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/nevaberry/nevaberry-plugins/celery-knowledge-patchnpx skills add Nevaberry/nevaberry-plugins --skill celery-knowledge-patchgit clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsWhat 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 | $0.00009 | $0.01375 |
| Opus 5 | $0.00005 | $0.00687 |
| Sonnet 5 | $0.00002 | $0.00275 |
| Haiku 4.5 | $0.00001 | $0.00137 |
Grade A, and why
celery-knowledge-patch 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Celery Knowledge Patch
Load this skill when maintaining Celery applications, workers, brokers, result backends, schedules, or task workflows. Start with the quick reference, then open the topic file that matches the work at hand.
Reference index
| Reference | Topics |
|---|---|
| runtime-and-lifecycle.md | Runtime and dependency requirements, support policy, worker shutdown, signals, pools, and testing |
| brokers-and-queues.md | RabbitMQ quorum queues, Redis, SQS, Google Cloud Pub/Sub, publishing, ETA limits, and queue creation |
| tasks-and-scheduling.md | Pydantic tasks, crontab parsing, canvas behavior, timeouts, and gevent revocation |
| result-backends.md | Database, Redis, DynamoDB, and Azure Blob Storage result backends |
Check compatibility before upgrading
Runtime requirements changed
- For 5.5, use CPython 3.8–3.13 or PyPy 3.10+, Kombu 5.5 or newer, redis-py 4.5.2 or newer, Billiard 4.2.1 or newer, and Django 2.2.28 or newer.
- For 5.6, use CPython 3.9–3.13 or PyPy 3.11, Kombu 5.6 or newer, and Billiard 4.2.4 or newer.
- SQLAlchemy 1.4 and 2.0 are supported.
- Celery 4.x is unsupported. Celery 5.x is not an LTS line and is supported only until Celery 6.x.
See runtime-and-lifecycle.md before changing Python, framework, or transport dependencies.
SQS uses pycurl again
Celery 5.5 replaced the pycurl dependency with urllib3, but the 5.6 SQS
transport reverses that change and uses pycurl again. Ensure 5.6 SQS worker
images and deployment environments provide the restored dependency.
Singleton groups unroll
A one-item group chained with | unrolls to its contained signature. The
downstream task receives the item result, not a one-element list:
workflow = group(add.s(1, 1)) | consume.s()
Here, consume receives 2. Audit downstream tasks that assumed a list.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 177 lines · 9 tokens per session scan A 1923d287caca
celery-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (24 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 1,375 once invoked, about $0.0000 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
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…
api-config
Reference for core and server configuration in @cyanheads/mcp-ts-core. Covers env var tables with defaults, priority order, server-specific Zod schema pattern, and Workers lazy-parsing requirement.