child-session

child-session is a skill for Claude Code from This-HW/claude-code-kit. It costs 58 tokens per session (1,746 once invoked), scanned A, original, MIT.

A set of rules for a worker coding session after a parent session delegates a task to it. The worker confirms its assignment, checks the brief, works in its own branch or worktree, and reports completion in a fixed format.

In plain words
What is it for?
Use it whenever a coding agent receives a task from a coordinating session and must verify its instructions, record its worker status, and return a structured report.
Why use it?
A delegated worker may otherwise misunderstand its scope, use unsafe commands, or change shared code directly. These checks make the handoff and boundaries explicit before implementation starts.

Skill for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions Claude Code; mentions Codex.

Part of the claude-code-kit plugin — 20 skills, 4 hooks shipped together

Good fit Use it whenever a coding agent receives a task from a coordinating session and must verify its instructions, record its worker status, and return a structured report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/this-hw/claude-code-kit/child-session
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 This-HW/claude-code-kit --skill child-session
Clone the repo
git clone --depth 1 https://github.com/This-HW/claude-code-kit

Made for: Claude Code.

Or install claude-code-kit, the plugin that ships this one along with the rest of its 20 skills, 4 hooks.

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 child-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/this-hw/claude-code-kit/child-session/github.svg)](https://agentmods.dev/skills/this-hw/claude-code-kit/child-session)
Your own site
<a href="https://agentmods.dev/skills/this-hw/claude-code-kit/child-session"><img src="https://agentmods.dev/badge/skills/this-hw/claude-code-kit/child-session/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 child-session

Your own site · 80×15
<a href="https://agentmods.dev/skills/this-hw/claude-code-kit/child-session"><img src="https://agentmods.dev/badge/skills/this-hw/claude-code-kit/child-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,746 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 $0.00058 $0.01746
Opus 5.5 $0.00023 $0.00698
Sonnet 5.5 $0.00012 $0.00349
Haiku 4.5 $0.00006 $0.00175

Measured 1mo ago against content hash 92d50dc23723, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

child-session 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 1mo 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.

plugins/common/skills/child-session/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Child Session 스킬

control-loop을 쓰는 부모 세션이 워커를 디스패치할 때 함께 로드하는 스킬이다. 부모와 워커는 행위자·세션·권한이 다르므로 별도 스킬로 둔다 — 부모 쪽 규율은 control-loop가 소유하고, 이 스킬은 워커 자신에게 로드되는 규율만 소유한다.

브리프에 적힌 금지사항을 워커가 어긴 사고가 실제로 있었다 — 원칙을 부모 쪽 문서에만 적어 두는 것만으로는 부족했다. 규율이 워커 자신의 세션에 로드돼야 지켜진다.


0. 인자 4개 확인 — 가장 먼저

디스패치 시 다음 4개와 함께 로드된다:

  1. 부모 세션 이름/식별자
  2. 역할 + 워크트리 경로
  3. 4블록 브리프(전제 / 범위·계약 / 금지사항 / 보고형식 — 스키마 SSOT는 rules/delegation-contract.md)
  4. 금지사항 기본값(push 금지, 통합 브랜치 쓰기 금지, 파괴적 git 명령 금지, 공유 원장 쓰기 금지 등)

하나라도 빠지면 추측하지 않는다. 부모에게 물어라 — 호스트가 제공하는 수단으로. 이 확인이 구현보다 먼저다.

1. 한 줄 확인 보고

인자 4개를 확보했으면, 작업을 시작하기 전에 무엇을 맡았고 어디서 작업하는지 부모에게 한 줄로 확인한다. 이것이 착수 신호다.

2. 마커 기록

로드 시 마커를 쓴다. 위치는 $(git rev-parse --git-dir)/cck/child.json.

  • 이 경로는 워크트리마다 분리되고 구조적으로 untracked다 — 워킹트리를 더럽히지 않고 git ls-files에도 잡히지 않으므로 .gitignore 등재를 따로 검사할 필요가 없다.
  • 내용: rules/child-marker.md 의 스키마를 그대로 따른다 — 키 이름이 고정돼 있다 (schema·parent·role·base_commit·written_at). 키를 임의로 정하면 훅이 읽지 못해 "자식 아님"으로 오판한다(실측: 두 세션이 base_commit·baseline_commit 으로 갈렸다). 부모 없이 스스로 로드했으면 parent 는 "self" 다.
  • 치환으로 쓴다(추가가 아니라) — 새 브리프를 받을 때마다 마커를 덮어쓴다. 같은 워크트리를 다음 작업이 이어받는 경우, 이전 브리프의 부모 이름·기준 커밋이 낡은 채 남아 있는 것을 막는다.
  • 예외 — 주 체크아웃에는 쓰지 않는다. git rev-parse --git-common-dir과 --git-dir이 같은 경로로 나오면 주 체크아웃이다. 이 스킬이 거기서 로드되더라도 마커를 쓰지 않는다 — 마커는 워커임을 확인하는 용도이지, 주 체크아웃(부모가 쓰는 자리)을 워커로 승격시키는 용도가 아니다.
  • gitdir이 없는 비-git 환경으로 폴백할 때만, 마커 대신 상태 파일이 .gitignore에 등재돼 있는지 확인한다.

