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.
npx skills add lunchpaillola/pipa-skills --skill composiogit clone --depth 1 https://github.com/lunchpaillola/pipa-skillsWrote 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.
[](https://agentmods.dev/skills/lunchpaillola/pipa-skills/composio)<a href="https://agentmods.dev/skills/lunchpaillola/pipa-skills/composio"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/composio/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.
<a href="https://agentmods.dev/skills/lunchpaillola/pipa-skills/composio"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/composio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00024 | $0.00928 |
| Opus 5 | $0.00012 | $0.00464 |
| Sonnet 5 | $0.00005 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
composio-mcp 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Apply
- User asks Pipa to interact with an external app such as Gmail, Slack, GitHub, Notion, Linear, Google Calendar, or similar.
- User wants Pipa to send, create, update, fetch, summarize, or monitor records in a connected service.
- User asks for a connected-app action and Composio MCP tools are available in the current agent runtime.
- User explicitly mentions Composio, Composio MCP, connected accounts, external app tools, or Pipa connected workflows.
Core Rule
Use the Composio MCP tools exposed in the current runtime. Do not switch to any non-MCP Composio workflow, install Composio locally, or initialize projects.
If Composio MCP tools are not available, stop and ask the user to connect or enable the Composio MCP for this agent environment.
Exception: when a Pipa read-only assessment has other usable evidence, record unavailable MCP or account access as a source gap and continue. Do not initiate authorization unless the user asks to connect it.
Workflow
- Clarify the target app, action, and user-visible outcome if the request is ambiguous.
- Inspect the available Composio MCP tools before choosing an action.
- Prefer the smallest specific MCP tool that can complete the request.
- Check whether the required connected account or authorization is available.
- If authorization is missing, ask the user to complete the MCP-provided connection flow and wait for confirmation.
- Execute the action through the MCP tool with explicit parameters.
- Report concise provenance: app, action, tool used, and the relevant record ID, URL, title, or timestamp returned by the tool.
MCP Tool Pattern
The Composio MCP is self-describing. Use its metadata tools instead of relying on local reference files.
- Search first with the MCP tool-discovery operation for the user's use case.
- Review the returned tool schemas, connection status, recommended plan, and pitfalls.
- If a toolkit has no active connection, use the MCP connection-management operation and give the user the returned authorization link.
- If a tool result points to a schema reference, fetch the complete schema before execution.
- Execute only returned tool slugs with schema-compliant arguments.
- For independent actions, use the MCP batch-execution operation when available.
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.
- 11d ago First seen · 87 lines · 24 tokens per session scan A 95c650543fba
composio-mcp is a skill published in the GitHub repository lunchpaillola/pipa-skills (3 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 928 once invoked, about $0.0001 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.
Other skills, from other repositories
composio
Build AI agents and apps with Composio - access 200+ external tools with Tool Router or direct execution.
composio
Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK.
composio
Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK.
composio
Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK.
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
CSOC Operations & Playbook Automation
SOC alert triage, incident playbook automation, escalation workflows, shift reporting, and SOC KPI tracking.