Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ggombee/code-forge/smith-create-agentnpx skills add ggombee/code-forge --skill smith-create-agentgit clone --depth 1 https://github.com/ggombee/code-forgeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00073 | $0.04382 |
| Opus 5 | $0.00036 | $0.02191 |
| Sonnet 5 | $0.00015 | $0.00876 |
| Haiku 4.5 | $0.00007 | $0.00438 |
Grade A, and why
smith-create-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smith Create Agent
프로젝트를 분석하고 Smith 2.0 에이전트 정의 파일을 생성하는 스킬.
호출 경로
| 경로 | 동작 |
|---|---|
사용자 직접 (/code-forge:smith-create-agent) |
Step 1부터 풀 실행 — 프로젝트 분석 + 대화형 확인 |
/code-forge:setup에서 위임 호출 (orchestrator) |
Step 1 스킵 — .claude/profile.json이 이미 Step 5에서 생성됐으므로 재사용. 즉시 Step 2 Deep Analysis부터 시작 |
위임 감지 방법: .claude/profile.json이 현재 턴에 이미 존재하면 setup으로부터 위임된 호출로 간주한다. 사용자 재확인 질문을 생략하고 분석/생성 파이프라인으로 직행한다.
References
references/subagent-spec.md— Claude Code subagent frontmatter 필드 전체 규격
기본 생성 구조
최소 8개 파일을 기본으로 생성하되, 프로젝트 성격에 따라 추가 에이전트를 자유롭게 생성한다:
.agents/agents/
├── {project}-domain.md (class, STATE) ← 도메인 모델/용어/플로우
├── {project}-policy.md (class, STATE) ← SSOT/금지 영역/규칙
├── {project}-context.md (class, STATE) ← 디렉토리 맵/추상화/패턴
├── {project}-base.md (class, STATE) ← extends: framework+language+위 3개
├── {project}-architect.md (instance) ← 분석/설계
├── {project}-dev.md (instance) ← 개발/구현
├── {project}-reviewer.md (instance) ← 코드 리뷰
├── {project}-tester.md (instance) ← 테스트 작성
├── .analysis-manifest.json ← 분석 메타데이터 (staleness 감지용)
└── ... 프로젝트에 필요한 만큼 추가
Deep Analysis Pipeline (Step 2)
프로젝트 분석을 4축 병렬로 수행한다:
2-1. 기술 스택 스캔 (기존 유지)
- package.json, tsconfig.json 등에서 기술 스택 파악
2-2. 도메인 분석 (신규)
- 타입 정의, API 라우트, DB 스키마, 상태 관리, README에서 교차 검증
- 핵심 엔티티, 비즈니스 플로우, 도메인 용어 추출
- →
{project}-domain.md생성
2-3. 정책 분석 (신규)
- CLAUDE.md, ESLint, tsconfig, CI, CODEOWNERS에서 추출
- SSOT 위치, 수정 금지 영역, import 규칙, PR/커밋 규칙
- →
{project}-policy.md생성
2-4. 컨텍스트 분석 (신규)
- 디렉토리 트리, import 빈도, shared 파일에서 추론
- 아키텍처 패턴 (레이어드, DDD, feature-based 등) 자동 분류
- →
{project}-context.md생성
base class extends 확장
기존: framework + language만 extends
변경: framework + language + domain + policy + context extends
→ instance는 변경 불필요 (투명한 확장)
--refresh 모드
.analysis-manifest.json의 analyzedAt으로부터 30일 이상 경과 시 재분석 권장.
변경된 축만 선택적으로 재분석하고, 사용자 정의 규칙(userDefinedRules)은 보호.
추가 에이전트 예시
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 381 lines · 73 tokens per session scan A a1150c0d93ea
smith-create-agent is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 4,382 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
digital-health-clinical-asr-setup
Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIAAPIKEY check, deps install, TTS+ASR smoke test.
scaffold
Use when starting hyperflow in a new project, refreshing the .hyperflow/ cache, or installing auto-detection shims (AGENTS.md, CLAUDE.md). One-shot project setup; does not start the spec → scope → dispatch chain. Trigger with /hyperflow:scaffold, "init hyperflow", "set up hyperflow", "refresh hyperflow", "install…
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
environment-discovery
Systematic exploration of unknown environments before starting work.
forgetful-cli-setup
Set up the Forgetful CLI and connect from a terminal — install, local or remote mode, auth, and verification. Use when connecting a human or headless agent via shell, wiring CI with token auth, or operating a local server (serve, database selection, feature flags, re-embedding). Also covers the machine contract…
forgetful-mcp-setup
Set up an MCP client for Forgetful — wire Claude Code, Cursor, Copilot, Codex, Gemini, or OpenCode to the server and verify the connection behaves. Covers stdio vs HTTP transport, auth and scopes, the three meta-tools every client sees, and delegation to subagents.