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 sablier-labs/sablier-skills --skill sablier-cancel-open-ended-streamgit clone --depth 1 https://github.com/sablier-labs/sablier-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/sablier-labs/sablier-skills/sablier-cancel-open-ended-stream)<a href="https://agentmods.dev/skills/sablier-labs/sablier-skills/sablier-cancel-open-ended-stream"><img src="https://agentmods.dev/badge/skills/sablier-labs/sablier-skills/sablier-cancel-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.
<a href="https://agentmods.dev/skills/sablier-labs/sablier-skills/sablier-cancel-open-ended-stream"><img src="https://agentmods.dev/badge/skills/sablier-labs/sablier-skills/sablier-cancel-open-ended-stream.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 | $0.00110 | $0.02100 |
| Opus 5.5 | $0.00044 | $0.00840 |
| Sonnet 5.5 | $0.00022 | $0.00420 |
| Haiku 4.5 | $0.00011 | $0.00210 |
Grade A, and why
sablier-cancel-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 2mo 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sablier Flow Stream Cancellation
Overview
Cancel 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 where the wallet is sender or recipient, drops already-voided streams, and executes one batch(bytes[]) transaction per selected stream that splices the appropriate sub-calls atomically:
- Sender (or sender + recipient) with
refundable > 0→[refundMax(streamId, sender), void(streamId)]. The sender recovers the unstreamed deposit and the stream is permanently stopped in the same transaction. - Sender (or sender + recipient) with
refundable == 0→[void(streamId)]. Inform the user nothing is left to refund — the stream will be voided but no funds will be returned. - Recipient-only →
[void(streamId)]. Inform the user that as the recipient, they can void the stream but only the sender can refund unstreamed funds.
The skill always uses batch(bytes[]) as the entrypoint so refund + void run atomically per stream. When the batch contains a single sub-call (void only), the runbook MAY call void(uint256) directly instead of wrapping in batch — this is a small gas optimization, flagged in the runbook.
This skill charges no markup. Both void(uint256) and refund(streamId,…) are free at the protocol level — MSG_VALUE = 0 always.
This skill is a coordinator for Flow cancellation 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. May be the stream's sender (refund + void), the recipient (void only), or both. The skill surfaces every non-voided stream where wallet ∈ {sender, 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. |
What ships with it
2 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.
- 2mo ago First seen · 107 lines · 110 tokens per session scan A f8d1751548dd
sablier-cancel-open-ended-stream is a skill published in the GitHub repository sablier-labs/sablier-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 2,100 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
agentic-street
Earn yield on USDC by investing in AI-managed DeFi funds, or launch your own fund and build a public track record on Base. Browse funds, deposit USDC, check fund performance, monitor proposals, veto suspicious trades, withdraw returns, create investment fund, propose DeFi trades via adapters or raw calls, earn…
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
bridge
Cross-chain token transfers using Wormhole and CCTP.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
marginfi
MarginFi — Solana lending and borrowing.