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 commands/dykyi-roman/awesome-claude-code/audit-dockergit clone --depth 1 https://github.com/dykyi-roman/awesome-claude-codeWrote 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/commands/dykyi-roman/awesome-claude-code/audit-docker)<a href="https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/audit-docker"><img src="https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/audit-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 | $0.00023 | $0.01568 |
| Opus 5 | $0.00012 | $0.00784 |
| Sonnet 5 | $0.00005 | $0.00314 |
| Haiku 4.5 | $0.00002 | $0.00157 |
Grade A, and why
audit-docker 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 yesterday.
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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Audit
Perform a comprehensive audit of Docker configuration, including architecture, security, performance, and production readiness.
Input Parsing
Parse $ARGUMENTS to extract path, level, and optional meta-instructions:
Format: [path] [level] [-- <meta-instructions>]
Arguments:
- path: Target directory (optional, default: ./)
- level: Audit depth - quick|standard|deep (optional, default: standard)
- -- meta-instructions: Additional focus areas or filters (optional)
Examples:
- /acc:audit-docker
- /acc:audit-docker ./
- /acc:audit-docker deep
- /acc:audit-docker ./ deep
- /acc:audit-docker -- focus on security
- /acc:audit-docker deep -- focus on security
- /acc:audit-docker -- level:deep (backward compatible)
Parsing rules:
- Split
$ARGUMENTSby--(space-dash-dash-space) - First part = positional arguments, Second part = meta-instructions
- In positional arguments, check if any word is a valid level (
quick|standard|deep) - If level found → extract it; remaining = path (or default
./) - Also accept
level:quick|standard|deepin meta-instructions (backward compatibility) - Priority: positional > meta-instruction > default (
standard)
Pre-flight Check
-
Find Docker artifacts:
# Dockerfiles ls Dockerfile* 2>/dev/null ls docker/Dockerfile* 2>/dev/null # Compose files ls docker-compose*.yml docker-compose*.yaml 2>/dev/null # Docker-related configs ls .dockerignore 2>/dev/null ls docker/ 2>/dev/null ls nginx.conf nginx/ 2>/dev/null # PHP project info cat composer.json 2>/dev/null | head -30 -
If no Docker files found:
- Report "No Docker configuration found"
- Suggest
/acc:generate-docker fullto create complete Docker setup
Instructions
Use the acc:docker-coordinator agent to perform the audit:
Task tool with subagent_type="acc:docker-coordinator"
prompt: "Perform comprehensive Docker audit at [PATH]. Audit level: [LEVEL].
Operation: AUDIT
[FOCUS_AREAS if provided]
Use TaskCreate/TaskUpdate for progress visibility. Create tasks for each audit phase.
Audit areas:
1. Dockerfile architecture (multi-stage, layer ordering, BuildKit)
2. Base images and PHP extensions (selection, pinning, compatibility)
3. Docker Compose (services, health checks, networking, environment)
4. Performance (build time, image size, caching, PHP-FPM, OPcache)
5. Security (user permissions, secrets, vulnerabilities, network)
6. Production readiness (health checks, graceful shutdown, logging, monitoring)
Generate a full audit report with:
- Summary table by category
- Issues by severity (Critical/High/Medium/Low)
- Specific recommendations with code examples
- Overall score and risk level"
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.
- yesterday First seen · 234 lines · 0 tokens per session scan A 3f6593932bf7
audit-docker is a command published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 20d ago), licensed MIT. It adds 23 tokens to every session and 1,568 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
create-docker-mcp-tunnel
Stand up an Anthropic MCP tunnel locally with Docker Compose so Claude can call a private MCP server (manual-credentials quickstart).
sandbox
Manage sandbox backends and tooling.
dockerfile
Validate Dockerfiles for GPU/CUDA configuration issues before building.
index
Command "index" from thrashr888/agentkernel, covering commands, quick reference, daily drivers (root level), sandbox lifecycle (sandbox / sb) and ssh (ssh).
deploy
Build, test, deploy with staged rollout.
status
List all SandboxClaims with phase, age, template, and bound pod. Detects stuck-in-Pending claims and surfaces likely causes.