Agent skill

Composio CLI

by rome-os in rome-os/rome

Help users operate the published Composio CLI to find the right tool, connect accounts, inspect schemas, execute tools, subscribe to trigger events with composio listen, script workflows with…

MITAuto-check passedProductivity & Automation

Install Composio CLI

skills CLI
$ npx skills add rome-os/rome --skill composio-cli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rome-os/rome composio-cli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rome-os/rome.git skills-src && mkdir -p .claude/skills && cp -r skills-src/rome_apps/connector/src/skills/composio-cli .claude/skills/composio-cli && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
composio-cli
GitHub stars
725
Token cost
~2.7k tokens
SKILL.md length
1,082 words
Files
1
Skills in repo
18
Repo updated
First seen
Licence
MIT

At a glance

Help users operate the published Composio CLI to find the right tool, connect accounts, inspect schemas, execute tools, subscribe to trigger events with composio listen, script workflows with…

  • Works in 5 steps: Start with composio execute whenever the… → If several independent tool calls must… → If execute says the toolkit is not… → …
  • Events with composio listen
  • SKILL.md covers Preflight: Is The User Logged…, Connection Invariant: One…, Default Workflow and execute - Run A Tool, plus 6 more sections
  • Calls npm; reaches api.github.com

What it does

Composio CLI is an agent skill from rome-os/rome. Help users operate the published Composio CLI to find the right tool, connect accounts, inspect schemas, execute tools, subscribe to trigger events with composio listen, script workflows with composio run, and call authenticated app APIs with composio proxy. Use when the user asks how to do something with composio, wants to run a known tool slug, needs to discover a slug with composio search, fix a missing connection with composio link, inspect tool inputs with --get-schema or --dry-run, troubleshoot top-level…

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering App automation through connectors. It works with Composio and Gmail. The repository describes itself as: A compounding agent OS for recursive agents. Also an open source alternative to Grok Bot and Meta's Muse. The licence is MIT.

When your agent uses it

  • Events with composio listen
  • Script workflows with composio run
  • Call authenticated app APIs with composio proxy
  • The user asks how to do something with composio

Example prompts

  • “/composio-cli”

Requirements

  • Node.js

Workflow steps

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

  1. Start with composio execute whenever the slug is known.
  2. If several independent tool calls must happen at once, use composio execute -p/--parallel with repeated -d groups.
  3. If execute says the toolkit is not connected, run composio link and retry.
  4. If the arguments are unclear, run composio execute --get-schema or --dry-run before guessing.
  5. Reach for composio search "" only when the slug is unknown. search accepts one or more queries, so batch related discovery work into a…

What it can do on your machine

Read from SKILL.md and the folder at commit ed26d88. 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

    Shell commands in SKILL.md call:

    • npm

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.github.com

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Composio CLI loads about 2.7k tokens when it runs. Until then it costs about 150 tokens; SKILL.md has 1,082 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~150
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 rome-os/rome at commit ed26d88, republished under its MIT licence (© rome-os). 1,082 words, ~2,656 tokens.

Download SKILL.mdSave it as .claude/skills/composio-cli/SKILL.md (or your agent's skills folder).
name
composio-cli
description
Help users operate the published Composio CLI to find the right tool, connect accounts, inspect schemas, execute tools, subscribe to trigger events with `composio listen`, script workflows with `composio run`, and call authenticated app APIs with `composio proxy`. Use when the user asks how to do something with `composio`, wants to run a known tool slug, needs to discover a slug with `composio search`, fix a missing connection with `composio link`, inspect tool inputs with `--get-schema` or `--dry-run`, troubleshoot top-level CLI flows, or explicitly needs `composio dev` guidance.

Composio CLI

Preflight: Is The User Logged In?

Before running any toolkit command, confirm the user is logged in. If they are not, stop and tell them to log in — do not improvise.

bash
composio whoami   # exits non-zero when there is no session

If whoami fails (no Composio session), the user is logged out. Stop here. Do not:

  • run composio login yourself,
  • look for an alternate toolkit, slug, or proxy route,
  • ask the user to paste a key, or
  • attempt any other workaround.

Respond directly to the user with one message: they need to log in to Composio first, via the "Log in with Composio" action on the Composio app's dashboard. Then end your turn and wait — the request cannot proceed until they have logged in.

Only once whoami succeeds do you continue to the workflow below.

Connection Invariant: One Account Per Toolkit

Rome operates exactly one connected account per toolkit. This is load-bearing because execute, proxy, and run have no flag to choose an account — they act on the toolkit's single connected account, and when more than one exists Composio silently resolves a non-deterministic default. You cannot tell, and cannot control, which account a tool ran as. A second Gmail means a "send email" might go out from the wrong account with no signal.

