agentmods.dev

Circuit: Command for Claude Code

.claude/commands/taxiing.md

taxiing is a command for Claude Code from CIrcui-try/Circuit. It costs 32 tokens per session (1,116 once invoked), scanned A, original, MIT.

A local implementation step that follows a saved plan in a Git worktree, a separate working directory for a branch.

In plain words
What is it for?
Use it with an issue ID to prepare earlier workflow stages when needed, implement the plan, update the issue status, track tasks, and create intermediate commits.
Why use it?
It keeps implementation work tied to the issue plan while preventing this stage from pushing changes or opening a pull request.

Command for Claude Code

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

This is CIrcui-try/Circuit's own configuration. It tells Claude Code how to work on Circuit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Circuit configures →

not rated 5repo 5mo ago A scan 32 tokens original MIT
View source ↗ CIrcui-try/Circuit circui-try.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to CIrcui-try/Circuit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/CIrcui-try/Circuit/main/.claude/commands/taxiing.md
Clone the repo
git clone --depth 1 https://github.com/CIrcui-try/Circuit

Made for: Claude Code.

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 taxiing

README.md
[![agentmods](https://agentmods.dev/badge/commands/circui-try/circuit/taxiing/github.svg)](https://agentmods.dev/commands/circui-try/circuit/taxiing)
Your own site
<a href="https://agentmods.dev/commands/circui-try/circuit/taxiing"><img src="https://agentmods.dev/badge/commands/circui-try/circuit/taxiing/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 taxiing

Your own site · 80×15
<a href="https://agentmods.dev/commands/circui-try/circuit/taxiing"><img src="https://agentmods.dev/badge/commands/circui-try/circuit/taxiing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,116 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 $0.00032 $0.01116
Opus 5.5 $0.00013 $0.00446
Sonnet 5.5 $0.00006 $0.00223
Haiku 4.5 $0.00003 $0.00112

Measured 2mo ago against content hash 7a45fe83a4a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

taxiing 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 2mo 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.

.claude/commands/taxiing.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

이륙 시퀀스의 3단계 (Taxiing). door-closing 에서 작성한 plan.md 를 따라 워크트리 안에서 코드를 구현하고 중간 커밋한다. git push, gh pr create 같은 원격 부수효과는 절대 수행하지 않는다.

$ARGUMENTS 형식: <ISSUE-ID> [--force]. 예: /taxiing CIR-15.

인자 파싱

  1. --force 분리. 첫 토큰을 <ISSUE> 로.
  2. <ISSUE> 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/.claude/state/<ISSUE>.json
  • PLAN_FILE = $MAIN_REPO_ROOT/.claude/state/<ISSUE>.plan.md

자동 체이닝

상태 파일을 읽어 다음 순서로 실행:

  1. boarding.done_at == null 이거나 --force → /boarding <ISSUE> [--force] 실행. 채워져 있으면 스킵 메시지 한 줄.
  2. door_closing.done_at == null 이거나 --force → /door-closing <ISSUE> [--force] 실행. 채워져 있으면 스킵 메시지 한 줄.
  3. 본 단계 진행.

자기 단계 실행 절차

  1. 스킵 판정: taxiing.done_at 이 채워져 있고 --force 가 없으면 스킵 메시지 출력 후 종료.
  2. 워크트리 진입: 상태 파일의 worktree_path 를 사용해 워크트리 디렉토리로 cd. 경로가 없으면 /door-closing <ISSUE> --force 안내 후 중단.
  3. 티켓 상태 동기화: Linear 이슈가 Done/Canceled 가 아니면 상태를 In Progress 로 직접 변경한다.
  4. plan.md 로딩: PLAN_FILE 을 읽어 구현 단계 / 변경 파일 / 테스트 전략 / 수락 기준을 파악.
  5. 구현 진행:
    • 구현 단계 항목을 TodoWrite 로 펼쳐 진행 상황 추적.
    • 코드 작성 시 백엔드는 Router → Service → Repository, 프런트엔드는 Data/Domain/Presentation 레이어 컨벤션을 따른다.
    • 의미 있는 단위마다 영어 Conventional Commits 스타일로 커밋. 형식: <type>: <English summary> (<ISSUE>) 예 feat: add numeric keypad component (CIR-21).
  6. 테스트 작성·실행:
    • 백엔드 변경: pytest 통과 확인.
    • 프런트엔드 변경: Vitest(단위) 또는 Playwright(E2E), 그리고 npm run build 통과 확인.
    • 실패하면 다음 단계로 넘어가지 않고 해결한다.
  7. console.log 검사: 변경된 프런트엔드 파일에 console.log 가 남아있으면 사용자에게 알린다.
  8. 남은 변경 커밋: git status 가 깨끗해질 때까지 커밋. 커밋되지 않은 변경이 남으면 종료하지 않는다.
  9. 상태 파일 갱신: taxiing.done_at = <UTC ISO8601> 저장.
  10. 요약 출력: 추가된 커밋 수와 통과된 테스트 종류를 한두 문장으로 안내.

주의사항

  • git push, gh pr create, gh pr edit, git push --force* 절대 금지. 그건 takeoff 책임.
  • develop / main 에 직접 커밋 금지.
  • 커밋 메시지는 반드시 영어로 작성한다. 한국어를 쓰지 않는다.
  • .env, credentials.json 등 민감한 파일은 스테이징에서 제외.
  • 구현 중 불명확한 점은 임의 판단하지 말고 사용자에게 질문.
  • Linear 티켓 상태는 자동화에 위임하지 않고 직접 Todo → In Progress → Done 으로만 처리한다.
  • --force 사용 시 — taxiing 만 다시 돌리는 의미는 거의 없으므로(이미 커밋된 코드를 되돌릴 수 없음) 사용자에게 “기존 커밋을 그대로 두고 plan 잔여분만 이어서 진행할까, 아니면 사용자가 직접 reset 후 재호출할까” 한 번 확인 받는다.

Read the full file on GitHub · 58 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. 2mo ago First seen · 58 lines · 32 tokens per session scan A 7a45fe83a4a0

Subscribe to this mod's changes

taxiing is a command published in the GitHub repository CIrcui-try/Circuit (5 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,116 once invoked, about $0.0001 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 2026-08-31.

CommitsGit and workflowPlanningagentaicircuitcodexharness-engineeringskills
Related

Other commands, from other repositories

commit

Based on the above changes, create a single git commit.

anthropics/claude-plugins-official · 4 tokens

vios-git

VIOS git conventions: branch names, commit messages, and merge-request descriptions. Use before creating any branch, commit, or MR.

NVIDIA-AI-Blueprints/video-search-and-summarization · 32 tokens

commit

Run when user calls /commit or asks to generate a commit message. Analyzes staged changes and writes a structured commit message.

guanyang/open-agent-hub · 28 tokens

fix-comments

Address PR review comments by implementing requested changes automatically.

rohitg00/awesome-claude-code-toolkit · 13 tokens

commit-push-pr

Commit, push, and open a PR.

fuxicodex/Fuxi · 8 tokens

commit

Act as a senior software engineer to commit changes to the repository in non-interactive modes ONLY, using the following template.

paralleldrive/aidd · 0 tokens