workflows) — is CI-verified on every PR against a source-hash manifest, so wiki pages cannot silently drift from the code they document.
|
|
323
322
|
|
|
324
323
|
---
|
|
325
324
|
|