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-debugging-pythonnpx skills add resonatehq/resonate-skills --skill resonate-basic-debugging-pythongit clone --depth 1 https://github.com/resonatehq/resonate-skillsWhat 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 | $0.00062 | $0.02388 |
| Opus 5 | $0.00031 | $0.01194 |
| Sonnet 5 | $0.00012 | $0.00478 |
| Haiku 4.5 | $0.00006 | $0.00239 |
Grade A, and why
resonate-basic-debugging-python 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 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.
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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resonate Debug and Troubleshoot — Python
Overview
Use this skill to diagnose Resonate runtime issues in Python. The Python SDK v0.7.0 uses async def + await (not generators); failure modes differ from TypeScript's generator-based v1 API and from the legacy v0.6.x Python SDK. Focus on reproducible symptoms, promise state, registration, and determinism.
For the language-agnostic replay + recovery mental model, read durable-execution first.
Triage flow
- Classify the failure: import/syntax error, runtime SDK error, server error code, workflow stuck/hanging, or unexpected replay behavior.
- Confirm Python is ≥ 3.12 and
resonate-sdk>=0.7.0is installed. - Confirm the Resonate server is reachable:
resonate devstarts it onlocalhost:8001(Rust v0.9.x, single port — no separate store port). - Confirm the worker process is running, connected to the right URL and group, and registered for the right functions.
- Inspect the promise state and call graph for the invocation ID.
- Validate determinism — no
time.time(), norandom.random(), no un-checkpointed side effects in the orchestrator body.
Version + compat pins
- Python ≥ 3.12 — the SDK uses recent typing syntax. 3.11 and below won't import.
resonate-sdk>=0.7.0— async/await rewrite; incompatible with v0.6.x API.- Resonate server v0.9.x (Rust, single port 8001) — run with
resonate devfor local development. resonate-sdkon PyPI (notresonate— the bare name is a different package).
If from resonate.resonate import Resonate fails, you either have the wrong package installed or you're on Python < 3.12.
Async/await pitfalls (Python-specific)
These are the most common Python-only footguns with the v0.7.0 SDK.
Forgot await before a Context call
async def foo(ctx: Context, arg: str) -> str:
ctx.run(bar, arg) # missing await; returns a future the SDK sees but you lose the result
return "done"
The future is tracked by structured concurrency (the runtime will still join it before settling foo), but the result is lost and your orchestrator continues without it. Fix:
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 · 258 lines · 62 tokens per session scan A e1f2480f6b24
resonate-basic-debugging-python is a skill published in the GitHub repository resonatehq/resonate-skills (6 stars, last pushed 10d ago), licensed Apache-2.0. It adds 62 tokens to every session and 2,388 once invoked, about $0.0003 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.
Other skills, from other repositories
tidebase
Give AI agents an identity and a credential vault (broker API calls so the agent and model never see the secret), plus checkpoint/resume, durable queues and cron schedules, cancellation, human approval gates, live progress state, subagent fanout, and per-run cost tracking, using Tidebase (open-source…
kitaru-release
Discover dependencies and prepare or execute Kitaru core and plugin releases, including version proposals, Kitaru UI selection, release PRs, ordered tag commands, artifact verification, and recovery. Use when a user asks what a release depends on or wants to prepare, cut, publish, verify, or recover a Kitaru, Kitaru…
economic-reasoning
Economic decision-making for agents in EconomySpace. Activate when the agent observes currency, prices, income, tax, or trading opportunities to make informed financial decisions.
care.basic
Offer basic care check-ins for neighbors.
messaging.group
Send a concise practical group update.
safety.respond
Respond to urgent or risky events with safety movement, announcement, and memory.