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/circui-try/circuit/door-closingnpx skills add CIrcui-try/Circuit --skill door-closinggit clone --depth 1 https://github.com/CIrcui-try/CircuitWrote 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/circui-try/circuit/door-closing)<a href="https://agentmods.dev/skills/circui-try/circuit/door-closing"><img src="https://agentmods.dev/badge/skills/circui-try/circuit/door-closing.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 | $0.00030 | $0.01135 |
| Opus 5 | $0.00015 | $0.00567 |
| Sonnet 5 | $0.00006 | $0.00227 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
door-closing 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
이륙 시퀀스의 2단계 (Door-closing). develop을 fetch하고 워크트리를 만든 뒤 구현 계획(plan.md)을 디스크에 작성한다. 코드 변경·푸시는 하지 않는다.
$ARGUMENTS 형식: <ISSUE-ID> [--force]. 예: /door-closing CIR-15.
인자 파싱
$ARGUMENTS에서--force분리. 첫 번째 토큰을<ISSUE>로 사용.<ISSUE>가 없으면 사용법 안내 후 중단.
상태 파일 경로
MAIN_REPO_ROOT = $(git rev-parse --path-format=absolute --git-common-dir | xargs dirname)STATE_FILE = $MAIN_REPO_ROOT/.Codex/state/<ISSUE>.jsonPLAN_FILE = $MAIN_REPO_ROOT/.Codex/state/<ISSUE>.plan.md
자동 체이닝
호출 시 <ISSUE> 의 상태 파일을 읽어 다음 순서로 실행:
stages.boarding.done_at이null이거나--force가 주어졌으면/boarding <ISSUE> [--force]를 먼저 실행. 채워져 있으면boarding skipped (done at <시각>)한 줄만 출력.- 그 다음 본 단계 진행.
자기 단계 실행 절차
-
스킵 판정:
stages.door_closing.done_at이 채워져 있고--force가 없으면 한 줄 요약 출력 후 종료. -
메인 레포로 이동: 워크트리 안이라면
cd $MAIN_REPO_ROOT. -
현재 작업 상태 확인:
git status로 미커밋 변경사항이 있으면 사용자에게 알리고 계속할지 확인. -
develop 최신화:
git checkout develop && git pull origin develop. 충돌 시 사용자 위임 후 중단. -
브랜치명 결정: 상태 파일의
branch필드(boarding 단계가 채움) 사용. 비어있으면 Linear MCPget_issue의gitBranchName으로 다시 채움. -
티켓 상태 동기화: Linear 이슈가
Done/Canceled가 아니면 상태를In Progress로 직접 변경한다. -
워크트리 생성:
- 워크트리 경로:
.Codex/worktrees/<branch>(메인 레포 기준 상대경로). git worktree add .Codex/worktrees/<branch> -b <branch> develop.- 동일 브랜치/경로가 이미 있으면:
--force면 사용자에게 “기존 워크트리 삭제 후 재생성?” 확인 받고git worktree remove --force .Codex/worktrees/<branch>후 재생성.--force가 없으면 기존 워크트리 재사용 (git worktree add .Codex/worktrees/<branch> <branch>).
- 워크트리 경로:
-
구현 계획 작성: 워크트리 안에서 코드 탐색 후
PLAN_FILE작성:# <ISSUE> 구현 계획 ## 목표 - <한 줄 요약> ## 변경 파일 - `<path>` — <변경 사유 한 줄> - ... ## 구현 단계 1. ... 2. ... ## 테스트 전략 - <pytest / Vitest / Playwright / npm run build 항목별로> ## 수락 기준 매핑 - <issue.md 의 수락 기준 → 어떤 변경/테스트로 충족하는지> ## 리스크 / 미해결 질문 - ...탐색 폭이 넓으면 Explore 서브에이전트 1개에 위임.
-
상태 파일 갱신:
worktree_path,plan_path채우고stages.door_closing.done_at = <UTC ISO8601>. -
요약 출력: 워크트리 경로, 변경 파일 수, 구현 단계 수를 한두 문장으로 안내.
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.
- 4d ago First seen · 81 lines · 30 tokens per session scan A fc13366b12e4
door-closing is a skill published in the GitHub repository CIrcui-try/Circuit (5 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 1,135 once invoked, about $0.0002 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
evaluator-write-qa-parallel
Internal Auto-Harness evaluator skill for parallel sprint QA and QA report writing. Use only inside the Evaluator subagent during evaluatorqaparallel.
evaluator-write-qa
Internal Auto-Harness evaluator skill for sprint QA and QA report writing. Use only inside the Evaluator subagent during qa mode.
evaluator-write-retest-parallel
Internal Auto-Harness evaluator skill for parallel sprint retest and retest report writing. Use only inside the Evaluator subagent during evaluatorretestparallel.
evaluator-write-retest
Internal Auto-Harness evaluator skill for sprint retest and retest report writing. Use only inside the Evaluator subagent during retest mode.
generator-build-integrator
Internal Auto-Harness generator skill for worktree-merge build integration. Use only inside the parallel Generator integrator during build mode.
generator-draft-contract-parallel
Internal Auto-Harness generator skill for parallel sprint contract drafting. Use only inside the Generator subagent when it is producing or revising the current parallel sprint contract.