Composio is a software toolkit that gives AI agents access to authenticated tools for interacting with apps and services. Developers use its SDKs, command-line interface, sessions, and sandbox to build agents that can carry out actions. The catalogue add-ons support workflows for using Composio with coding agents.
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.
git clone --depth 1 https://github.com/ComposioHQ/composioWrote 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/commands/composiohq/composio/api-update)<a href="https://agentmods.dev/commands/composiohq/composio/api-update"><img src="https://agentmods.dev/badge/commands/composiohq/composio/api-update/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/commands/composiohq/composio/api-update"><img src="https://agentmods.dev/badge/commands/composiohq/composio/api-update.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 | $0.00000 | $0.01152 |
| Opus 5.5 | $0.00000 | $0.00461 |
| Sonnet 5.5 | $0.00000 | $0.00230 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
api-update 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 1mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Update Command
Check for open PRs in the Composio client repositories and create a plan for updating the SDKs.
Workflow
Step 1: Check for Open PRs
Fetch open PRs from both client repositories:
- TypeScript Client:
github.com/composiohq/composio-base-ts - Python Client:
github.com/composiohq/composio-base-py
Use the GitHub CLI (gh) to list open PRs:
gh pr list --repo composiohq/composio-base-ts --state open --json number,title,url,headRefName,body
gh pr list --repo composiohq/composio-base-py --state open --json number,title,url,headRefName,body
Step 2: Get PR Patches
For each open PR, fetch the diff/patch to understand the changes:
gh pr diff <PR_NUMBER> --repo composiohq/composio-base-ts
gh pr diff <PR_NUMBER> --repo composiohq/composio-base-py
Step 3: Analyze Changes
For each PR, analyze the diff to identify:
- New API endpoints - New methods/functions added to the client
- Modified parameters - Changes to existing function signatures
- Deprecated endpoints - Removed or deprecated functionality
- Type changes - Updates to type definitions/schemas
- Breaking changes - Any backward-incompatible changes
Step 4: Identify SDK Impact
Map client changes to SDK files that need updates:
TypeScript SDK (@composio/core):
- Check
ts/packages/core/src/for affected code - Types:
ts/packages/core/src/types/ - Models:
ts/packages/core/src/models/ - Services:
ts/packages/core/src/services/
Important - Naming Convention for TypeScript: The API uses kebab-case (e.g.,
connected-accounts,auth-configs,tool-router) but the TypeScript SDK uses camelCase (e.g.,connectedAccounts,authConfigs,toolRouter).When mapping API changes to TypeScript SDK:
- Convert all kebab-case parameter names to camelCase
- Convert all kebab-case property names to camelCase
- Keep the original kebab-case names in comments for reference to the API
- Example: API's
callback_urlorcallback-urlbecomescallbackUrlin TypeScript
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.
- 1mo ago First seen · 139 lines · 0 tokens per session scan A 205c5e0cb9d0
api-update is a command published in the GitHub repository ComposioHQ/composio (30,595 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,152 tokens. 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.
Other commands, from other repositories
generate-endpoint
Génération Endpoint FastAPI.
type-coverage
Vérification Couverture des Types Python.
generate-command
Génération Commande Symfony.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.
pn-audit-security
OWASP-guided security review — auth posture, input validation, secrets, CORS, JWT, rate limiting. Surgical command for backend security. Use standalone or as part of pn-backend-audit.
catalog-integrations
Wraps agents/integration-catalog-builder/AGENT.md. Named Credentials + Remote Sites + Connected Apps + Auth Providers + Certificates, cross-referenced with Apex/Flow usage, scored for posture.