rn-harness-resume

rn-harness-resume is a skill for Claude Code from tjdrhs90/rn-launch-harness. It costs 21 tokens per session (769 once invoked), scanned A, original, MIT.

A recovery step for restarting a paused app-building pipeline from its saved progress. A pipeline is a series of automated stages, and the saved state records where it stopped and why.

In plain words
What is it for?
Use it to resume a paused pipeline, confirm that its pause condition is resolved, restore its running state, and continue with the next stage.
Why use it?
It avoids starting the whole process again after a rate limit, error, or required manual action. It also finds the correct run when several projects are paused.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the rn-launch-harness plugin — 17 skills shipped together

Good fit Use it to resume a paused pipeline, confirm that its pause condition is resolved, restore its running state, and continue with the next stage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tjdrhs90/rn-launch-harness/rn-harness-resume
Install

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.

Any agent
npx skills add tjdrhs90/rn-launch-harness --skill rn-harness-resume
Clone the repo
git clone --depth 1 https://github.com/tjdrhs90/rn-launch-harness

Made for: Claude Code.

Or install rn-launch-harness, the plugin that ships this one along with the rest of its 17 skills.

Wrote 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.

agentmods badge for rn-harness-resume

README.md
[![agentmods](https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-resume/github.svg)](https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-resume)
Your own site
<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-resume"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-resume/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.

agentmods 80×15 button for rn-harness-resume

Your own site · 80×15
<a href="https://agentmods.dev/skills/tjdrhs90/rn-launch-harness/rn-harness-resume"><img src="https://agentmods.dev/badge/skills/tjdrhs90/rn-launch-harness/rn-harness-resume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 769 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00769
Opus 5 $0.00010 $0.00385
Sonnet 5 $0.00004 $0.00154
Haiku 4.5 $0.00002 $0.00077

Measured 11d ago against content hash d7c3088edad4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

rn-harness-resume 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 11d 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.

skills/rn-harness-resume/SKILL.md · 86 lines

What it actually says

rn-harness-resume — 파이프라인 재개

일시정지된 파이프라인을 재개한다. 레이트 리밋, 수동 작업 완료 후 사용.

Trigger

  • /rn-harness --resume
  • 자동 재개 (hooks/stop-failure-handler.sh)

Process

Step 0: 런 워크스페이스 탐색 (Locate the run)

각 런은 격리된 폴더에 있으므로 state.md가 고정 경로에 없다. 후보를 모두 찾는다:

# 스테이징 중인 런(Phase 1–4, depth 5) + 졸업한 프로젝트(Phase 5+, depth 4) 모두 스캔
find . -maxdepth 5 \
  \( -path './.rn-harness/*/docs/harness/state.md' \
     -o -path './*/docs/harness/state.md' \
     -o -path './docs/harness/state.md' \) 2>/dev/null
  • 후보 1개 → 그 폴더가 워크스페이스. workspace_dir로 사용.
  • 후보 여러 개 (여러 런이 진행/일시정지 중) → 각 state.mdrun_id·current_phase·status·updated_at을 요약해 AskUserQuestion으로 어느 런을 재개할지 선택받는다.
  • 후보 0개 → 재개할 파이프라인 없음. 사용자에게 안내 후 종료.

선택된 워크스페이스로 cd한 뒤(이후 모든 경로는 그 안의 docs/harness/ 기준) Step 1로 진행한다.

Step 1: state.md 확인

status: paused
pause_reason: [rate_limit | manual_action | error]
next_role: [재개할 스킬]

Step 2: 재개 조건 확인

rate_limit:

  • 레이트 리밋이 풀렸는지 확인
  • 아직 제한 중이면 대기

manual_action:

  • 사용자에게 수동 작업 완료 여부 확인
  • AskUserQuestion: "수동 작업을 완료하셨나요?"

error:

  • 에러 내용 확인
  • 수정 가능하면 수정 후 재개
  • 수정 불가하면 사용자에게 안내

Step 3: 상태 복구

status: running
pause_reason: ""
resume_attempts: N+1
updated_at: [현재 시간]

Step 4: 역할 루프 재개

next_role에 해당하는 스킬 호출.

Auto-Resume (hooks)

hooks/stop-failure-handler.sh가 레이트 리밋 감지 시:

  1. state.mdstatus: paused, pause_reason: rate_limit
  2. 리셋 시간 파싱
  3. at 명령으로 자동 재개 스케줄
  4. macOS 알림 발송

HARD GATES

  • 재개 전 반드시 런 워크스페이스를 특정하고 그 안에서 작업 (여러 런이면 사용자에게 선택받음)
  • paused 상태가 아니면 재개 불가
  • rate_limit인데 아직 제한 중이면 재개 금지
  • manual_action인데 사용자 확인 없으면 재개 금지
Changes

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.

  1. 11d ago First seen · 86 lines · 21 tokens per session scan A d7c3088edad4

Subscribe to this mod's changes

rn-harness-resume is a skill published in the GitHub repository tjdrhs90/rn-launch-harness (9 stars, last pushed 10d ago), licensed MIT. It adds 21 tokens to every session and 769 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

appstore-publish

A workflow guide for publishing an app to the App Store, including prerequisites, tool loading, submission, and resubmission steps.

jeonghwanko/mimi-seed-sdk · 52 tokens

mimi-seed-update

An update guide for Mimi Seed that identifies the installed version and installation type, then applies the matching update process. It also covers plugin installation.

jeonghwanko/mimi-seed-sdk · 142 tokens

playstore-publish

A guide for publishing to Google Play, including required conditions, tool loading, the run sequence, in-app products, and subscriptions. Google Play is Google’s store for Android apps and digital purchases.

jeonghwanko/mimi-seed-sdk · 62 tokens

mimi-seed

A guide for using Mimi Seed, including required conditions, loading its tools, the execution flow, and linking local login details to a remote MCP service. MCP is a way for an agent to use tools provided by another program or service.

jeonghwanko/mimi-seed-sdk · 111 tokens

video-create-publish

Create, render, validate, and optionally publish polished short-form videos and YouTube Shorts with Mimi Seed. Use for story-to-video production, vertical social videos, carousel-to-video adaptations, visual-quality revisions, or YouTube upload/status work where typography, shorts-style burned captions, human-safe…

jeonghwanko/mimi-seed-sdk · 106 tokens

deploy

A Mimi Seed release workflow that connects CI builds, release-readiness checks, release-note creation, and store updates. CI is automated software that builds and checks code; the stores are Google Play and Apple’s App Store.

jeonghwanko/mimi-seed-sdk · 73 tokens