To keep every tool call deterministic:

  • Never create a second account for a toolkit. Do not pass --alias to composio link to add an additional account, and do not enable the multi_account experimental feature. The alias buys you nothing on execution — there is no --alias/--account on execute — it only lets you accumulate ambiguous accounts.
  • Check before linking. composio link <toolkit> --list shows existing accounts. If one is ACTIVE, you are connected — retry execute, do not link again.
  • If --list shows more than one account for a toolkit, stop and surface it. Tell the user the toolkit has duplicate accounts and tool calls are ambiguous until the extras are removed. Do not guess which one to use.

Default Workflow

  1. Start with composio execute <slug> whenever the slug is known.
  2. If several independent tool calls must happen at once, use composio execute -p/--parallel with repeated <slug> -d <json> groups.
  3. If execute says the toolkit is not connected, run composio link <toolkit> and retry.
  4. If the arguments are unclear, run composio execute <slug> --get-schema or --dry-run before guessing.
  5. Reach for composio search "<task>" only when the slug is unknown. search accepts one or more queries, so batch related discovery work into a single command when useful.

execute - Run A Tool

Use execute when the tool slug is already known.

bash
composio execute GITHUB_GET_THE_AUTHENTICATED_USER -d '{}'

Inspect required inputs without executing:

bash
composio execute GITHUB_CREATE_AN_ISSUE --get-schema

Preview safely:

bash
composio execute GITHUB_CREATE_AN_ISSUE --skip-connection-check --dry-run -d '{ owner: "acme", repo: "app", title: "Bug report", body: "Steps to reproduce..." }'

Pass data from a file or stdin:

bash
composio execute GITHUB_CREATE_AN_ISSUE -d @issue.json
cat issue.json | composio execute GITHUB_CREATE_AN_ISSUE -d -

Upload a local file:

bash
composio execute SLACK_UPLOAD_OR_CREATE_A_FILE_IN_SLACK \
  --file ./image.png \
  -d '{ channels: "C123" }'

Run independent tool calls in parallel:

bash
composio execute --parallel \
  GMAIL_SEND_EMAIL -d '{ recipient_email: "a@b.com", subject: "Hi" }' \
  GITHUB_CREATE_AN_ISSUE -d '{ owner: "acme", repo: "app", title: "Bug" }'

Key flags:

  • --get-schema: Inspect required arguments without executing the tool.
  • --dry-run: Preview the request shape without performing the action.
  • --file: Inject a local file path into a tool that exposes exactly one uploadable file argument.
  • --parallel: Execute multiple independent tool calls in the same invocation.

There is no flag to pick an account — execute uses the toolkit's single connected account (see "Connection Invariant" above). Keep one account per toolkit so this is unambiguous.

  • --file only works when the tool exposes a single uploadable file input. Otherwise use explicit -d JSON.

search - Find The Slug

Use search only when the tool slug is not already known.

bash
composio search "create a github issue"
composio search "send an email" --toolkits gmail
composio search "send an email" "create a github issue"
composio search "my emails" "my github issues" --toolkits gmail,github
  • Batch related discovery work into one search invocation, then move back to execute once the correct slugs are known.

Use link when execute reports that a toolkit is not connected, or when the user explicitly wants to authorize an account.

bash
composio link gmail
composio link gmail --list          # inspect existing accounts before linking
composio link googlecalendar --no-browser

Key flags:

  • --list: List the toolkit's existing connected accounts instead of linking. Run this first — if an account is already ACTIVE, retry execute rather than linking.

  • --alias: Names an additional account for a toolkit (requires the multi_account experimental feature). Avoid it — Rome keeps one account per toolkit, and extra accounts make execute ambiguous (see "Connection Invariant").

  • Retry the original execute command after linking succeeds.

Show full SKILL.md (419 more words)Show less

proxy - Raw API Access

Use proxy when a toolkit supports a raw API operation that is easier than finding a dedicated tool slug.

bash
composio proxy https://api.github.com/user --toolkit github --method GET </dev/null

run - Scripting, LLMs, and Programmatic Workflows

For programmatic calls, loops, output plumbing, or anything beyond a single tool call, prefer composio run.

composio run executes an inline ESM JavaScript/TypeScript snippet with authenticated execute(), search(), proxy(), and the experimental experimental_subAgent() helper pre-injected. No SDK setup required.

