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 skills add scroogy-dev/scroogy-agent-skills --skill context-harvestgit clone --depth 1 https://github.com/scroogy-dev/scroogy-agent-skillsWrote 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/scroogy-dev/scroogy-agent-skills/context-harvest)<a href="https://agentmods.dev/skills/scroogy-dev/scroogy-agent-skills/context-harvest"><img src="https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/context-harvest/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/scroogy-dev/scroogy-agent-skills/context-harvest"><img src="https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/context-harvest.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00095 | $0.03194 |
| Opus 5 | $0.00048 | $0.01597 |
| Sonnet 5 | $0.00019 | $0.00639 |
| Haiku 4.5 | $0.00010 | $0.00319 |
Grade A, and why
context-harvest 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 8d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
개요
소스코드 바깥에 존재하는 What(계약, 명세)과 Why(정책, 의사결정)를 외부 소스에서 수집·증류하여 .ai/30_contract/, .ai/40_domain/, .ai/50_adr/ 문서로 만드는 스킬입니다.
code-map과의 관계
code-map과 context-harvest는 쌍을 이루는 스킬입니다.
| 스킬 | 역할 | 대상 영역 |
|---|---|---|
code-map |
소스코드(How)를 색인 | 60_codebase/ |
context-harvest |
소스코드 바깥의 What + Why를 수집·증류 | 30_contract/, 40_domain/, 50_adr/ |
/context-harvest → 30_contract/, 40_domain/, 50_adr/ 문서 생성
/code-map --local sync → 새로 생긴 30/40/50 문서를 60_codebase/에서 교차 참조 연결
관련 skill
- ai-workspace (권장):
.ai/디렉토리 구조를 활용합니다. 없으면 필요한 디렉토리를 직접 생성합니다. - code-map (연동): 이 스킬이 생성한 30/40/50 문서를
60_codebase/에서 교차 참조로 연결합니다.
참조 문서
- 공통 규칙:
.ai/10_rules/context-loading.md— 있으면 따르며, 이미 적재되어 있으면 재로딩하지 않습니다. - 스킬 고유 추가 참조:
- 기존
.ai/30_contract/,.ai/40_domain/,.ai/50_adr/문서의 프론트매터 — 증분 수집 판정(last_harvested비교) .ai/10_rules/writing-principles.md·.ai/10_rules/writing-principles-local.md— 있으면 산출물 작성 원칙으로 참조 (충돌 시 local 우선; 없으면 본문의 "산출물 접기 기준"이 기본값)
- 기존
핵심 원칙
SSoT 원칙 유지
- SSoT는 소스코드이다.
- 이 스킬이 수집하는 정보는 **소스코드에 반영된 사실의 계약/명세(What)와 배경/근거(Why)**이다.
- 산출물은
.ai/내부 문서이며, 외부 URL은 문서 내 "원본 출처" 섹션에만 기재한다. - 소스코드에 대응하지 않는 정보(기각된 제안, 미구현 요청 등)는 수집하지 않는다.
증류 원칙
- 외부 소스의 원문을 그대로 복사하지 않는다.
- 핵심 결정/정책/근거만 추출하여 간결한 마크다운으로 증류한다.
- 고객 정보, 개인정보가 포함된 내용은 제거하고 증류한다.
실행 흐름 (대화형)
스킬은 CLI 옵션 없이 실행하며, 대화형으로 소스와 URL을 수집한다.
사용자: /context-harvest
스킬: 수집할 소스를 선택해주세요 (복수 선택 가능):
1) 웹 URL (법령, 공식 문서, 뉴스 등)
2) GitHub (issues / PRs)
3) Confluence (페이지 + 하위)
4) Jira (프로젝트 이슈)
사용자: 1, 2
스킬: [웹 URL] 수집할 URL을 입력해주세요 (여러 개 가능):
사용자: https://law.go.kr/..., https://docs.example.com/...
스킬: [GitHub] 리포지토리 URL을 입력해주세요:
사용자: https://github.com/org/repo
스킬: 수집을 시작합니다...
- 웹 URL 2건 fetch 중...
- GitHub org/repo issues/PRs 스캔 중...
유일한 CLI 옵션은 --full이며, 증분이 아닌 전체 재스캔을 강제한다.
사용자: /context-harvest --full
소스 목록
| 번호 | 소스 | 접근 수단 | URL 입력 | 수집 내용 예시 |
|---|---|---|---|---|
| 1 | 웹 URL | WebFetch 도구 | 멀티 | 법령, 공식 문서, 뉴스, RFC, 블로그, 외부 API 스펙 등 |
| 2 | GitHub issues / PRs | MCP (github) 또는 gh CLI |
단일 (리포 URL) | 기술적 설계 결정, 버그 원인 분석, 리뷰에서 나온 Why, 거절된 대안 |
| 3 | Confluence | MCP (atlassian) | 단일 (페이지 URL) | 정책, 법적 근거, 비즈니스 요건, 도메인 명세, API 계약 |
| 4 | Jira | MCP (atlassian) | 단일 (프로젝트 URL) | 비즈니스 배경, 외부 API 스펙, 요구사항 |
What ships with it
3 files 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.
- 8d ago First seen · 263 lines · 95 tokens per session scan A 72c06289216e
context-harvest is a skill published in the GitHub repository scroogy-dev/scroogy-agent-skills (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 95 tokens to every session and 3,194 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…