Run N tasks under a concurrency cap K via a sliding-window worker pool.

Apache-2.0Auto-check passedAgent Workflows

Install Pool

skills CLI
$ npx skills add opensage-agent/opensage-adk --skill pool -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install opensage-agent/opensage-adk pool --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/opensage-agent/opensage-adk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/opensage/bash_tools/workflow/pool .claude/skills/pool && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pool
GitHub stars
127
Token cost
~462 tokens
SKILL.md length
132 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run N tasks under a concurrency cap K via a sliding-window worker pool.

  • Many subagent invocations would otherwise hit provider rate limits
  • SKILL.md covers Usage, Common Use Cases and Requires Sandbox
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Rate limiting

What it does

Pool is an agent skill from opensage-agent/opensage-adk. Run N tasks under a concurrency cap K via a sliding-window worker pool. Use when many subagent invocations would otherwise hit provider rate limits.

Its SKILL.md is about 460 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Rate limiting and Subagents. The licence is Apache-2.0.

When your agent uses it

  • Many subagent invocations would otherwise hit provider rate limits
  • Tasks that involve Rate limiting
  • Tasks that involve Subagents

Example prompts

  • “/pool”

What it can do on your machine

Read from SKILL.md and the folder at commit 54d6470. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pool loads about 462 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 132 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~462

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from opensage-agent/opensage-adk at commit 54d6470, republished under its Apache-2.0 licence (© opensage-agent). 132 words, ~462 tokens.

Download SKILL.mdSave it as .claude/skills/pool/SKILL.md (or your agent's skills folder).
name
pool
description
Run N tasks under a concurrency cap K via a sliding-window worker pool. Use when many subagent invocations would otherwise hit provider rate limits.

Pool Pattern

Many tasks (say 20) to run via subagents, but provider RPM/TPM (or memory) caps how many can run at once (say 6). Maintain a sliding window of K active subagents.

Usage

tasks = [task_1, task_2, ..., task_N]
K = 6                          # concurrency cap
active = {}                    # sid -> task_id
done = {}                      # task_id -> final result text

while tasks or active:
    # Fill the pool up to K
    while tasks and len(active) < K:
        t = tasks.pop(0)
        r = call_subagent(agent_name="worker", request=t.prompt, mode="async")
        active[r.session_id] = t.id

    # Short-poll for any one to finish, then drain
    for sid in list(active.keys()):
        r = wait_for_subagent(sid, timeout=1.0)
        if r.success and r.state in ("sleeping", "unloaded"):
            done[active[sid]] = read_inbox_for(sid)
            del active[sid]
            break  # restart fill loop

Key points:

  • No first-completed multi-wait primitive yet. wait_for_subagent with a small timeout polls; loop until one finishes.
  • K depends on the provider. Hosted Anthropic / OpenAI vs local LiteLLM proxy → very different limits. Start with 4-6.
  • Order of completion is unpredictable. Don't assume done-order matches submission order.
  • Failed tasks free their slot like any other completion. Retry failed ones in a separate pass, or feed them into the multi-model pattern.

Common Use Cases

  • Batch evaluation: N CTF / SWE-bench tasks on one orchestrator
  • Bulk code review on many files
  • Fan-out exploration when each branch is independent

Requires Sandbox

None — pure orchestration.

© opensage-agent, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in src/opensage/bash_tools/workflow/pool of opensage-agent/opensage-adk.

Open the folder on GitHubat commit 54d6470

Compare with similar skills

Pool next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pool compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pool this skillopensage-agent/opensage-adk127—~462Automated safety check: PassApache-2.0
Claude Statusbarleeguooooo/claude-code-usage-bar377—~2.5kAutomated safety check: PassMIT
Akb Ingestdnotitia/akb161—~2kAutomated safety check: PassCustom licence
Agentsbutterbase-ai/butterbase-skills5341 repos~1.8kAutomated safety check: PassMIT
API Error Reporthoangsonww/Claude-Code-Agent-Monitor1k—~750Automated safety check: PassMIT
Lmstudio Subagentssundial-org/awesome-openclaw-skills663—~1.2kAutomated safety check: PassMIT

Similar skills

  • Claude Statusbar

    leeguooooo/claude-code-usage-bar

    Manage cs (claude-statusbar) — switch theme/style/density, override severity colors, preview combinations, run doctor, reset config, install, upgrade (cs upgrade — the only supported upgrade path)…

    377 GitHub stars~2.5k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Akb Ingest

    dnotitia/akb

    Ingest whatever you point at into an AKB vault — a local file, a web URL, a GitHub PR/release/commit, a Confluence page, or a Jira issue.

