join

A connection tool for attaching to an existing Composer document, a shared, real-time markdown workspace. Once attached, the agent can read it, comment, suggest changes, and respond to mentions.

In plain words
What is it for?
Use it to join a Composer room from its URL or room ID and collaborate on the document.
Why use it?
It lets you work with a document that already exists instead of creating a new one or manually copying its contents.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/hyperactdoting/composer-plugin/join
Any agent
npx skills add hyperactdoting/composer-plugin --skill join
Clone the repo
git clone --depth 1 https://github.com/hyperactdoting/composer-plugin

Made for: Claude Code, Codex.

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,900 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00094 $0.01900
Opus 5 $0.00047 $0.00950
Sonnet 5 $0.00019 $0.00380
Haiku 4.5 $0.00009 $0.00190

Measured yesterday against content hash 38aeeb79bdf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

join 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.

skills/join/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Composer — Join a doc

Composer is a real-time collaborative markdown editor. composer_join_room attaches you to an existing room so you can read, comment, suggest, and respond to mentions.

When to load this skill

  • The user pastes a usecomposer.md/d/<id> URL.
  • They run /composer:join <url> (the slash command delegates here).
  • They ask you to "watch this Composer doc" / "join this room" with a URL or roomId.

If they want to spin up a NEW doc from markdown they've shown you, that's create, not join — load composer:create instead.

Talk like a person, not the MCP

Don't volunteer tool names, internal codes (COMPOSER_AUTH_REQUIRED, HTTP statuses, 4403), file paths, or mechanics ("polling", "device flow"). Translate tool results into plain language before relaying. Verification and room URLs are the exceptions — the user clicks those, paste them verbatim. If the user explicitly asks what's happening under the hood, answer honestly. See composer:create ➜ "Talk like a person, not the MCP" for the full guidance.

Steps

1. Sign in (kick this off immediately, every session)

Same as the composer:create skill: always call composer_login first, before composer_join_room. If the user is already signed in, it returns instantly and you proceed silently. If not, the first call returns COMPOSER_AUTH_REQUIRED with a one-tap approval link — tell the user once (warmly) that you've kicked off sign-in, paste the link verbatim, and immediately call composer_login again to block until they approve. A COMPOSER_AUTH_PENDING return means they haven't approved yet — make sure they've seen the link, then call again to keep waiting. See composer:create step 1 for the full pattern, including the timeout copy and the "don't ask permission, just kick it off" framing.

2. First-run only — agree on the agent's display name

If composer_join_room (step 4) returns an "ask the user what to call you" error, no actingAs name is saved yet. Use the user.name from composer_login to propose a default — "<FirstName>'s Agent" (e.g. "Josh's Agent"). Account name missing or handle-like → fall back to something playful: Monty, Gerty, Rosie, Otto, Pip. Never suggest Claude, Gemini, Sonnet, Opus, Haiku, GPT, or any other model name. Phrase as a single sentence the user can accept or override: "I'll go by Josh's Agent in Composer docs — sound good?" Retry with their answer as actingAs. The name persists to ~/.composer/user.json and is reused forever — this step only happens once per machine.

Read the full file on GitHub · 164 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. yesterday First seen · 164 lines · 94 tokens per session scan A 38aeeb79bdf4

Subscribe to this mod's changes

join is a skill published in the GitHub repository hyperactdoting/composer-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 1,900 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens