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 commands/circui-try/circuit/boardinggit clone --depth 1 https://github.com/CIrcui-try/CircuitWhat 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 | $0.00027 | $0.01087 |
| Opus 5 | $0.00014 | $0.00544 |
| Sonnet 5 | $0.00005 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
boarding 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 yesterday.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
이륙 시퀀스의 1단계 (Boarding). Linear 이슈를 읽어 요구사항을 정리하고 코드 영향 범위를 메모해 디스크에 캐싱한다. Linear 티켓 상태 동기화 외 원격 부수효과 없음.
$ARGUMENTS 형식: <ISSUE-ID> [--force]. 예: /boarding CIR-15, /boarding CIR-15 --force.
인자 파싱
$ARGUMENTS에서--force토큰 분리. 남은 토큰의 첫 번째를<ISSUE>로 취급.<ISSUE>가 비어있으면 사용법 안내 후 중단:/boarding <Linear 이슈 ID> [--force].
상태 파일 경로
MAIN_REPO_ROOT = $(git rev-parse --path-format=absolute --git-common-dir | xargs dirname)STATE_DIR = $MAIN_REPO_ROOT/.claude/stateSTATE_FILE = $STATE_DIR/<ISSUE>.jsonISSUE_FILE = $STATE_DIR/<ISSUE>.issue.mdSTATE_DIR이 없으면 생성한다.
자기 단계 실행 절차
-
상태 파일 로딩. 없으면 빈 상태(
stages.boarding.done_at = null)로 초기화. -
스킵 판정:
stages.boarding.done_at이 채워져 있고--force가 없으면 한 줄 요약(boarding skipped (done at <시각>)) 출력 후 종료. -
이슈 조회:
mcp__linear-server__get_issue로<ISSUE>조회. 못 찾으면 사용자에게 알리고 중단.Done/Canceled상태면 사용자에게 경고하고 계속 진행할지 확인. -
티켓 상태 동기화: 이슈가 작업 전 상태(Backlog/Triage 등)이면 Linear 상태를
Todo로 직접 변경한다. 이미In Progress,Done,Canceled이면 되돌리지 않는다. -
요구사항 정리: 제목·상태·우선순위·라벨·설명을 분석해 다음 형식으로
ISSUE_FILE작성:# <ISSUE> — <제목> - 상태: <status> - 우선순위: <priority> - 라벨: <labels> - 브랜치: <gitBranchName> ## 요구사항 1. ... 2. ... ## 수락 기준 - ... ## 코드 영향 범위 - <Grep/Glob 으로 식별한 파일·디렉토리 목록과 한 줄 메모> -
코드 영향 범위 탐색: Grep/Glob 으로 이슈 키워드와 매칭되는 파일·심볼을 찾아
코드 영향 범위섹션 채우기. 탐색 범위가 넓으면 Explore 서브에이전트를 1개 띄워 위임. -
상태 파일 갱신: 다음 필드를 채워 저장.
{ "issue": "<ISSUE>", "branch": "<gitBranchName>", "stages": { "boarding": { "done_at": "<UTC ISO8601>" }, "door_closing": { "done_at": null }, "taxiing": { "done_at": null }, "takeoff": { "done_at": null } }, "issue_cache": { "title": "...", "description_md": "...", "labels": [...], "priority": <number>, "status": "...", "fetched_at": "<UTC ISO8601>" }, "issue_summary_path": "<ISSUE_FILE 상대경로>" }
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.
- yesterday First seen · 84 lines · 27 tokens per session scan A d0d7727a442a
boarding is a command published in the GitHub repository CIrcui-try/Circuit (5 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 1,087 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.
Other commands, from other repositories
planwt
You are the orchestrator for a bounded worktree task.
statuswt
You are checking the status of all active worktree task files in the project.
finishwt
You are finishing a worktree task.
harness-parallel
Run the parallel Auto-Harness orchestration flow with worktree workers. /auto-harness:harness-parallel.
harness
Run the full Auto-Harness orchestration flow. /auto-harness:harness.
qa-parallel
Advance parallel Evaluator-side actions only. Auto-selects review, QA, retest, or final report from status.md. /auto-harness:qa-parallel [sprint].