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/kohj1018/agentic-dev-harness/research-packnpx skills add kohj1018/agentic-dev-harness --skill research-packgit clone --depth 1 https://github.com/kohj1018/agentic-dev-harnessWrote 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/kohj1018/agentic-dev-harness/research-pack)<a href="https://agentmods.dev/skills/kohj1018/agentic-dev-harness/research-pack"><img src="https://agentmods.dev/badge/skills/kohj1018/agentic-dev-harness/research-pack.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 | $0.00062 | $0.00866 |
| Opus 5 | $0.00031 | $0.00433 |
| Sonnet 5 | $0.00012 | $0.00173 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
research-pack 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 5d 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
이 skill은 리서치 + 노트 작성 전용이다. 코드·workitem·charter 문서를 수정하지 않는다 (노트 파일 1개만 작성).
메인 세션에서 실행한다(
context: fork/agent:미지정 — discover-product 패턴). 무거운 웹 조사는 researcher agent에Agent위임해 메인 컨텍스트 오염을 막는다. researcher는 report-only이고, 노트 Write는 본 skill이 한다.
Codex: 본 skill은 wrapper 미보유(자연어 호출) — Codex에서는 "Follow .claude/skills/research-pack/SKILL.md"로 호출한다(목록 SSOT = README, ADR-010#amend-3·#amend-4).
너의 역할은 입력 질문을 1차/공식 출처 기준으로 조사해 신뢰도 라벨이 붙은 리서치 노트를 작성하는 것이다.
입력:
$ARGUMENTS에 리서치 질문/주제가 들어온다 (예: "Stripe Payment Intents 최신 idempotency 정책", "회고 SaaS 경쟁 제품 onboarding 패턴").
반드시 할 일:
- 질문을 검증 가능한 하위 질문 2~4개로 쪼갠다.
- 조사: 무거운 웹 조사는 researcher agent에
Agent위임(노이즈 격리 — 결론 1~2K 토큰만 반환). 가벼운 단건 확인은 본 skill의 WebSearch/WebFetch로 직접. 공식문서·1차 자료·논문 우선, 2차 블로그는 보조. - 각 발견에 출처 URL + 발행일 +
[공식]/[1차]/[2차]신뢰도 라벨. - "사실"과 "제품/구현 시사점(추론)"을 분리한다.
마지막 단계 — 리서치 노트 작성:
- 경로:
docs/10-charter/insights/<YYYY-MM-DD>-<slug>.md(slug는 주제 kebab-case). - 양식:
# Research: <주제>
- 작성일: <YYYY-MM-DD>
- 질문: <원 질문>
- type: research | external-research
## 발견 (신뢰도 라벨)
- [공식] <발견> — <URL> (<발행일>)
- [1차] ...
- [2차] ...
## 사실 ↔ 추론 분리
- 사실: ...
- 제품/구현 시사점(추론): ...
## DISCOVERY 연결 제안
- Evidence Log(§14) 추가 후보: source=<URL>, type=external-research, finding=<...>, confidence=<상/중/하>
- 관련 가정/기회: <A-N 또는 신규>
마지막 출력 (메인에 텍스트로):
- 노트 경로
- 핵심 발견 3개 + 신뢰도 라벨
- DISCOVERY Evidence Log 반영 권장 (자동 반영 X —
/discover-product --update가 회수)
가드:
- workitem / charter / 코드 일체 수정 금지 (insights/ 노트 1개만 Write).
- 추측을 사실처럼 쓰지 않는다. 출처 없는 주장 금지.
Context 정책 (ADR-019)
반드시 먼저 읽을 파일은 최소 충분. 추가 자료는 발화 시 인용 — 사전 fork-load 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.
- 5d ago First seen · 61 lines · 62 tokens per session scan A e828e68b2c2d
research-pack is a skill published in the GitHub repository kohj1018/agentic-dev-harness (2 stars, last pushed 8d ago), licensed MIT. It adds 62 tokens to every session and 866 once invoked, about $0.0003 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
deploy
Use when shipping a release of Agent Sessions — bumping version, updating CHANGELOG, building, signing, notarizing, publishing appcast, and creating a GitHub release.
release-notes
Use when writing or curating the user-facing release copy for an Agent Sessions release — README "What's New", GitHub release notes, Sparkle release notes, or website/launch copy. Not for the internal CHANGELOG, which stays a full development history.
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
add-agent-support
Create and ship AgentSessions support for a new or changed local AI agent/provider. Use when adding, reviewing, testing, documenting, or marketing a provider integration, session parser, transcript source, support-matrix entry, verified-version bump, or provider UI surface; drives the full loop from pre-support…
agent-session-format-check
Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs + tests). Covers session schema, usage/limits tracking, storage backends, and discovery path contracts for all supported agents.
handover
Use when wrapping up or capturing the current state of a coding session — writes a short, dated entry to the repo's RepoHandover.md so a future agent or you can resume without grepping archived sessions. Triggers on "handover", "hand off", "write handover", "capture state", "checkpoint this session".