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 skills add chainguard-demo/claude-plugins --skill mapping-container-images-to-chainguardgit clone --depth 1 https://github.com/chainguard-demo/claude-pluginsWrote 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/chainguard-demo/claude-plugins/mapping-container-images-to-chainguard)<a href="https://agentmods.dev/skills/chainguard-demo/claude-plugins/mapping-container-images-to-chainguard"><img src="https://agentmods.dev/badge/skills/chainguard-demo/claude-plugins/mapping-container-images-to-chainguard/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.
<a href="https://agentmods.dev/skills/chainguard-demo/claude-plugins/mapping-container-images-to-chainguard"><img src="https://agentmods.dev/badge/skills/chainguard-demo/claude-plugins/mapping-container-images-to-chainguard.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00035 | $0.02052 |
| Opus 5 | $0.00017 | $0.01026 |
| Sonnet 5 | $0.00007 | $0.00410 |
| Haiku 4.5 | $0.00003 | $0.00205 |
Grade A, and why
mapping-container-images-to-chainguard 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 12d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When converting FROM statements in a Dockerfile to use Chainguard images, follow
these steps:
- Use the dfc MCP server for automated conversion where available
- Apply tag mapping rules
- Look up unknown images using the ai-docs MCP server
- Handle special cases (generic Linux bases, static binaries, FIPS)
Use the dfc MCP Server
If the dfc MCP server is available, use it to perform automated conversion. It
handles registry rewriting, image name translation, and tag mapping automatically.
Use the convert_dockerfile tool to convert a full Dockerfile, or
analyze_dockerfile to inspect the current state before converting.
When using dfc, always pass the organization name if you know it. If you don't,
use ORG as a placeholder and remind the user to substitute their own.
Organization Name
Every Chainguard customer has their own organization namespace at cgr.dev:
cgr.dev/ORGANIZATION/image-name:tag
- For enterprise customers, use the customer's Chainguard organization name
- For free tier / public images, use
chainguard
Check ~/.claude/chainguard-preferences.md if it exists, or ask the user if the
organization name is unknown.
Tag Mapping Rules
Follow these rules when converting tags from upstream images to Chainguard:
chainguard-basealways useslatest— never add a version or-devsuffix- No tag or non-semantic tag →
latestFROM node→FROM cgr.dev/ORGANIZATION/node:latestFROM node:lts→FROM cgr.dev/ORGANIZATION/node:latest
- Semantic version → truncate to major.minor
FROM node:14.17.3→FROM cgr.dev/ORGANIZATION/node:14.17
- Add
-devsuffix when the stage hasRUNcommands (exceptchainguard-base)FROM node:14(stage has RUN) →FROM cgr.dev/ORGANIZATION/node:14-devFROM node:14(no RUN) →FROM cgr.dev/ORGANIZATION/node:14
- Final stage of a multi-stage build should use a non-dev image unless it
has
RUNcommands
Examples:
FROM node:14→FROM cgr.dev/ORG/node:14-dev(if stage has RUN commands)FROM node:14.17.3→FROM cgr.dev/ORG/node:14.17-dev(if stage has RUN commands)FROM debian:bullseye→FROM cgr.dev/ORG/chainguard-base:latest(always)FROM golang:1.19-alpine→FROM cgr.dev/ORG/go:1.19-dev(if stage has RUN commands)
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.
- 12d ago First seen · 182 lines · 35 tokens per session scan A 481fa0f0198b
mapping-container-images-to-chainguard is a skill published in the GitHub repository chainguard-demo/claude-plugins (7 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,052 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 2026-08-31.
Other skills, from other repositories
build-mcpb
This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem…
nextjs-deployment
Provides comprehensive patterns for deploying Next.js applications to production. Use when configuring Docker containers, setting up GitHub Actions CI/CD pipelines, managing environment variables, implementing preview deployments, or setting up monitoring and logging for Next.js applications. Covers standalone output…
opencode-sandbox
Run OpenCode in a docker-dev sandbox (SSH/gh on by default; --no-ssh/--no-github to isolate). Prints docker exec attach; kept until you confirm rm. Don't use for opencode.ai (opencode-runner), Herdr, or the app.
escaping-hardened-containers
Escape containers that drop capabilities, enforce seccomp profiles, and run behind AppArmor or SELinux — enumerating residual capabilities, analyzing seccomp filters, abusing single-capability escapes, cgroup release agents, filesystem mounts, and runtime CVEs. Use when a container has no --privileged flag but retains…
pentest-cloud-infrastructure
Cloud security posture management and container security assessment for AWS, Azure, GCP, and Kubernetes.
configure-log-aggregation
Set up centralized log aggregation with Loki and Promtail (or ELK stack), including log parsing, label extraction, retention policies, and integration with metrics for correlation. Use when consolidating logs from multiple services into a searchable system, replacing local log files with centralized queryable storage…