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/resonatehq/resonate-skills/resonate-basic-durable-world-usage-pythonnpx skills add resonatehq/resonate-skills --skill resonate-basic-durable-world-usage-pythongit clone --depth 1 https://github.com/resonatehq/resonate-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/resonatehq/resonate-skills/resonate-basic-durable-world-usage-python)<a href="https://agentmods.dev/skills/resonatehq/resonate-skills/resonate-basic-durable-world-usage-python"><img src="https://agentmods.dev/badge/skills/resonatehq/resonate-skills/resonate-basic-durable-world-usage-python.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.02423 |
| Opus 5 | $0.00032 | $0.01211 |
| Sonnet 5 | $0.00013 | $0.00485 |
| Haiku 4.5 | $0.00006 | $0.00242 |
Grade A, and why
resonate-basic-durable-world-usage-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 6d 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.post(WEBHOOK_URL, json=arg) # runs on every replay How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resonate Basic Durable World Usage — Python
Overview
Durable functions are the payload of Resonate. They are async def coroutines that the SDK treats as a sequence of durable checkpoints. Every await ctx.run(...) or await ctx.rpc(...) is a save point: if the process crashes, the function resumes from the last successful checkpoint on another process or a restart.
This skill covers the Context API (ctx.*) that you use inside those functions. The ephemeral-world counterpart (Resonate class, registration, top-level invocation) lives in resonate-basic-ephemeral-world-usage-python.
The contract
Every durable function:
- Is registered with
r.register(fn)in the ephemeral world. - Takes
ctx(the Context) as its first parameter; any other parameters after that are the invocation args. - Uses
awaitto interact withctx. Each awaitedctx.*call is a durable checkpoint. - Is deterministic when replayed: no direct
time.time(), norandom.random(), no raw network I/O outsidectx.run.
Minimal shape:
from __future__ import annotations
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from resonate.context import Context
async def process_order(ctx: Context, order_id: str) -> dict:
# step 1 — durable: its result is persisted
order = await ctx.run(load_order, order_id)
# step 2 — durable: runs locally in the same worker
charge = await ctx.run(charge_card, order)
# step 3 — ordinary Python control flow; free to branch, loop, raise
if not charge["ok"]:
raise RuntimeError(f"payment failed: {charge['reason']}")
return {"order_id": order_id, "status": "paid"}
If this function crashes after step 1 but before step 2, it resumes at step 2 on restart — load_order is NOT re-run. Its result is read from the promise store.
Same-process invocation: ctx.run
ctx.run invokes another function in the same process durably. The durable function awaits it and the result is checkpointed:
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.
- 6d ago First seen · 275 lines · 64 tokens per session scan A ce6cba649105
resonate-basic-durable-world-usage-python is a skill published in the GitHub repository resonatehq/resonate-skills (6 stars, last pushed 14d ago), licensed Apache-2.0. It adds 64 tokens to every session and 2,423 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
create-workflow-python
This skill creates a Dapr workflow application in Python. Use this skill when the user asks to "create a workflow in Python", "write a Python workflow application" or "build a workflow app in Python".
check-prereq-agent-python
This skill checks prerequisites for building durable AI agents in Python with the Dapr Agents SDK or a Diagrid framework wrapper. Use this skill when the user asks to "check prerequisites for Python agents", "verify Python agent environment", or "check Python agent setup".
check-prereq-python
This skill checks prerequisites for building Dapr Workflow apps in Python. Use this skill when the user asks to "check prerequisites for Python", "verify Python environment", or "check Python setup".
fix-python-test
When a Python test is failing, follow this loop precisely.
fastapi-pro
Production FastAPI patterns — async endpoints, SQLAlchemy 2.0 async, Pydantic V2, dependency injection, JWT auth, testing. Use for Python 3.11+ FastAPI backends. NOT for Django (→ django-patterns) or Node.js (→ backend-patterns).
data-visualization-analyst
Guide data cleanup and chart design into publication-quality visual outputs with clear narrative framing.