    161 GitHub stars~2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Agents

    butterbase-ai/butterbase-skills

    A skill your agent uses when designing, deploying, or debugging a Butterbase Agent (declarative LLM/tool graph), registering an MCP server for tool use, or wiring access controls and rate limits.

    534 GitHub starsUsed in 1 repo~1.8k tokens
    Agent WorkflowsAuto-check passed
  • API Error Report

    hoangsonww/Claude-Code-Agent-Monitor

    Produce a detailed report on APIError events from Agent Monitor data — counts over time, which sessions and models are affected, and the likely root cause (rate limits, overload/529, or…

    1k GitHub stars~750 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Lmstudio Subagents

    sundial-org/awesome-openclaw-skills

    Reduces token usage from paid providers by offloading work to local LM Studio models.

    663 GitHub stars~1.2k tokensUpdated 7 mo ago
    Agent WorkflowsAuto-check passed
  • Inngest Agents

    Asymmetric-al/core

    A skill your agent uses when building durable AI agents or agentic workflows with Inngest and AgentKit, including model calls, tool calls, multi-agent networks, human approval, realtime progress…

    382 GitHub stars~2.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from opensage-agent/opensage-adk

All 21 skills in this repo
  • Run Fuzzing Campaign

    opensage-agent/opensage-adk

    Run a fuzzing campaign using AFL++ with optional seeds; supports --custommutatorpath (you can write your own custom mutator and use this to execute).

    127 GitHub stars~542 tokensUpdated 2 mo ago
    Auto-check passed
  • Create New Tool

    opensage-agent/opensage-adk

    Scaffold a new bashtools Skill under bashtools/newtools/. An agent skill from opensage-agent/opensage-adk.

    127 GitHub stars~302 tokensUpdated 2 mo ago
    Auto-check passed
  • Extract Crashes

    opensage-agent/opensage-adk

    Extract crash inputs from fuzzing output into a target directory.

    127 GitHub stars~215 tokensUpdated 2 mo ago
    Auto-check passed
  • Get Call Paths

    opensage-agent/opensage-adk

    Get a path in the call graph from a source function to a specified destination function in the codebase.

    127 GitHub stars~272 tokensUpdated 2 mo ago
    Auto-check passed
  • Get Callee

    opensage-agent/opensage-adk

    Tool to get the callee of a function in the codebase by function name and file path.

    127 GitHub stars~223 tokensUpdated 2 mo ago
    Auto-check passed
  • Get Caller

    opensage-agent/opensage-adk

    Tool to get the caller of a function in the codebase. An agent skill from opensage-agent/opensage-adk.

    127 GitHub stars~208 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Pool

What does Pool do?

Run N tasks under a concurrency cap K via a sliding-window worker pool. Pool is an agent skill from opensage-agent/opensage-adk. Run N tasks under a concurrency cap K via a sliding-window worker pool.

When should I use Pool?

Pool fits situations like: many subagent invocations would otherwise hit provider rate limits; tasks that involve Rate limiting; tasks that involve Subagents.

How do I install Pool in Claude Code?

Run `npx skills add opensage-agent/opensage-adk --skill pool -a claude-code`. Or copy the skill folder (src/opensage/bash_tools/workflow/pool in opensage-agent/opensage-adk) into .claude/skills/pool in your project. Claude Code loads it when a task matches its description.

How do I install Pool in Codex?

Run `npx skills add opensage-agent/opensage-adk --skill pool -a codex`. Or copy the skill folder (src/opensage/bash_tools/workflow/pool in opensage-agent/opensage-adk) into .agents/skills/pool in your project. Codex loads it when a task matches its description.

Can I use Pool in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add opensage-agent/opensage-adk --skill pool -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pool, .gemini/skills/pool, .github/skills/pool and .opencode/skills/pool in your project.

What does Pool need to run?

SKILL.md names no scripts, command-line tools or credentials: Pool is instructions for the agent only.

Does Pool access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pool safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pool use?

Pool is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pool use?

About 462 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pool?

Skills that share tags, products or a category with Pool: Claude Statusbar (leeguooooo/claude-code-usage-bar, 377 stars), Akb Ingest (dnotitia/akb, 161 stars), Agents (butterbase-ai/butterbase-skills, 534 stars) and API Error Report (hoangsonww/Claude-Code-Agent-Monitor, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pool?

opensage-agent (a GitHub organization) maintains it in opensage-agent/opensage-adk, which has 127 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on August 4, 2026.

Source: opensage-agent/opensage-adk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.