task-routine-ko

task-routine-ko is a skill for Claude Code from Kwangseok-Seo/skills. It costs 283 tokens per session (13,023 once invoked), scanned A, original, MIT.

A development workflow that takes a task from design through testing, implementation, verification, review, and a Git commit. It can read tasks from a local Markdown checklist or a GitHub issue, and records recommendations, choices, and outcomes in an append-only log.

In plain words
What is it for?
Use it to work through checklist or GitHub issue tasks in a Git repository, choose manual, assisted, or automatic execution, and review the resulting decision log.
Why use it?
It gives each task a fixed sequence and clear checkpoints, while letting you control which decisions can run without approval. It stops at the commit, so pushing code, opening pull requests, and changing trackers remain manual.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

Part of the kwangseok-seo-skills plugin — 10 skills shipped together

Good fit Use it to work through checklist or GitHub issue tasks in a Git repository, choose manual, assisted, or automatic execution, and review the resulting decision log.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kwangseok-seo/skills/task-routine-ko
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 Kwangseok-Seo/skills --skill task-routine-ko
Clone the repo
git clone --depth 1 https://github.com/Kwangseok-Seo/skills

Made for: Claude Code.

Or install kwangseok-seo-skills, the plugin that ships this one along with the rest of its 10 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 task-routine-ko

README.md
[![agentmods](https://agentmods.dev/badge/skills/kwangseok-seo/skills/task-routine-ko/github.svg)](https://agentmods.dev/skills/kwangseok-seo/skills/task-routine-ko)
Your own site
<a href="https://agentmods.dev/skills/kwangseok-seo/skills/task-routine-ko"><img src="https://agentmods.dev/badge/skills/kwangseok-seo/skills/task-routine-ko/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 task-routine-ko

Your own site · 80×15
<a href="https://agentmods.dev/skills/kwangseok-seo/skills/task-routine-ko"><img src="https://agentmods.dev/badge/skills/kwangseok-seo/skills/task-routine-ko.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 283 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,023 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.
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 $0.00283 $0.13023
Opus 5 $0.00142 $0.06512
Sonnet 5 $0.00057 $0.02605
Haiku 4.5 $0.00028 $0.01302

Measured 10d ago against content hash c1caae1f8051, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

task-routine-ko 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 10d 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/task-routine-ko/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

작업 목록을 받아 각 항목을 고정된 사이클로 커밋까지 몰고 간다: 설계 루프 → 구현 루프(구현 / 검증 / 리뷰) → 커밋.

"그냥 작업하기" 와 다른 점은 둘이다.

  1. 자율성 다이얼. 모든 결정 지점은 위험 등급을 갖는다. 무인 실행은 레벨이 허용 등급이 auto-eligible 일 때만 — 둘 중 하나로는 안 된다. 네 부류의 행위는 auto 를 포함한 모든 레벨에서 사람에게 묻는다.
  2. append-only 결정 로그. 추천 하나, 선택 하나, 나중의 결과 하나가 각각 한 줄로 append 된다. 이 로그가 다이얼을 올릴 근거다 — 다이얼은 감으로 올리지 않는다.

고정 순서: 셋업(1회) → 프로브 → 작업 해석 → 정렬 → 그룹핑 → 항목별 사이클 → 요약.

아래 게이트가 계약이다 — 진입 조건·상한·금지선. 선택지 문안·판단표·절차 등 나머지는 references/ 에 있고 그 경로에 진입할 때 1회만 on-demand 로 읽는다.

이 스킬은 커밋에서 멈춘다. push·PR 생성·머지·회고는 하지 않는다. 그건 이미 쓰고 있는 다른 스킬에 넘긴다.

git 이 필요하고, git 저장소도 필요하다. 나머지는 전부 강등하고 그 사실을 말하지만, git 이 없으면 단위 기준선도 변경 집합도 worktree 도 커밋도 없다 — 실행 자체가 없다.

참조 적재 지도

읽을 파일 시점 매 실행
references/autonomy.md Phase 1 이전 — 레벨 × 등급 표, hard stop 판정, 브레이크 의미론 항상
PHASE-FORMAT.md Phase 1 진입 시 — Phase 1–4 가 화면에 내는 것 항상
references/sources.md 작업 해석 시 — 어댑터 계약, 로컬 마크다운·GitHub 구현 항상
DESIGN-LOOP.md Step 1 진입 시 — 검토 프로토콜, 그리고 스킵 판단이 읽는 스킵 표 항상
BUILD-LOOP.md Step 2 진입 시, 또는 위저드 2번 질문 — 검증·리뷰 도구, 지문 표, 정리 범위, TDD 인계 항상
references/telemetry.md 결정 레코드나 체크포인트를 쓸 때 — 두 스키마, 그리고 Phase 4 의 한 줄이 읽는 문턱값 항상
references/execution.md 한 그룹이라도 항목을 2개 이상 담을 때 — 실행자 계약과 폴백 사다리 조건부
references/setup.md 첫 실행 또는 setup 인자 — 위저드, config 스키마, 능력 프로브 조건부
references/report.md report 인자 — 성적표, 그리고 로그가 말해줄 수 없는 것 조건부

각 파일은 세션당 최대 1회. 이 중 여섯은 매 실행에서 진입하고, 진짜로 지연되는 것은 마지막 셋뿐이다 — 순차 실행이면 execution.md 를, config 가 이미 있으면 setup.md 를, report 가 아닌 실행이면 report.md 를 읽지 않는다. 이 컬럼이 있는 이유는 없을 때의 대안이 이 스킬의 시작 비용을 잘못 말하기 때문이다 — 아홉 개의 지연 적재로 읽히는데 그중 여섯이 매번 일어난다면 그건 참조 적재 지도가 아니다.

Read the full file on GitHub · 249 lines

Files

What ships with it

9 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.

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. 10d ago First seen · 249 lines · 283 tokens per session scan A c1caae1f8051

Subscribe to this mod's changes

task-routine-ko is a skill published in the GitHub repository Kwangseok-Seo/skills (2 stars, last pushed 24d ago), licensed MIT. It adds 283 tokens to every session and 13,023 once invoked, about $0.0014 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.