3. 전제 검증 — 구현보다 먼저

브리프에 적힌 사실 주장을 코드에서 확인한다. "없다 / 신설한다"라고 적혀 있어도 그대로 믿지 않고 grep이나 대상 파일 직접 열람으로 재확인한다. 전제가 틀렸으면 구현하지 않는다 — 멈추고 부모에게 보고한다.

기준 커밋 확인: 브리프에 적힌 해시와 자기 워크트리의 git rev-parse HEAD를 대조한다. 다르면 착수하지 않고 즉시 에스컬레이션한다. 브랜치 이름(main 등)은 기준으로 쓰지 않는다 — 로컬 브랜치는 다른 체크아웃이 물고 있어 낡아 있을 수 있다.

4. 구현 — 금지사항은 명령 수준으로 지킨다

  • 자기 워크트리의 피처 브랜치에만 커밋한다. 통합 브랜치(main 등) 체크아웃·쓰기 금지.
  • push 금지.
  • 데몬·상시 프로세스 재시작 금지 — 부모 세션이나 다른 워커에 영향을 준다.
  • 공유 원장(병합 전 상태를 반영하는 파일) 쓰기 금지 — 병합 전까지 다른 워커·부모에 반영되지 않아 상태가 유실되거나 분기된다.
  • 브리프의 금지사항은 명령 수준으로 지킨다. 예: "읽기만"이 아니라 "--check만 실행, --apply 실행 금지"처럼 구체적으로 해석한다. 원칙 수준 금지("깨뜨리지 않는다") 는 실제로 어겨진 전례가 있다.

Read the full file on GitHub · 114 lines

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. 1mo ago First seen · 114 lines · 58 tokens per session scan A 92d50dc23723

Subscribe to this mod's changes

child-session is a skill published in the GitHub repository This-HW/claude-code-kit (4 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,746 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-08.

Related

Other skills, from other repositories

code-standards

Prabhdeep (Sonu) Singh's personal coding standards — the house rules and quality bar for how code gets written. INVOKE before writing, generating, refactoring, or reviewing ANY code in ANY language — schemas, endpoints, queries, logging, validation, error handling — even when nobody says "standards" or "style".…

PrabhdeepSingh/claude-plugins · 81 tokens

design-tree

Make design decisions as an explicit branching tree — genuine alternatives, decisive rationale, rejected branches preserved. INVOKE PROACTIVELY when planning or designing any implementation approach, or choosing between architectures, libraries, or data models — especially in plan mode. Skip trivial or forced changes…

PrabhdeepSingh/claude-plugins · 62 tokens

self-review

Surface the riskiest parts of the current diff so a reviewer knows where to look hardest — one inline pass on small diffs, one cold read on a cheaper model tier with in-session synthesis on substantial ones. INVOKE PROACTIVELY whenever a change is finished and about to be handed off, reviewed, or shipped. It points…

PrabhdeepSingh/claude-plugins · 79 tokens

ticket-lifecycle

The ticket-as-control-plane rulebook — the single home for the tracker-operations contract, tracker resolution, the type/priority taxonomy, human-only trigger authorization, derived status, and trust boundaries. INVOKE when reading or writing tickets in a queue-driven flow, resolving a repo's tracker, or deciding…

PrabhdeepSingh/claude-plugins · 105 tokens

tdd

Test-driven development — the red-green-refactor discipline for code that's correct by design, not by accident. INVOKE PROACTIVELY whenever writing or changing code, fixing a bug, adding or structuring tests, or choosing what to mock — even when nobody says "TDD" or "tests". (Tests are code held to…

PrabhdeepSingh/claude-plugins · 80 tokens

pr-conventions

Author PR descriptions from the right per-change-type template (the repo's own PULLREQUESTTEMPLATE wins), embed issue-tracker links, keep the description current as fixes land, and reply to human and bot review threads. INVOKE when opening or updating a PR or responding to reviewer comments — inside /sonu:ship or…

PrabhdeepSingh/claude-plugins · 80 tokens