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/startnpx skills add ggombee/code-forge --skill startgit 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 | $0.00076 | $0.06159 |
| Opus 5 | $0.00038 | $0.03080 |
| Sonnet 5 | $0.00015 | $0.01232 |
| Haiku 4.5 | $0.00008 | $0.00616 |
Grade B, and why
start scanned grade B with 2 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 2d ago.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat >> .claude/state/progress.md <<EOF Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "X-Figma-Token: $FIGMA_TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 611 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start — 작업 시작부터 완료까지
참조: 구현 시
rules/build-guide.md, 완료 후 검증 시rules/review-guide.md
MD 파일 또는 자유 텍스트로 작업을 정의하면, 분석 → 디자인 → 구현 → 검증 → 커밋 → PR까지 전체 플로우를 수행한다.
[즉시 실행] 이 메시지를 받으면 아래 흐름을 바로 실행하세요.
작업 내용: $ARGUMENTS
--auto 모드 (슬랙봇/Channels/Remote Control 호환, 비블로킹):
$ARGUMENTS에--auto가 포함되면 아래 동작:- Figma MCP 실패 시: 안내 없이 스킵
- 디자인 확인 단계: MCP 실패면 스킵
- 구현 시작 확인(8단계): LOW/MEDIUM 복잡도 → 자동 Yes / HIGH → 계획만 출력 후 중단
- AskUserQuestion 사용 최소화
참조 규칙:
@${CLAUDE_PLUGIN_ROOT}/instructions/multi-agent/coordination-guide.md(병렬 실행)@${CLAUDE_PLUGIN_ROOT}/instructions/multi-agent/agent-roster.md(에이전트 선택)@${CLAUDE_PLUGIN_ROOT}/rules/thinking-model.md(GROUND→APPLY→VERIFY)
옵션
| 옵션 | 설명 | 예시 |
|---|---|---|
| (없음) | 전체 플로우 (분석→구현→검증→커밋→PR) | /start feature.md |
--auto |
비블로킹 모드 (슬랙봇/Channels 호환) | /start TICKET-123 --auto |
--plan-only |
분석+계획만 출력하고 멈춤 | /start feature.md --plan-only |
--no-design |
디자인 분석 스킵 | /start "API 엔드포인트 추가" --no-design |
--skip-test |
테스트 스킵 | /start style-fix.md --skip-test |
--draft |
Draft PR로 생성 | /start feature.md --draft |
--no-pr |
커밋만, PR 생성 안 함 | /start hotfix.md --no-pr |
Flow CLI 자동 호출 계약 (2026-05-19 redesign G5)
/start는 각 Phase에서 flow-toolkit의 flow CLI를 자동 호출하여 5-family 통합을 완성한다. command -v flow 실패 시 graceful skip (해당 Phase 본 작업은 정상 진행, flow 호출만 스킵).
| Phase | flow 명령 | 효과 |
|---|---|---|
| 1 (티켓 ID 감지) | flow workflow start <ticket> --json |
~/.flow/projects/{repo}/workflows/{id}/state.json 생성. Codex/Cursor 이어받기 기반 |
| 1-2 (BE URL 감지) | flow spec capture <URL> --redact --json |
.policy/api-specs/{endpoint}.md 생성. type 정의 전 응답 우선 |
| 3 (정책 매트릭스) | flow tc select <ticket> --json 또는 flow policy diff <ticket> |
영향 TC + 변경 컴포넌트 자동 식별 |
| 5 (검증) | flow run report + flow tc verify --stale + flow policy lint |
사이클 결과 + 메타데이터 stale 검증 |
| 7 (회고) | flow retroforge whet --draft |
3회+ 반복 패턴 감지 → 규칙 초안 (2026-06-12 교체 — flow 휴면 의존 제거, §7-1) |
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.
- 2d ago First seen · 611 lines · 76 tokens per session scan B 63b877159e86
start is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 6,159 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sql-reporting
Conventions and review steps for writing analytics SQL against the warehouse. Use whenever the task involves querying tables, building a report, or aggregating metrics.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:human-like-code-review
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.