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/neverinfamous/memory-journal-mcp/dockernpx skills add neverinfamous/memory-journal-mcp --skill dockergit clone --depth 1 https://github.com/neverinfamous/memory-journal-mcpWrote 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/neverinfamous/memory-journal-mcp/docker)<a href="https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/docker"><img src="https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/docker.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 | $0.00108 | $0.01523 |
| Opus 5 | $0.00054 | $0.00762 |
| Sonnet 5 | $0.00022 | $0.00305 |
| Haiku 4.5 | $0.00011 | $0.00152 |
Grade C, and why
docker scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
&& rm -rf /var/lib/apt/lists/* Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **The runtime stage should have ZERO build tools** (no compilers, no git, no curl) How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker & Container Engineering Standards
This skill codifies 2026 Docker best practices — secure, minimal, reproducible container images using BuildKit, multi-stage builds, and Compose v2.
1. Dockerfile Fundamentals
Always Start With BuildKit Syntax
# syntax=docker/dockerfile:1
Place this as the first line of every Dockerfile. It enables:
- Parallel stage execution
- Cache mounts (
--mount=type=cache) - Secret mounts (
--mount=type=secret) - Reproducible builds across Docker versions
Base Image Selection
| Use Case | Recommended Base | Why |
|---|---|---|
| Node.js | node:22-slim |
Debian Slim — small, has essential libs |
| Python | python:3.13-slim |
Minimal Debian, no build tools |
| Go | scratch or distroless |
Static binary needs nothing |
| General | debian:bookworm-slim |
Stable, well-patched, small |
- NEVER use
:latest— always pin to a specific version tag - Prefer
-slimvariants over full images to reduce attack surface - Consider
distrolessfor production — no shell, no package manager = minimal attack surface
2. Multi-Stage Builds (Required for Production)
Multi-stage builds are mandatory for any production image. They separate build-time dependencies from runtime. See templates.md for the full annotated Multi-Stage Build template.
Key Rules
- Name every stage:
FROM ... AS builder— makes builds readable and targetable - Copy only artifacts: Use
COPY --from=builderto cherry-pick built files - Never install dev dependencies in the runtime stage
- The runtime stage should have ZERO build tools (no compilers, no git, no curl)
3. Security Hardening
Non-Root Execution (Mandatory)
# Create a system user with no home directory, no login shell
RUN groupadd -r appgroup && useradd -r -g appgroup -s /usr/sbin/nologin appuser
# Switch to the non-root user BEFORE CMD
USER appuser
What ships with it
2 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.
- 4d ago First seen · 169 lines · 108 tokens per session scan C 438f91c1be96
docker is a skill published in the GitHub repository neverinfamous/memory-journal-mcp (20 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,523 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
good-skill
Use only for fixture validation of narrow skill routing. Avoid for normal repo work.
broad-skill
Always use this skill for every task and all tasks.
faf-expert
Expert in the .faf format (Persistent Project Context for AI) and the faf-cli toolkit. Use when working with .faf files, scoring AI-readiness, syncing project context to CLAUDE.md, or discussing the Foundational Context Layer (FCL) doctrine. IANA-registered (application/vnd.faf+yaml). Anthropic-listed as "Persistent…
caveman-fixture
Always use caveman terse speech for every task.
skill-creator
Generate a new skill from a plain-language description — decides invocation control, arguments, and context cost, then scaffolds, validates, and tests it.
context-end
Close a workspace session by reviewing a proposed summary, recording approved outcomes, updating state and decisions, and checking repository safety. Use only when the user explicitly asks to end, close, or hand off the current session.