threads-web-publish

threads-web-publish is a skill for Claude Code, Codex from Tygb99/threads-writing-skills. It costs 381 tokens per session (4,027 once invoked), scanned A, original, MIT.

A procedure for operating Threads, Meta's social network, through a web browser. It covers publishing, scheduling, editing, replies, images, alternative text, mentions, and direct-message-based posts.

In plain words
What is it for?
Use it to publish or schedule posts, attach photos, add alternative text, create reply chains, edit posts, quote posts, pin replies, or draft posts from messages.
Why use it?
It accounts for browser and Threads behaviours that can lose text, alter hashtags, or invalidate the editing session.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to publish or schedule posts, attach photos, add alternative text, create reply chains, edit posts, quote posts, pin replies, or draft posts from messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tygb99/threads-writing-skills/threads-web-publish
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 Tygb99/threads-writing-skills --skill threads-web-publish
Clone the repo
git clone --depth 1 https://github.com/Tygb99/threads-writing-skills

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.

agentmods badge for threads-web-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/tygb99/threads-writing-skills/threads-web-publish/github.svg)](https://agentmods.dev/skills/tygb99/threads-writing-skills/threads-web-publish)
Your own site
<a href="https://agentmods.dev/skills/tygb99/threads-writing-skills/threads-web-publish"><img src="https://agentmods.dev/badge/skills/tygb99/threads-writing-skills/threads-web-publish/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 threads-web-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/tygb99/threads-writing-skills/threads-web-publish"><img src="https://agentmods.dev/badge/skills/tygb99/threads-writing-skills/threads-web-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 381 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,027 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00381 $0.04027
Opus 5 $0.00191 $0.02014
Sonnet 5 $0.00076 $0.00805
Haiku 4.5 $0.00038 $0.00403

Measured 6d ago against content hash 254c153b2a49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

threads-web-publish 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 6d 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.

threads-web-publish/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threads 웹 발행 운영

Threads 웹은 브라우저 자동화로 다루기에 함정이 많다. 여기 있는 것은 전부 실제로 한 번씩 사고를 내고 알아낸 것들이다.

전제: 로그인 세션에 붙는 브라우저 도구로 조작한다. 상세 문서의 항목에는 확인에 쓴 도구를 적어두었다 — 2026-07-27·07-29 실측은 claude-in-chrome, 2026-07-31과 08-01 일부는 Aside repl, 08-01 사진·업로드 실패 항목은 다시 claude-in-chrome이며 인용카드 항목은 두 도구로 교차 확인했다. 관측이 엇갈릴 때 도구를 바꿔 재현하면 원인을 가릴 수 있으니 도구명을 지우지 말 것.

공식 API는 예약 발행을 지원하지 않는다. 예약이 필요하면 웹을 쓴다.


절대 규칙 5개

이건 매번 적용한다. 나머지는 상황에 맞는 상세 문서를 열어 본다.

  1. 작업 중 새로고침 금지. page.reload()는 작성 중 상태를 초기화하고 ref를 전부 무효화한다. 상태 확인은 새 snapshot()이나 screenshot()으로 한다. 새로고침은 작업이 끝나고 최종 검증할 때 한 번만.

  2. 모든 편집 칸은 .으로 시작해 타이핑하고, 끝나면 맨 앞 1글자를 지운다. 단 이 잘림은 도구별이다 — claude-in-chrome에서는 거의 매번 일어나지만, Aside repl(Playwright keyboard.type)에서는 5회 시도에서 재현되지 않았다(2026-08-25). Aside에서 가드는 무해하지만 필수가 아니고, 가드를 쓰면 "가드 제거가 유실 글자를 상쇄"하는 부작용(아래 함정)이 남으니 문자 단위 대조는 어느 도구든 생략하지 않는다.

  3. 해시태그(주제 태그)는 글당 1개 모델로 바뀌었다 (2026-08-25 Aside repl 실측). 구 규칙 "#태그 공백이 경계를 만든다"는 현재 UI에서 성립하지 않는다 — 공백을 넣어도 첫 #부터 줄 끝까지 통째로 하나의 주제 태그로 파싱되고, 태그 팝업이 뜬 상태에서 Enter를 치면 태그가 본문에서 빠져나가 모달 상단 커뮤니티 또는 주제 검색칸으로 승격된다(저장 결과는 미검증). 기본이 해시태그 0개라 실무 영향은 적지만, 태그를 쓸 거면 여러 개를 본문에 넣으려 하지 말 것.

  4. 팝업은 X 버튼으로 닫는다(해시태그 팝업엔 X가 있고, 멘션 팝업엔 없다 — 멘션은 후보 클릭이나 커서 이동으로). Escape는 조심한다: 팝업이 떠 있으면 첫 Escape는 팝업만 닫지만(2026-08-25 Aside 실측), 팝업이 없는 상태의 Escape는 작성창을 닫아 임시 저장하시겠어요? 확인창을 띄운다. 작업을 이어갈 때는 그 창에서 취소다. 저장 안 함은 되돌릴 수 없다. 본문이 빈 작성창은 확인창 없이 그냥 닫힌다.

  5. 추정 금지 — 확인할 수 있는 것은 확인한다.

    • 댓글 뜻은 대화 전체를 시간순으로 펴서 정한다. 목록·요약에 잘려 나온 한 줄로 판단하지 마라. 같은 댓글을 두 세션 연속 오독한 사례가 있다 — 앞 댓글이 잘린 채로만 보고 뒤 댓글만 읽은 것이 원인이었다. 판정은 {id}/conversation 전문으로 한다.
    • 사진·링크 유무를 규칙에서 역산하지 마라. "브랜드 사진은 상시 첨부"가 규칙이어도 실제 첨부는 API media_type/media_url로 확인한다. 지표 표가 이것 때문에 3건 틀린 적이 있다.
    • 본 것으로 원인을 지어내지 마라. 화면에 결과가 있다고 내가 한 것이 아니다. 사용자도 같은 브라우저를 조작한다. DM이 차단됐다고 보고한 뒤 대화창에 메시지가 보이자 "차단됐는데도 나갔다"고 단정한 적이 있는데, 차단은 맞았고 사용자가 직접 보낸 것이었다. 관측은 옳고 인과가 틀리는 쪽이 더 위험하다 — 모르면 물어본다.
    • 시각은 행동 직전에 다시 찍는다 (TZ=Asia/Seoul date). 8시간 지난 초안의 방금을 그대로 발행할 뻔한 적이 있다.
    • 모르면 채우지 말고 미확인으로 표시해 사람에게 넘긴다.

Read the full file on GitHub · 115 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago Changed 254c153b2a49
  2. 10d ago First seen · 115 lines · 381 tokens per session scan A 6fec3eccb807

Subscribe to this mod's changes

threads-web-publish is a skill published in the GitHub repository Tygb99/threads-writing-skills (48 stars, last pushed 8d ago), licensed MIT. It adds 381 tokens to every session and 4,027 once invoked, about $0.0019 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 2026-08-30.

Related

Other skills, from other repositories

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens