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 instructions/chussum/mobius/claude-mdgit clone --depth 1 https://github.com/chussum/mobiusWrote 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/instructions/chussum/mobius/claude-md)<a href="https://agentmods.dev/instructions/chussum/mobius/claude-md"><img src="https://agentmods.dev/badge/instructions/chussum/mobius/claude-md.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 | $0.24098 | $0.24098 |
| Opus 5 | $0.12049 | $0.12049 |
| Sonnet 5 | $0.04820 | $0.04820 |
| Haiku 4.5 | $0.02410 | $0.02410 |
Grade A, and why
mobius CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
invalid_grant는 원인이 딴판). (2) URLSession vs 참조 클라이언트(python/curl)를 **더미 자격으로** How it starts
The opening of the file, as written. The whole thing — 791 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobius (뫼비우스) — Claude·Codex 계정 매니저
Claude Code CLI + Claude Desktop + OpenAI Codex CLI 계정을 전환/자동 전환 하는
macOS 메뉴바 앱 + mobius CLI. Swift Package (SwiftUI, macOS 14+).
프로바이더(claude/codex)별 독립 풀 — 각 풀에서 primary 소진 → fallback 자동 전환 →
primary 회복 시 자동 복귀. 사용자 노출 용어는 '자동 전환'(구 '자동 fallback').
이 파일은 항상 최신 상태로 유지한다. 구조·핵심 사실·실패 기록이 바뀌면 같은 커밋에서 갱신할 것.
빌드 / 실행
swift test # 유닛 테스트 (MobiusCore)
swift build # 컴파일 확인
Scripts/make-app.sh # dist/Mobius.app 번들 조립 + 서명
Scripts/make-dmg.sh # dist/Mobius-<ver>.dmg 배포 이미지 (드래그 설치)
open dist/Mobius.app # 실행 (메뉴바 ∞ 아이콘)
Scripts/setup-signing.sh # (1회) 고정 서명 인증서 생성 — 아래 '서명' 참조
구조
Sources/MobiusCore/ 앱·CLI 공유 코어 (전부 의존성 주입 → 테스트 가능)
MobiusEnvironment.swift 모든 경로 컨테이너 (MOBIUS_HOME/CODEX_HOME 오버라이드)
Models.swift Provider / AccountProfile / AccountsFile(프로바이더별 풀) / RateLimitInfo
ProviderConfigIO.swift 프로바이더 어댑터 프로토콜 (secret data = 프로바이더 정의 바이트)
KeychainClient.swift SystemKeychain + InMemoryKeychain(테스트)
ClaudeConfigIO.swift Claude 자격증명 읽기/쓰기 (★ 아래 '진실의 원천' 필독)
AccountStore.swift 프로필 영속(accounts.json) + 비밀 스냅샷(0600 파일, opaque Data)
CodexConfigIO.swift Codex 자격증명 읽기/쓰기 (auth.json 통째 스왑, JWT 신원)
Switcher.swift 전환/되저장/롤백/reconcile/adopt — 등록된 어댑터 풀 전체에 적용
RateLimitParser.swift Claude 세션 로그 rate-limit 이벤트 파서 (실측 기반)
CodexRateLimitParser.swift Codex rate_limits 상태 파서 (매 턴 in-band, 게이지+소진 판정)
CodexStatusRouter.swift Codex 상태의 계정 귀속 — 전환 전 세션 파일 격리 (오염 방지 ★아래)
SessionLogWatcher.swift 세션 로그 tail — (루트, 파서, 정책) 주입 제네릭 (네트워크 0)
AutoSwitchEngine.swift 순수 상태머신, 풀당 1인스턴스 (쿨다운/마진/autoSwitchedFromPrimary,
on/off는 풀별 autoSwitchByProvider — 기록 없는 풀은 켬; 모델스코프 pin)
UsageFetcher.swift Claude usage 엔드포인트 조회 (게이지용, 팝오버 열 때만; Codex는 로그로 대체)
모델 스코프 주간 한도(weekly_scoped)도 파싱 → ScopedUsageLimit
SyncEngine.swift 멀티 Mac 동기화 (클라우드 폴더 미러, ★ 아래 '동기화 원칙')
UpdateChecker.swift GitHub 릴리스 업데이트 확인 (하루 1회)
Sources/mobius/ CLI (list/switch/status/capture/auto)
Sources/MobiusApp/ SwiftUI 메뉴바 앱 + AppState + Views/ + LoginFlow + DesktopCoordinator
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 · 791 lines · 24,098 tokens per session scan A 8d53cf20a7bb
mobius CLAUDE.md is an instructions file published in the GitHub repository chussum/mobius (58 stars, last pushed 7d ago), licensed MIT. It adds 24,098 tokens to every session, about $0.1205 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Unity-MCP copilot-instructions.md
Copilot instructions for IvanMurzak/Unity-MCP, covering project guidelines, critical rules, no c# reflection for private access, code review and code style.
mcp-erpnext AGENTS.md
AGENTS.md instructions for Casys-AI/mcp-erpnext, covering agents.md, project overview, project structure & module organization, build, test, and development commands and run all tests (also: deno task test).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
mcp-erpnext CLAUDE.md
Claude Code instructions for Casys-AI/mcp-erpnext: See AGENTS.md for all repository guidelines, architecture, conventions, and task recipes.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
powerbi-mcp CLAUDE.md
Instructions for sulaiman013/powerbi-mcp, covering claude.md and developer notes.