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 agentmods add skills/cohen-liel/hivemind/async-pythonnpx skills add cohen-liel/hivemind --skill async-pythongit clone --depth 1 https://github.com/cohen-liel/hivemindWhat 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 | $0.00037 | $0.00919 |
| Opus 5 | $0.00018 | $0.00460 |
| Sonnet 5 | $0.00007 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
async-python scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
requests.get(url) # Blocking HTTP call How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Async Python Patterns
Core Concepts
import asyncio
# Basic async function
async def fetch_user(user_id: int) -> User:
async with aiohttp.ClientSession() as session:
async with session.get(f"/users/{user_id}") as resp:
return await resp.json()
# Run from sync context
user = asyncio.run(fetch_user(123))
Concurrency Patterns
Run tasks in parallel (gather)
# All run at the same time — total time = slowest task
users, posts, comments = await asyncio.gather(
fetch_user(user_id),
fetch_posts(user_id),
fetch_comments(user_id),
)
# With error handling — return exceptions instead of raising
results = await asyncio.gather(
fetch_user(user_id),
fetch_posts(user_id),
return_exceptions=True,
)
for result in results:
if isinstance(result, Exception):
logger.error(f"Task failed: {result}")
Limit concurrency (Semaphore)
# Process 100 items but max 10 at a time
sem = asyncio.Semaphore(10)
async def process_with_limit(item):
async with sem:
return await process(item)
results = await asyncio.gather(*[process_with_limit(i) for i in items])
Timeout
try:
result = await asyncio.wait_for(fetch_data(), timeout=10.0)
except asyncio.TimeoutError:
logger.warning("Fetch timed out after 10s")
result = None
Background tasks (fire and forget)
async def main():
# Don't await — runs in background
task = asyncio.create_task(send_notification(user_id))
# But keep reference so GC doesn't kill it
background_tasks = set()
background_tasks.add(task)
task.add_done_callback(background_tasks.discard)
Async context manager
class DatabasePool:
async def __aenter__(self):
self.pool = await asyncpg.create_pool(dsn)
return self
async def __aexit__(self, *args):
await self.pool.close()
async with DatabasePool() as db:
await db.pool.fetchrow("SELECT * FROM users WHERE id = $1", 1)
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.
- 2d ago First seen · 145 lines · 37 tokens per session scan A 5fff368cae71
async-python is a skill published in the GitHub repository cohen-liel/hivemind (108 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 919 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dagr-producer
Emit and maintain a dagr run file — a live, contract-valid JSON description of recursive projects, tasks, attempts, gates, evidence, policies, events, and operator-message resolutions that dagr view renders as a DAG. Use when orchestrating agents or tracking multi-step work that a dagr pane should display.
autonomous-dev-team
Multi-agent team execution with DAG task scheduling, specialized roles, and consensus synthesis.
loop-engineering
Use when a repeatable task must become a bounded Trigger -> Execute -> Verify -> State loop, scheduled automation, goal agent, or metric-driven research cycle.
agent-teams-command
Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require bounded multi-agent command.
agentic-engineering
Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.
harness-engineering
Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.