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.
npx skills add ComposioHQ/composio --skill effect-v4git 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/skills/composiohq/composio/effect-v4)<a href="https://agentmods.dev/skills/composiohq/composio/effect-v4"><img src="https://agentmods.dev/badge/skills/composiohq/composio/effect-v4/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/composiohq/composio/effect-v4"><img src="https://agentmods.dev/badge/skills/composiohq/composio/effect-v4.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 | $0.00157 | $0.01062 |
| Opus 5.5 | $0.00063 | $0.00425 |
| Sonnet 5.5 | $0.00031 | $0.00212 |
| Haiku 4.5 | $0.00016 | $0.00106 |
Grade A, and why
effect-v4 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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Effect v4
The CLI, @composio/cli-keyring, and @composio/json-schema-to-effect-schema run on
Effect v4. Every claim below is grounded in the migrated source, not memory of v3.
Exact version matrix
effect, @effect/platform-bun, and @effect/vitest
are pinned to the same exact 4.0.3 — never ^, @next, or a mismatched
version across packages. @effect/cli and @effect/platform no longer exist as
dependencies; their surfaces are consolidated into effect and effect/*.
See versions.json for the full matrix (also typescript, vitest).
Read next
- references/core-patterns.md — services, layers, typed
errors, Schema, choosing between
Effect.genandEffect.fn,Optioncombinators in place ofisSometernaries, driving time in tests withTestClock(fork, adjust until the fiber settles, join) instead ofit.live, and the v3→v4 rename table (labeled historical, for recognizing stale patterns). - references/cli-surface.md —
effect/cli:Command,Flag,Argument,GlobalFlag,CliConfig, the customCliOutput.Formatter, and the runner's double-print rule. - references/upgrade-workflow.md — procedure for bumping to a newer release.
Code excerpts in those references are short quotes from real, currently-compiling repo files (path cited at each excerpt) — not standalone examples. The compile-checked source of truth is always the cited file itself; when it and a reference disagree, trust the file and fix the reference.
Non-negotiables
Effect.gen(function* () {...})for effect values — the dominant form, including named module consts — and(params) => Effect.gen(...)for parameterized helpers.Effect.fn(...)is the function form whose effects carry stack-frame annotations (its optional name string adds a per-call tracing span), worth it for service members and combinator callbacks that should be attributable in error reports. All forms re-run their body per execution. See "Effect.genvsEffect.fn" in core-patterns.- Define services with
Context.Serviceand an explicitstatic readonly Default/layerlayer built withLayer.succeed/Layer.effect/Layer.provide. V4 does not generate a layer for you. - Model expected failures with
Schema.TaggedError(or a plainData.TaggedErrorwhen no Schema fields are needed) and recover withEffect.catchTag/catchTags/Match, never manual_tagstring comparisons. - Wrap fallible Promises with
Effect.tryPromise({ try, catch });Effect.promiseturns rejection into a defect. Noasync/awaitortry/catchinside Effect workflows — ESLint bans them ints/packages/cli/src. - Treat every remembered v3 package name and API as wrong until verified against
ts/vendor/effect(read-only source oracle — never edit or import from it) and the installed[email protected]typings. Source may be ahead of the published package; the compiler is the compatibility gate.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago Changed · +2 lines 0c40a84a1b6b
- 14d ago Changed · -12 tokens per session 3b0bffa5b66a
- 29d ago Changed 47206adf4a5f
- 1mo ago Changed 6c50d4ca86a7
- 1mo ago First seen · 73 lines · 169 tokens per session scan A 48426caddc3b
effect-v4 is a skill published in the GitHub repository ComposioHQ/composio (30,770 stars, last pushed yesterday), licensed MIT. It adds 157 tokens to every session and 1,062 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
document-code
Apply Google Style documentation standards to Python, Go, TypeScript, and Terraform code. Use when writing or reviewing code that needs docstrings/comments/JSDoc, when asked to "document this code", "add docstrings", "follow Google Style", or when improving code documentation quality. Supports Python docstrings, Go…
pn-python-scaffolding
Scaffolds new Python API projects (FastAPI, Flask, Django) or routes. Use when adding a new route/module; covers project layout, env/secrets, validation, error handling, and idiomatic Python patterns.
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
adk-style
Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or…