Borrowing it
Nothing to install: this file belongs to Adelie-Squad/solosquad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Adelie-Squad/solosquad/main/.claude/skills/trend-tracker/SKILL.mdgit clone --depth 1 https://github.com/Adelie-Squad/solosquadWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/adelie-squad/solosquad/trend-tracker)<a href="https://agentmods.dev/skills/adelie-squad/solosquad/trend-tracker"><img src="https://agentmods.dev/badge/skills/adelie-squad/solosquad/trend-tracker.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00033 | $0.01956 |
| Opus 5 | $0.00016 | $0.00978 |
| Sonnet 5 | $0.00007 | $0.00391 |
| Haiku 4.5 | $0.00003 | $0.00196 |
Grade A, and why
trend-tracker 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trend Tracker
영향력 있는 AI 지식·프로젝트를 지속 추적하고, 하네스 엔지니어링 / 멀티 에이전트 / 24-7 자동화 3축에서 통합 트렌드와 기술 구조를 분석한다. 산출물은 항상 docs/trend-record/에 누적된다.
1. Tier 1 추적 레퍼런스
웹 조사 시 항상 1차 출처(공식 GitHub, 공식 블로그, 논문)를 먼저 확인한다.
| # | 레퍼런스 | 카테고리 | 핵심 포커스 |
|---|---|---|---|
| 1 | Anthropic | 모델/하네스 | Claude, Claude Code, Agent SDK, prompt caching, harness engineering 공식 글 |
| 2 | OpenClaw | 하네스 | 자가 업데이트, 자연어 cron, 메신저 상주 |
| 3 | Hermes (Nous Research) | 멀티에이전트 | trajectory → skill 자동 요약, FTS5 메모리 |
| 4 | garrytan/gstack (사용자가 "harrytang"으로 칭한 것의 정정명) | 멀티에이전트 | Think→Plan→Build→Review→Test→Ship→Reflect 슬래시 체인 |
| 5 | phuryn/pm-skills | 멀티에이전트 | auto-load + slash 듀얼 트리거, PM 스킬 마켓플레이스 |
| 6 | karpathy/autoresearch | 24/7 자동화 | metric gate + git rollback 자율 루프 |
| 7 | MiroFish (CAMEL-AI OASIS) | 멀티에이전트 (관찰) | 1M 에이전트 swarm 시뮬레이션 |
| 8 | paperclipai/paperclip (site) | 멀티에이전트 / 24-7 자동화 | org chart 기반 에이전트 노동 관리, 월예산 한도·승인 게이트, 멀티런타임(Claude/OpenClaw/Cursor) 오케스트레이션 |
| 9 | iamlukethedev/claw3d (site) | 멀티에이전트 (시각화/관찰) | 3D 가상 오피스로 에이전트 활동 가시화, OpenClaw/Hermes 등 런타임 무관 supervision 레이어 |
| 10 | Ralphathon (해커톤 문화) | 24-7 자동화 | Ralph Loop(Huntley) 기반 자율 코딩 while-루프 해커톤. 1차 GitHub 출처 없음 — 강의·커뮤니티·SNS에서 구체 사례·방법 수집 |
§1 예외 — Ralphathon: 해커톤 문화는 단일 1차 출처가 없으므로 §3.1의 "트위터 일회성 인용 금지" 규칙을 완화한다. 단, ① 강의 영상·블로그 글·커뮤니티 토론 스레드처럼 재참조 가능한 URL만 받아들이고 ② 한 행사·한 사례당 최소 2개 독립 출처를 교차 확인하며 ③ 신호 표의 "출처" 칸에 채널 유형(강의/Discord/X 스레드)을 명시한다.
Tier 2(월간 스캔): Anthropic/OpenAI/DeepMind 공식 블로그, GitHub trending(agents claude-code multi-agent 토픽), HN 1주 누적 상위(키워드: agent, harness, autonomous), X — karpathy / swyx / simonw / Anthropic researchers.
승격 규칙: Tier 2에서 2회 이상 의미 있는 신호 → Tier 1 승격 후보로 INDEX.md에 추기.
2. 분석 3축
- 하네스 엔지니어링: 컨텍스트 윈도우 운영, 메모리 시스템, 도구 호출 패턴, 자가 진화, 슬래시/스킬 구조
- 멀티 에이전트: 라우팅, 핸드오프 프로토콜, 공유 상태, 권한 경계, 협업 모델
- 24/7 자동화: 크론/스케줄러, 신호 기반 트리거, 자율 의사결정 경계, human-in-the-loop 위치
각 신호를 상/중/하/— 로 평가. "—"는 해당 축과 무관하다는 명시 (공백 금지).
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.
- 7d ago First seen · 107 lines · 33 tokens per session scan A 9f44c4a70196
trend-tracker is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 16d ago), licensed MIT. It adds 33 tokens to every session and 1,956 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
dspy-ruby
This skill should be used when working with DSPy.rb, a Ruby framework for type-safe, composable LLM applications.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.