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/docker-knowledge-patchnpx skills add Nevaberry/nevaberry-plugins --skill docker-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 | $0.00007 | $0.02333 |
| Opus 5 | $0.00003 | $0.01167 |
| Sonnet 5 | $0.00001 | $0.00467 |
| Haiku 4.5 | $0.00001 | $0.00233 |
Grade A, and why
docker-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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Knowledge Patch
Use this patch when work touches Docker Engine runtime, networking, images, the Engine API, Go integrations, Buildx, BuildKit, Dockerfile, or Compose.
How to use this patch
- Identify the component and read its complete topic reference before changing configuration, API calls, parsers, or automation.
- Check the installed daemon, CLI, API, Buildx, BuildKit, Dockerfile frontend, and Compose versions that matter to the task. They do not share one version.
- For Engine work, distinguish a fresh installation from an upgrade and check both the daemon version and negotiated API version.
- Treat output formats as interfaces: request an explicit CLI format and parse event, progress, and Compose streams according to their record framing.
- Prefer the project's manifests, configuration, code, tests, and observed behavior whenever they disagree with compatibility guidance.
Reference index
| Reference | Topics |
|---|---|
| runtime.md | Daemon lifecycle, storage, resources, security, rootless, Swarm, Windows, and platform support |
| networking.md | Attachments, DNS, IPv4/IPv6, IPAM, gateways, firewalls, and routing |
| images-registry.md | Image stores, inspection, archives, platforms, registries, identity, and trust |
| engine-api.md | API floors, version-gated schemas, event framing, updates, and deprecations |
| go-sdk-cli.md | Go module, client, type, and call migrations; CLI integration changes |
| buildx.md | Buildx, Bake, Imagetools, builders, exporters, policies, and resources |
| buildkit-dockerfile.md | BuildKit sources, provenance, verification, deployment, Dockerfile, and linting |
| compose.md | Compose SDK, builds, reconciliation, lifecycle, providers, publish, Watch, and output |
What ships with it
9 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 · 236 lines · 7 tokens per session scan A aec5ada7d65f
docker-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (24 stars, last pushed 6d ago), licensed MIT. It adds 7 tokens to every session and 2,333 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
k8s-sidecar-testing
End-to-end testing workflow for nat464-sidecar in IPv6-only Kubernetes clusters. Use when setting up test environments, deploying the sidecar to k3s, verifying IPv6-to-IPv4 translation (inbound and outbound), benchmarking performance, running path validation, or troubleshooting pod networking issues. Triggers: 'test…
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.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
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-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.