manus

manus is a skill for Claude Code, Codex from aigorahub/elves. It costs 30 tokens per session (247 once invoked), scanned A, original, MIT.

A command for launching private, limited research through Manus, a research service, with optional coordination by Cobbler. It can also distribute a fixed list of research items across separate tasks.

In plain words
What is it for?
Use it when the user types /manus, including requests for wide research or research over a supplied list of items.
Why use it?
It provides a controlled way to gather research while preserving privacy, tracking coverage, and retrying known failures without creating duplicate work.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/aigorahub/elves/manus
Any agent
npx skills add aigorahub/elves --skill manus
Clone the repo
git clone --depth 1 https://github.com/aigorahub/elves

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for manus

README.md
[![agentmods](https://agentmods.dev/badge/skills/aigorahub/elves/manus.svg)](https://agentmods.dev/skills/aigorahub/elves/manus)
Your own site
<a href="https://agentmods.dev/skills/aigorahub/elves/manus"><img src="https://agentmods.dev/badge/skills/aigorahub/elves/manus.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 247 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.00247
Opus 5 $0.00015 $0.00123
Sonnet 5 $0.00006 $0.00049
Haiku 4.5 $0.00003 $0.00025

Measured 5d ago against content hash df99192f2d3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

manus 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 5d 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.

aliases/claude/manus/SKILL.md · 22 lines

What it actually says

Manus Research

This is the Elves-managed Claude Code alias for /manus <topic> and the roster forms /manus --wide|--fanout --items-file <roster.json> ….

Load the installed elves skill's Provider shortcut protocols and references/provider-shortcuts.md. Resolve scripts/run_manus.sh from the active Elves skill root, keep the target repository as the working directory, validate the arguments and MANUS_API_KEY, and run it. Preserve private visibility, bounded waits, structured coverage, ignored manifests, and duplicate-safe --resume behavior that retries only archived, known-failed steps instead of improvising API calls. In --wide mode Cobbler is the outer orchestrator: it accepts native Wide Research only after exact roster reconciliation, repairs missing/duplicated items with deterministic fan-out, and synthesizes last.

Changes

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.

  1. 5d ago First seen · 22 lines · 30 tokens per session scan A df99192f2d3c

Subscribe to this mod's changes

manus is a skill published in the GitHub repository aigorahub/elves (213 stars, last pushed 8d ago), licensed MIT. It adds 30 tokens to every session and 247 once invoked, about $0.0002 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 2026-08-30.