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 jimtin/production-ai --skill docker-disk-cleanupgit clone --depth 1 https://github.com/jimtin/production-aiWrote 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/jimtin/production-ai/docker-disk-cleanup)<a href="https://agentmods.dev/skills/jimtin/production-ai/docker-disk-cleanup"><img src="https://agentmods.dev/badge/skills/jimtin/production-ai/docker-disk-cleanup.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 5.1 | $0.00074 | $0.01027 |
| Opus 5 | $0.00037 | $0.00513 |
| Sonnet 5 | $0.00015 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
docker-disk-cleanup 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 7d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Disk Cleanup
Purpose
Use this skill to reclaim Docker disk space without damaging active local services, test databases, or PR-gate runs. Prefer the bundled script over ad hoc prune commands.
Operating Rules
- Start with an audit: filesystem free space,
docker info,docker system df, containers, and volumes. - Use
scripts/docker-disk-cleanup.mjs; do not hand-roll prune order unless the script is missing or cannot run. - Do not use
sudo. - Do not delete named project volumes manually. Let Docker remove only volumes it reports as dangling, after attachment checks.
- Do not run overlapping cleanup jobs. The script uses a lock in the report directory.
- Preserve active services. If gate-like containers are running, or the user says a gate is active, run active-gate mode so image and builder pruning use an age filter.
- Treat Docker race errors such as containers disappearing between list and prune as recheck-and- continue signals unless the script reports a hard failure.
- Keep reports sanitized: do not print env values, tokens, auth files, or secret-looking strings.
Quick Start
Run a dry run first:
node ~/.codex/skills/docker-disk-cleanup/scripts/docker-disk-cleanup.mjs audit
node ~/.codex/skills/docker-disk-cleanup/scripts/docker-disk-cleanup.mjs cleanup --dry-run
Run cleanup:
node ~/.codex/skills/docker-disk-cleanup/scripts/docker-disk-cleanup.mjs cleanup
For a known active PR gate or long validation run:
node ~/.codex/skills/docker-disk-cleanup/scripts/docker-disk-cleanup.mjs cleanup --active-gate-mode
When volume risk is unclear:
node ~/.codex/skills/docker-disk-cleanup/scripts/docker-disk-cleanup.mjs cleanup --skip-volumes
Workflow
- Confirm the target path. Probe the filesystem that actually holds Docker data or the active
workspace. Pass it with
--workspace <path>or setDOCKER_DISK_CLEANUP_WORKSPACE. If unsure, use the current working directory and say so. - Audit first. Run
auditorcleanup --dry-run. Readdocker system dfbefore deciding how aggressive cleanup should be. - Check active work. Inspect running containers and the script's
activeGateModedecision. Use--active-gate-modewhen a PR gate, test gate, or build is active. - Run serialized cleanup. The script plans commands in this order:
docker container prune -fdocker network prune -fdocker image prune -a ... -fdocker builder prune -a ... -f- dangling volume attachment checks
docker volume prune -a -fwhen supported, otherwisedocker volume prune -f- final
docker image prune -a ... -f
- Report the outcome. Include initial/final disk usage, Docker usage, mode, commands run, report path, removed-space summary when Docker provides one, skipped steps, and blockers.
What ships with it
6 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.
- 7d ago First seen · 109 lines · 74 tokens per session scan A fa4630edff5d
docker-disk-cleanup is a skill published in the GitHub repository jimtin/production-ai (1 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,027 once invoked, about $0.0004 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
Sandbox Isolation
Run untrusted or risky commands in Docker-based sandbox with resource limits and network isolation.
mirror-optimizer
A skill that detects a project’s package managers and configures regional package mirrors, mainly for deployments from mainland China. Package mirrors are alternate servers for downloading dependencies such as libraries and container images.
securing-cloud-and-supply-chain
A guide to protecting cloud infrastructure and the software supply chain, the systems and dependencies used to build and deliver software.
provisioning-infrastructure
Cloud-native infrastructure knowledge reference covering Kubernetes, Helm, Kustomize, Operators, CRDs, GitOps (ArgoCD, Flux), and IaC (Terraform, Pulumi, CDK). Use when provisioning infrastructure, managing clusters, or working with GitOps workflows.
devops-specialist
A DevOps and operations guide for running software reliably. DevOps combines software development with the work of building, deploying, monitoring, and maintaining systems.
test-integration-docker
Run comprehensive integration tests using real skills (Vercel, Anthropic, Expo) in a Docker container. Managed via Makefile for standard lifecycle control.