octoperf-async-polling

octoperf-async-polling is a skill for Claude Code from OctoPerf/octoperf-claude-plugins. It costs 115 tokens per session (2,307 once invoked), scanned A, original, Apache-2.0.

A guide for waiting on OctoPerf operations that run in the background, such as tests, report exports, and correlation tasks. These operations return an identifier first, and the final result becomes available later.

In plain words
What is it for?
Use it to poll OctoPerf task and test status until an asynchronous operation reaches a final state.
Why use it?
It prevents checking too often, missing early failures, or treating an unfinished operation as complete.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the octoperf plugin — 20 skills, 1 MCP server shipped together

Good fit Use it to poll OctoPerf task and test status until an asynchronous operation reaches a final state.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/octoperf/octoperf-claude-plugins/octoperf-async-polling
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 OctoPerf/octoperf-claude-plugins --skill octoperf-async-polling
Clone the repo
git clone --depth 1 https://github.com/OctoPerf/octoperf-claude-plugins

Made for: Claude Code.

Or install octoperf, the plugin that ships this one along with the rest of its 20 skills, 1 MCP server.

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 octoperf-async-polling

README.md
[![agentmods](https://agentmods.dev/badge/skills/octoperf/octoperf-claude-plugins/octoperf-async-polling/github.svg)](https://agentmods.dev/skills/octoperf/octoperf-claude-plugins/octoperf-async-polling)
Your own site
<a href="https://agentmods.dev/skills/octoperf/octoperf-claude-plugins/octoperf-async-polling"><img src="https://agentmods.dev/badge/skills/octoperf/octoperf-claude-plugins/octoperf-async-polling/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 octoperf-async-polling

Your own site · 80×15
<a href="https://agentmods.dev/skills/octoperf/octoperf-claude-plugins/octoperf-async-polling"><img src="https://agentmods.dev/badge/skills/octoperf/octoperf-claude-plugins/octoperf-async-polling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,307 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 $0.00115 $0.02307
Opus 5 $0.00057 $0.01154
Sonnet 5 $0.00023 $0.00461
Haiku 4.5 $0.00012 $0.00231

Measured 11d ago against content hash e3f7d45cd320, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

octoperf-async-polling 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 11d 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.

plugins/octoperf/skills/octoperf-async-polling/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OctoPerf — Polling async operations reliably

Several OctoPerf MCP tools kick off work that runs for seconds to hours and return immediately with a handle (benchResultId, taskId, …). The actual result lives behind a second "get-status" tool that you poll until terminal. This skill is the single source of truth for how to do that polling without burning the context window or missing an early failure.

When this applies

You started one of:

Starter tool Returns Status tool to poll
validate_virtual_user benchResultId get_virtual_user_validation (or get_bench_result)
run_scenario benchReportId + benchResultIds[] get_bench_result (state) and/or get_bench_status (%)
export_bench_report_pdf taskId get_task_result
update_report_data one taskId per run to update get_task_result
Async correlation task (auto-correlate workflow) taskId get_task_result

If your call returned the final answer (no taskId / no benchResultId), you're not in async territory — skip this skill.

The pacing rule

Pace the polls. Each MCP roundtrip takes 100–500 ms of context. Calling the status tool in tight succession over a 10-min test would consume 100+ tool turns with identical responses. Put a delay of N between polls — the how depends on your harness (see "How to insert the delay" below).

Pick N from the expected duration of the work:

Read the full file on GitHub · 182 lines

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. 11d ago First seen · 182 lines · 115 tokens per session scan A e3f7d45cd320

Subscribe to this mod's changes

octoperf-async-polling is a skill published in the GitHub repository OctoPerf/octoperf-claude-plugins (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 115 tokens to every session and 2,307 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.