What is codex-wrapper-sync?

A bridge that copies Codex skills and project instructions into tiguclaw so they can be reused there; Codex skills are folders containing `SKILL.md` instructions.

Use it to import Codex skills or project prompts into tiguclaw; it does not import Claude-style subagents because Codex has no such subagent format.

It avoids recreating Codex guidance for another assistant. It also transfers the important rules from `AGENTS.md`, the project instruction file, into `PROJECT.md`.

codex-wrapper-sync — Skill for Claude Code and Codex by tigu77

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 tigu77/tiguclaw --skill codex-wrapper-sync

Clone the repo

git clone --depth 1 https://github.com/tigu77/tiguclaw

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tigu77/tiguclaw/codex-wrapper-sync/github.svg)](https://agentmods.dev/skills/tigu77/tiguclaw/codex-wrapper-sync)

Your own site

<a href="https://agentmods.dev/skills/tigu77/tiguclaw/codex-wrapper-sync"><img src="https://agentmods.dev/badge/skills/tigu77/tiguclaw/codex-wrapper-sync/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tigu77/tiguclaw/codex-wrapper-sync"><img src="https://agentmods.dev/badge/skills/tigu77/tiguclaw/codex-wrapper-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,554 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.

Model	Per session	Once invoked
Fable 5.1	$0.00141	$0.01554
Opus 5.5	$0.00056	$0.00622
Sonnet 5.5	$0.00028	$0.00311
Haiku 4.5	$0.00014	$0.00155

Measured 1mo ago against content hash c29e772deb28, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-wrapper-sync 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.

skills/codex-wrapper-sync/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-wrapper-sync — Codex 자산을 tiguclaw 로 래핑

Codex 의 스킬을 tiguclaw 의 skills/ 로 가져온다. Codex 스킬도 <dir>/SKILL.md (frontmatter name/description) 포맷이라 tiguclaw 와 동일 → 래핑은 검증 + 복사가 본질. ★Codex 는 Claude Code 식 서브에이전트가 없다(단일 에이전트) → agents 는 대상 아님(스킬만). tiguclaw 는 매 턴 라이브 발견하므로 재시작 불요. 자매 스킬 = claude-wrapper-sync.

0) ★메인 지침 먼저 이해·반영 (AGENTS.md → PROJECT.md)

Codex 스킬은 프로젝트 AGENTS.md(+ 전역 ~/.codex/AGENTS.md 있으면)가 세운 컨벤션·규칙 컨텍스트를 전제한다. 스킬만 복사하면 겉돈다. 순서:

먼저 <project>/AGENTS.md(및 전역)를 Read 해 이해한다.
그 핵심 컨텍스트를 tiguclaw 의 <project>/PROJECT.md 에 반영(AGENTS.md ↔ PROJECT.md, 둘 다 프로젝트 메인 지침). 없으면 요지 정리해 작성(frontmatter name·description·status: active), 있으면 덮어쓰지 말고 스킬 의존 규칙만 보강. verbatim 통째보다 요지 를 담아라(길면 요약).
★LLM-agnostic(#2): PROJECT.md 에 반영해야 어느 어댑터로든 같은 맥락이 선다.
컨텍스트 의존 스킬은 프로젝트 스코프(<project>/.tiguclaw/skills) 래핑 권장 + project_register 등록.

1) 소스·대상 정하기

소스(존재하는 것만):
- 유저 스킬: ~/.codex/skills/<name>/SKILL.md. .system/ 은 제외(skill-creator 등 Codex 빌트인 — 유저 자산 아님).
- (선택) 프로젝트 프롬프트: ~/.codex/prompts/*.md → tiguclaw commands 로 래핑 가능(슬래시커맨드 동형).
- <project>/AGENTS.md: Codex 프로젝트 메인 지침 — §0 에서 이미 PROJECT.md 로 반영(스킬 아닌 컨텍스트).
대상(불명확하면 물어라): 전역 <TIGUCLAW_HOME>/skills (기본) 또는 특정 프로젝트 <project>/.tiguclaw/skills (2026-07-10 메타 폴더 컨벤션 — 프로젝트 자기 폴더와 충돌 회피).
Glob 로 ~/.codex/skills/*/SKILL.md(단 .system 제외) 목록을 만든다.

2) 드라이런 미리보기 (먼저 보여주고 확인)

각 스킬: 이름·소스경로 → 대상경로.
이름 충돌: 대상/빌트인(harness·code-review 등)에 같은 이름이면 ⚠️ + 덮어쓰기 명시 확인(빌트인 클로버링 금지).
frontmatter description 누락 → 드롭(사유 표기). name 은 없어도 폴더/파일명으로 채워진다 — 없다고 버리지 마라.

3) ★래핑 방식 — 전체 복사 (기본이자 원칙)

**원본 내용을 그대로 복사(self-contained)**한다 — 포인터·요약 아님. 자기완결이라 머신·이동·다른 인스턴스 sync 에도 안 깨진다. Codex 원본은 대부분 홈(~/.codex/skills, 머신 종속)이라 포인터 부적합 → 반드시 복사.
★절대·머신종속 경로 절대 금지(/Users/…, C:\…, ~/.codex/… 를 본문에 하드코딩 X). 원본을 참조하지 말고 내용을 복사하라.

3b) 복사 절차 (확인 후)

스킬: ~/.codex/skills/<name>/ 디렉터리 전체 → <대상>/skills/<name>/. SKILL.md(내용 전체) + 보조 파일(스크립트·레퍼런스) 함께(Glob 하위 열거 후 각각 Read/Write). metadata.short-description 등 부가 frontmatter 는 tiguclaw 가 무시 → verbatim 안전.
(선택) 프롬프트→커맨드: ~/.codex/prompts/<name>.md → <대상>/commands/<name>.md (내용 복사).

Read the full file on GitHub · 65 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.

1mo ago Changed c29e772deb28
1mo ago Changed · +1 lines 2c5c99f620c2
1mo ago First seen · 64 lines · 141 tokens per session scan A 41d78c4936b5

Subscribe to this mod's changes

codex-wrapper-sync is a skill published in the GitHub repository tigu77/tiguclaw (9 stars, last pushed today), licensed Apache-2.0. It adds 141 tokens to every session and 1,554 once invoked, about $0.0006 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.

Building agents LLM ai-agent claude mcp personal-assistant self-hosted

github

Interact with GitHub (issues, PRs, repos, releases) using the gh CLI. Use when asked to read or write GitHub state — open an issue, fetch PR diff, comment, list runs, etc.

Team-Commonly/commonly · 49 tokens

pandic-office

Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.

Team-Commonly/commonly · 59 tokens

pdf

Manipulate PDF files — extract text, count pages, render thumbnails, merge or split documents. Use for PDF-specific operations that don't fit markdown-converter (general read) or pandic-office (write from markdown).

Team-Commonly/commonly · 49 tokens

tmux

Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).

Team-Commonly/commonly · 48 tokens

rich-replies

Shape a reply for Telegram: headings, tables, folds, footnotes, formulas, pictures, slideshows, maps, and buttons (choice, link, copy, mini app) inside the text. Load before a structured answer, a comparison, a report in chat, or whenever you offer the user a choice or a link.

smixs/iva-agent · 71 tokens

telegram-userbot

A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.

smixs/iva-agent · 29 tokens