sablier-withdraw-open-ended-stream

sablier-withdraw-open-ended-stream is a skill for Claude Code from sablier-labs/sablier-skills. It costs 117 tokens per session (2,091 once invoked), scanned A, original, MIT.

A skill for withdrawing available tokens from Sablier Flow open-ended payment streams. Sablier Flow is a system for sending payments continuously over time, and the withdrawal can cover one or more streams.

In plain words
What is it for?
Discovering your Sablier Flow streams, selecting streams to withdraw from, and sending batched withdrawals on a selected blockchain network.
Why use it?
It finds eligible streams and prepares the withdrawals, reducing the need to inspect each stream and submit transactions one by one.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Discovering your Sablier Flow streams, selecting streams to withdraw from, and sending batched withdrawals on a selected blockchain network.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sablier-labs/sablier-skills/sablier-withdraw-open-ended-stream
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.

Any agent
npx skills add sablier-labs/sablier-skills --skill sablier-withdraw-open-ended-stream
Clone the repo
git clone --depth 1 https://github.com/sablier-labs/sablier-skills

Made for: Claude Code.

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 sablier-withdraw-open-ended-stream

README.md
[![agentmods](https://agentmods.dev/badge/skills/sablier-labs/sablier-skills/sablier-withdraw-open-ended-stream/github.svg)](https://agentmods.dev/skills/sablier-labs/sablier-skills/sablier-withdraw-open-ended-stream)
Your own site
<a href="https://agentmods.dev/skills/sablier-labs/sablier-skills/sablier-withdraw-open-ended-stream"><img src="https://agentmods.dev/badge/skills/sablier-labs/sablier-skills/sablier-withdraw-open-ended-stream/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.

agentmods 80×15 button for sablier-withdraw-open-ended-stream

Your own site · 80×15
<a href="https://agentmods.dev/skills/sablier-labs/sablier-skills/sablier-withdraw-open-ended-stream"><img src="https://agentmods.dev/badge/skills/sablier-labs/sablier-skills/sablier-withdraw-open-ended-stream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00117 $0.02091
Opus 5 $0.00059 $0.01045
Sonnet 5 $0.00023 $0.00418
Haiku 4.5 $0.00012 $0.00209

Measured 12d ago against content hash 0c397586893f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sablier-withdraw-open-ended-stream 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/filter-withdrawable.sh, scripts/max-min-fee.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/sablier-withdraw-open-ended-stream/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sablier Flow Stream Withdrawal

Overview

Withdraw available tokens from one or more Sablier Flow open-ended payment streams on the user's behalf. The skill discovers the user's streams through the Sablier indexer, lets the user pick any subset (default: all eligible), and executes one batch(bytes[]) transaction per SablierFlow contract on the selected chain.

Sablier Flow exposes two per-stream withdraw entrypoints (flow/src/interfaces/ISablierFlow.sol:497-531):

  • withdraw(uint256 streamId, address to, uint128 amount) — explicit-amount withdrawal.
  • withdrawMax(uint256 streamId, address to) returns (uint128) — drains the full currently-withdrawable balance.

Batching is provided by the inherited Batch.batch(bytes[]) payable (SablierFlow.sol:13,39; @sablier/evm-utils/src/Batch.sol). batch delegatecalls every entry against address(this), so msg.sender and msg.value are reused across all sub-calls. Each sub-call can target a different stream, amount, and to address. The batch is all-or-nothing: any sub-call revert bubbles up and reverts the whole transaction. There is no per-stream skip event analogous to Lockup's InvalidWithdrawalInWithdrawMultiple.

This skill charges no markup. The only fee paid is the on-chain protocol fee (calculateMinFeeWei) set by the comptroller; it may be 0. Because batch delegatecalls and reuses msg.value, the required msg.value is max(calculateMinFeeWei across the batch), not the sum.

This skill is a coordinator for Flow withdrawal and execution routing.

Arguments

Argument Description
chain_name EVM chain where the streams live (e.g. "Ethereum", "Base", "Polygon"). One chain per invocation.
wallet_address The user's wallet. Must be the streams' recipient (NFT owner) or an approved third party — the skill never surfaces sender-only streams, since the non-recipient path is restricted to to == recipient.
token_symbol Token symbol to narrow the search (e.g. "USDC", "SABL"). If omitted, every token the wallet has an active stream in is shown.

Read the full file on GitHub · 97 lines

Files

What ships with it

3 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.

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. 12d ago First seen · 97 lines · 117 tokens per session scan A 0c397586893f

Subscribe to this mod's changes

sablier-withdraw-open-ended-stream is a skill published in the GitHub repository sablier-labs/sablier-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 2,091 once invoked, about $0.0006 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.