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/researchnpx skills add ggombee/code-forge --skill researchgit 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 | $0.00046 | $0.00644 |
| Opus 5 | $0.00023 | $0.00322 |
| Sonnet 5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
research 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 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.
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.
What it actually says
Research Skill
구조화된 팩트 기반 리서치 및 마크다운 리포트 생성
트리거
/research [topic] + 옵션 플래그:
--quick: 빠른 분석 (3-5 쿼리, 500-1000자)- (기본): 표준 분석 (5-10 쿼리, 1500-3000자)
--deep: 심층 조사 (10-15 쿼리, 3000-6000자, 반복 패스)
인자 없으면 즉시 주제 요청.
깊이별 기준
| 항목 | Quick | Standard | Deep |
|---|---|---|---|
| 쿼리 수 | 3-5 | 5-10 | 10-15 |
| 최소 출처 | 5 | 10 | 20+ |
| 리포트 길이 | 500-1000자 | 1500-3000자 | 3000-6000자 |
| 반복 패스 | 없음 | 없음 | 있음 (갭 분석) |
주제 분류
| 유형 | 채널 |
|---|---|
| 기술 비교 | WebSearch + GitHub |
| 시장/트렌드 | WebSearch + 크롤링 |
| 경쟁사 분석 | WebSearch + GitHub |
| 학술 주제 | arXiv + 문서 페칭 |
| 내부 프로젝트 | 코드 탐색 + Grep |
워크플로우
| Phase | 작업 | 필수 |
|---|---|---|
| 1. 파싱 | 도구 감지, 주제 분류 | 도구 가용성 확인 |
| 2. 전략 | 핵심 질문 3-5개 정의, 범위 설정 | Sequential thinking |
| 3. 수집 | 병렬 데이터 수집 (researcher, explorer) | 최소 출처 수 준수 |
| 4. 갭 분석 | (deep만) 누락 영역 2차 쿼리 | Sequential thinking |
| 5. 리포트 | 피라미드 원칙: 결론 → 상세 | 출처 URL 필수 |
| 6. 저장 | .forge/research/[NN].topic_summary.md |
파일 저장 필수 |
리포트 기준
- 현재 연도 컨텍스트 포함
- 모든 핵심 주장에 출처 URL 명시
- 비교 시 증거 테이블 포함
- 피라미드 원칙: 요약 → 상세
금지 사항
| 금지 |
|---|
| 출처 없는 주장 |
| 비교 증거 없이 비교 결론 |
| 출력 파일 저장 없이 종료 |
| 최소 출처 수 미달 |
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 · 78 lines · 46 tokens per session scan A 9e95031cba5c
research is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 644 once invoked, about $0.0002 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
credit-analysis
固收与信用分析：信用债评级、利差分析、违约风险评估、城投债研究、可转债定价与策略。.
correlation-regime
Correlation-regime detection and crisis attribution — edge-density regime states with hysteresis, causal (no look-ahead) smoothing, regime-aware exposure context, first-mover crisis attribution with honest NAME / MACRO / AMBIGUOUS / ABSTAIN verdicts, and a correlation-rewiring leaderboard that catches slow bleed-outs.
behavioral-finance
Behavioral finance applications: theories of overreaction and underreaction, behavioral explanations for momentum and reversal, investor sentiment cycles, cognitive-bias checklists, and debiasing quantitative strategies.
deep-company-series
Write a publication-grade 8-part deep-dive series on a single company (120k words total): cognitive reset / moat / profit engine / hidden assets / era variable (e.g. AI) / financials Buffett-style / management / valuation+redlines. The core IP is NOT writing but REVISING — a strict fact-check checklist catches…
earnings-revision
Earnings estimate revisions, guidance analysis, and post-earnings drift (PEAD) — track analyst consensus changes, earnings surprise patterns, and management guidance shifts for US/HK equities.
performance-attribution
Performance attribution analysis — Brinson sector/stock-selection attribution, factor alpha/beta decomposition, market-timing evaluation, and benchmark comparison framework.