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/vstorm-co/full-stack-ai-agent-template/background-tasknpx skills add vstorm-co/full-stack-ai-agent-template --skill background-taskgit clone --depth 1 https://github.com/vstorm-co/full-stack-ai-agent-templateWrote 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/vstorm-co/full-stack-ai-agent-template/background-task)<a href="https://agentmods.dev/skills/vstorm-co/full-stack-ai-agent-template/background-task"><img src="https://agentmods.dev/badge/skills/vstorm-co/full-stack-ai-agent-template/background-task.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 | $0.00062 | $0.00955 |
| Opus 5 | $0.00031 | $0.00477 |
| Sonnet 5 | $0.00012 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
background-task 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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Background Tasks ({{ cookiecutter.background_tasks }})
Tasks live in backend/app/worker/tasks/ (e.g. email_tasks.py, rag_tasks.py, cleanup_tasks.py). The app uses {{ cookiecutter.background_tasks }}. An in-process fallback (worker/background/) exists for trivial cases.
When to use a task vs. inline
- Task: anything slow, retryable, or fire-and-forget — sending email, ingesting/embedding documents, calling slow external APIs, periodic cleanups, materialized-view refreshes.
- Inline: fast, transactional work that the response depends on.
Add a task
-
Define it in
backend/app/worker/tasks/<area>.py: {%- if cookiecutter.use_celery %}from app.worker.celery_app import celery_app @celery_app.task(name="send_welcome_email") def send_welcome_email(user_id: str) -> dict: ...Enqueue:
send_welcome_email.delay(user_id)(or.apply_async(args=[...], countdown=60)). {%- elif cookiecutter.use_taskiq %}from app.worker.taskiq_app import broker @broker.task async def send_welcome_email(user_id: str) -> dict: ...Enqueue:
await send_welcome_email.kiq(user_id). {%- elif cookiecutter.use_arq %}# add the coroutine, then list it in arq_app.WorkerSettings.functions async def send_welcome_email(ctx, user_id: str) -> dict: ...Enqueue:
await request.state.arq_pool.enqueue_job("send_welcome_email", user_id). {%- elif cookiecutter.use_prefect %}from prefect import flow @flow(name="send-welcome-email", log_prints=True) async def send_welcome_email_flow(user_id: str) -> dict: ...Fire-and-forget from a service:
asyncio.create_task(send_welcome_email_flow(user_id)). {%- endif %} -
Call it from a service (not from the route directly) — keep business logic in
services/, enqueue at the end of the unit of work. -
Schedule it (optional): {%- if cookiecutter.use_celery %} add to
beat_scheduleincelery_app.py(runmake celery-beat). {%- elif cookiecutter.use_taskiq %} append toSCHEDULESintasks/schedules.py(runmake taskiq-scheduler). {%- elif cookiecutter.use_arq %} add acron(...)entry toWorkerSettings.cron_jobsinarq_app.py. {%- elif cookiecutter.use_prefect %} register a deployment with aCronSchedule/IntervalScheduleinapp/worker/prefect_app.py. {%- endif %}
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.
- 4d ago First seen · 80 lines · 62 tokens per session scan A aba527143c88
background-task is a skill published in the GitHub repository vstorm-co/full-stack-ai-agent-template (1,862 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 955 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 2026-08-30.
Other skills, from other repositories
image-gen
在 Agent 沙盒中生成图片并保存到 outputs。当用户要求生成图片、海报、插画、文生图,或指定 Qwen-Image、其它兼容图片生成接口时使用此技能。.
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
playwright-testing
Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions…
content-refresher
Refresh outdated posts with current stats, new sections, freshness signals to restore rankings. 内容更新/排名恢复.
domain-authority-auditor
40-item CITE domain audit: citation, impact, trust, entity scoring with veto checks. 域名权威/网站可信度.
memory-management
Persist SEO/GEO campaign context across Claude sessions with automatic hot-list, active work, and archive tiers. 项目记忆/跨会话.