celery-knowledge

celery-knowledge is a skill for Claude Code, Cursor from redhat-community-ai-tools/UnifAI. It costs 38 tokens per session (1,080 once invoked), scanned A, original, Apache-2.0.

Domain guidance for a Celery worker service, which runs background jobs asynchronously so an application can continue responding while heavy work is processed.

In plain words
What is it for?
It helps maintain the RAG pipeline’s document ingestion, Slack channel ingestion, and real-time Slack event tasks across separate queues.
Why use it?
It keeps document and Slack processing out of the main API and supports retries, failure recovery, and additional worker instances.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: paths in frontmatter, but also installed under .cursor/.

Good fit It helps maintain the RAG pipeline’s document ingestion, Slack channel ingestion, and real-time Slack event tasks across separate queues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhat-community-ai-tools/unifai/celery
Install

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.

Any agent
npx skills add redhat-community-ai-tools/UnifAI --skill celery
Clone the repo
git clone --depth 1 https://github.com/redhat-community-ai-tools/UnifAI

Made for: Claude Code, Cursor.

Wrote 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.

agentmods badge for celery-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/celery/github.svg)](https://agentmods.dev/skills/redhat-community-ai-tools/unifai/celery)
Your own site
<a href="https://agentmods.dev/skills/redhat-community-ai-tools/unifai/celery"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/celery/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for celery-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhat-community-ai-tools/unifai/celery"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/unifai/celery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,080 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01080
Opus 5 $0.00019 $0.00540
Sonnet 5 $0.00008 $0.00216
Haiku 4.5 $0.00004 $0.00108

Measured 10d ago against content hash c72548383d0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

celery-knowledge 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 10d 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.

.cursor/skills/codebase/domains/celery/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Celery Worker Knowledge System

Async task execution service for the RAG pipeline. Shares the rag/ codebase — Celery tasks are thin wrappers that call RAG core services.

For domain logic, load the RAG domain skill (../rag/SKILL.md).

Role

  • Executes document processing pipeline stages asynchronously
  • Scales horizontally via additional worker instances
  • Handles task retry and failure recovery
  • Keeps the RAG API responsive by offloading heavy work

Entry Point

rag/entrypoint.sh with ROLE=celery runs:

celery -A infrastructure.celery.app worker -Q $CELERY_QUEUES

Three Queues

Queue Purpose Tasks
document_queue Document ingestion pipelines execute_pipeline_task
slack_queue Slack channel ingestion pipelines execute_pipeline_task
slack_events_queue Real-time Slack event processing process_slack_events_task (3 retries)

Key Files

File Role
rag/infrastructure/celery/app.py Celery app configuration
rag/infrastructure/celery/workers/pipeline_tasks.py execute_pipeline_task entry point
rag/infrastructure/celery/workers/slack_event_tasks.py process_slack_events_task entry point
rag/infrastructure/celery/pipeline_dispatcher.py Routes tasks to queues
global_utils/celery_app/init.py CeleryApp singleton factory

Task Execution Flow

CeleryPipelineDispatcher.dispatch(source_type, source_data)
    → derive queue from source_type (e.g. "document" → document_queue)
    → send_task() → RabbitMQ → Celery Worker picks up task
        → execute_pipeline_task()
            → resolve dependencies from app container
            → select handler (DocumentPipelineHandler / SlackPipelineHandler)
            → PipelineExecutor.execute(handler, source)
                → collect → process → chunk → embed → store

Worker Pool Configuration

  • threads pool when using remote Docling/embedding (I/O-bound)
  • solo pool for local processing (CPU-bound)
  • Controlled by config flags: use_remote_docling, use_remote_embedding

Read the full file on GitHub · 133 lines

Changes

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.

  1. 10d ago First seen · 133 lines · 38 tokens per session scan A c72548383d0f

Subscribe to this mod's changes

celery-knowledge is a skill published in the GitHub repository redhat-community-ai-tools/UnifAI (44 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 1,080 once invoked, about $0.0002 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.