Chain multiple tools:

bash
composio run '
  const me = await execute("GITHUB_GET_THE_AUTHENTICATED_USER");
  const emails = await execute("GMAIL_FETCH_EMAILS", { max_results: 1 });
  console.log({ login: me.data.login, fetchedEmails: !!emails.data });
'

Fan out with Promise.all:

bash
composio run '
  const [me, emails] = await Promise.all([
    execute("GITHUB_GET_THE_AUTHENTICATED_USER"),
    execute("GMAIL_FETCH_EMAILS", { max_results: 5 }),
  ]);
  console.log({ login: me.data.login, emailCount: emails.data.messages?.length });
'

Feed tool output into an LLM and get structured JSON back:

bash
composio run --logs-off '
  const emails = await execute("GMAIL_FETCH_EMAILS", { max_results: 5 });
  const brief = await experimental_subAgent(
    `Summarize these emails and count them.\n\n${emails.prompt()}`,
    { schema: z.object({ summary: z.string(), count: z.number() }) }
  );
  console.log(brief.structuredOutput);
'
  • Use top-level execute --parallel instead when the user only needs a few independent tool calls and does not need script logic.

Bundled Scripts

Reusable scripts ship in rome_apps/composio/scripts/ and are invoked via composio run -f.

gmail-parse-markdown.ts — Gmail → Markdown

GMAIL_FETCH_EMAILS returns each body as raw HTML — a single 50-message page is typically ~200k tokens, dominated by HTML markup and tracking URLs. This script fetches messages and converts each body to clean Markdown using @mozilla/readability (with a turndown fallback when readability mis-fires on transactional emails). Cuts a 50-message page to ~3-15k tokens depending on content.

Reach for it any time the user wants Gmail content fed to an LLM, summarized, or otherwise processed as text — not when they need raw HTML.

bash
# One-time setup (deps live alongside the script, not in the workspace):
(cd rome_apps/composio/scripts && npm install)

# Default: drop tracking URLs, keep anchor text, strip images
composio run -f rome_apps/composio/scripts/gmail-parse-markdown.ts -- --max 20

# Keep links inline (use only when downstream needs the URLs)
composio run -f rome_apps/composio/scripts/gmail-parse-markdown.ts -- \
  --query "is:unread newer_than:1d" --max 50 --include-links

Flags:

  • --query "<gmail-query>" — Gmail search query (e.g. "is:unread newer_than:1d")
  • --max <N> — max_results (default 10, max 500)
  • --page-token <token> — pagination cursor from a prior nextPageToken
  • --include-links — keep inline links (default strips URLs but preserves anchor text; ~3x token savings)
  • --raw — also return the original messageText alongside markdown (debugging only)

Output is JSON on stdout: { messages: [{ messageId, threadId, sender, subject, markdown, bodyFormat, ... }], nextPageToken, resultSizeEstimate, options }.

Auth

bash
composio whoami   # check current session — run this first (see Preflight above)

When whoami fails the user is logged out. Do not run composio login on their behalf and do not work around the missing session. Tell the user to log in via the dashboard and stop — see "Preflight: Is The User Logged In?" above.

The Composio Rome app reads the key live from the CLI session (~/.composio/user_data.json) — that session is the single source of truth; the app stores no copy of its own. Its dashboard exposes Composio login as one explicit browser action: "Log in with Composio" (or "Re-authorize" once logged in) opens Composio in a new tab to authorize Rome, which writes the issued key into the CLI session. The dashboard deliberately hides the CLI mechanics — the guardian just sees the button.

Because the app reads the CLI session directly, a composio login you (the agent) run in this terminal is picked up automatically — there is no separate "import" step.

© rome-os, 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 rome_apps/connector/src/skills/composio-cli of rome-os/rome.

Open the folder on GitHubat commit ed26d88

Compare with similar skills

Composio CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Composio CLI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Composio CLI this skillrome-os/rome725—~2.7kAutomated safety check: PassMIT
Connect Apps with ComposioComposioHQ/awesome-claude-skills77k3 repos~557Automated safety check: PassNone
Composio Cloud Toolsquarqlabs/argus277—~543Automated safety check: PassApache-2.0
Gmail Automationdavepoon/buildwithclaude3.6k4 repos~2.7kAutomated safety check: PassMIT
ComposioComposioHQ/composio30k1 repos~1.7kAutomated safety check: PassMIT
Openloomi Connectorsmelandlabs/openloomi1k—~3.3kAutomated safety check: PassApache-2.0

Similar skills

  • Connect Apps with Composio

    ComposioHQ/awesome-claude-skills

    Connects an agent to 1000+ external apps through the Composio Tool Router plugin, so it can actually send emails, create issues and post messages instead of only drafting them.

    77k GitHub starsUsed in 3 repos~557 tokens
    Productivity & AutomationAuto-check passed
  • Composio Cloud Tools

    quarqlabs/argus

    Routes requests to external SaaS apps such as GitHub, Gmail, Google Calendar, Slack, Notion and Linear through cloud tools, with safeguards on irreversible actions.

