Composio

What it does

When your agent uses it

• Tasks that involve App automation through connectors

Example prompts

• “/composio”

Requirements

• A credential in AGENT_API_TOKEN

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Discover apps with apps("toolkits") and connected accounts with apps("connections"). Follow nextCursor using the cursor query parameter…
2. 2Discover tools with apps("tools?" + new URLSearchParams({toolkit: "gmail", query: "search emails"})). Use actual discovered slugs, input…
3. 3On a human-started turn outside web chat, connect a missing app using apps("authorize", {toolkit: "gmail"}). Present the returned url to…
4. 4Execute using apps("execute", {tool: discovered.slug, accountId: account.id, version: discovered.version, arguments: args}). No project…
5. 5Preserve app-specific instructions: drafts remain drafts, and sending or deleting requires the user's requested action. Treat tool…

What it can do on your machine

Read from SKILL.md and the folder at commit 23af31b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • AGENT_API_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Composio loads about 1.6k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 812 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~62

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yc-software/qm at commit 23af31b, republished under its MIT licence (© yc-software). 812 words, ~1,551 tokens.

name

composio

description

Show the app connection picker or setup widget when users ask to connect apps, reopen setup, or need an app that isn't connected yet. Use QM’s authenticated backend for app discovery, consent, and execution without exposing project keys.

::connect-apps{}

const base = process.env.AGENT_API_URL;
const token = process.env.AGENT_API_TOKEN;
async function apps(path, body) {
  const response = await fetch(`${base}/v1/composio/${path}`, {
    method: body === undefined ? "GET" : "POST",
    headers: { "X-Agent-Capability": token, "Content-Type": "application/json" },
    ...(body === undefined ? {} : { body: JSON.stringify(body) }),
  });
  const result = await response.json();
  if (!response.ok) throw new Error(JSON.stringify(result));
  return result;
}

© yc-software, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills-seed/composio of yc-software/qm.

Open the folder on GitHubat commit 23af31b