    277 GitHub stars~543 tokensUpdated 4 mo ago
    Productivity & AutomationAuto-check passed
  • Gmail Automation

    davepoon/buildwithclaude

    Automate Gmail tasks via Rube MCP (Composio): send/reply, search, labels, drafts, attachments.

    3.6k GitHub starsUsed in 4 repos~2.7k tokens
    Productivity & AutomationAuto-check passed
  • Composio

    ComposioHQ/composio

    Route and complete Composio work across Composio For You and Composio Platform.

    30k GitHub starsUsed in 1 repo~1.7k tokens
    Productivity & AutomationAuto-check passed
  • Openloomi Connectors

    melandlabs/openloomi

    openloomi Connectors tools - manage the native 7 messaging integrations and pair with the composio skill for the 1000+ apps OAuth layer (Slack, Discord, X, Gmail, Outlook, Google…

    1k GitHub stars~3.3k tokensUpdated 14 days ago
    Productivity & AutomationAuto-check passed
  • Composio

    yc-software/qm

    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.

    15k GitHub stars~1.6k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from rome-os/rome

All 18 skills in this repo
  • Color Audit

    rome-os/rome

    Audit a design system's color palette against measurable color-science disciplines — WCAG/APCA contrast of declared token pairs, perceptual (OKLCH) ramp uniformity, color-blindness safety of…

    725 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Audit the subordinate copy in a UI — section descriptions, field helper text, hints, card subtitles, empty-state body copy, tooltip bodies — against the secondary-text ruleset, and emit a per-string…

    725 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • UX Semantics Audit

    rome-os/rome

    Audit an existing UI/UX design (React/JSX/TSX components, HTML, or generated app code) against a tiered ruleset of verifiable UX principles, and produce structured, evidence-cited findings that a…

    725 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Add a new Rome-managed OAuth integration for a third-party service so a user can delegate access by clicking Connect, and Rome can act on the service with the delegated token (the GitHub/Slack model…

    725 GitHub stars~3.6k tokensUpdated today
    Auto-check passed
  • File Issue

    rome-os/rome

    File one GitHub issue from a description the user gives — classify it as a bug report, feature request, or task spec, gather what the body needs from the tracker and the code, ask the user only for…

    725 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Routine From Chat

    rome-os/rome

    Turn a plain-language "do this automatically" request into a routine — either event-triggered ("text me when I get an email from my landlord") or scheduled ("remind me every Friday at 9am").

    725 GitHub stars~3.8k tokensUpdated today
    Auto-check passed

Works with

Questions about Composio CLI

What does Composio CLI do?

Help users operate the published Composio CLI to find the right tool, connect accounts, inspect schemas, execute tools, subscribe to trigger events with composio listen, script workflows with…. Composio CLI is an agent skill from rome-os/rome. Help users operate the published Composio CLI to find the right tool, connect accounts, inspect schemas, execute tools, subscribe to trigger events with composio listen, script workflows with composio run, and call authenticated app APIs with composio proxy.

When should I use Composio CLI?

Composio CLI fits situations like: events with composio listen; script workflows with composio run; call authenticated app APIs with composio proxy; the user asks how to do something with composio.

How do I install Composio CLI in Claude Code?

Run `npx skills add rome-os/rome --skill composio-cli -a claude-code`. Or copy the skill folder (rome_apps/connector/src/skills/composio-cli in rome-os/rome) into .claude/skills/composio-cli in your project. Claude Code loads it when a task matches its description.

How do I install Composio CLI in Codex?

Run `npx skills add rome-os/rome --skill composio-cli -a codex`. Or copy the skill folder (rome_apps/connector/src/skills/composio-cli in rome-os/rome) into .agents/skills/composio-cli in your project. Codex loads it when a task matches its description.

Can I use Composio CLI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rome-os/rome --skill composio-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/composio-cli, .gemini/skills/composio-cli, .github/skills/composio-cli and .opencode/skills/composio-cli in your project.

What does Composio CLI need to run?

Going by SKILL.md and its folder, Composio CLI needs the command-line tools its instructions call (npm). Our summary lists: Node.js.

Does Composio CLI access the network?

SKILL.md names 1 domain. In commands or code: api.github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Composio CLI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Composio CLI use?

Composio CLI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Composio CLI use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Composio CLI?

Skills that share tags, products or a category with Composio CLI: Connect Apps with Composio (ComposioHQ/awesome-claude-skills, 77k stars), Composio Cloud Tools (quarqlabs/argus, 277 stars), Gmail Automation (davepoon/buildwithclaude, 3.6k stars) and Composio (ComposioHQ/composio, 30k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Composio CLI?

rome-os (a GitHub organization) maintains it in rome-os/rome, which has 725 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 8, 2026.

Source: rome-os/rome on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.