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/lexfrei/ccc/docker-prunenpx skills add lexfrei/ccc --skill docker-prunegit clone --depth 1 https://github.com/lexfrei/cccWhat 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 | $0.00116 | $0.01425 |
| Opus 5 | $0.00058 | $0.00713 |
| Sonnet 5 | $0.00023 | $0.00285 |
| Haiku 4.5 | $0.00012 | $0.00143 |
Grade B, and why
docker-prune scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
colima ssh -- sudo fstrim -a -v How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reclaim Docker disk space, then report what was freed.
Operates in report → confirm → execute order. The scope is chosen through an interactive question, not flags. After approval, run the prune autonomously.
Step 1: Check the daemon
docker info >/dev/null 2>&1
If it fails, the Docker daemon is not reachable. On a Colima/Lima or other VM-backed setup, tell the user how to start it (e.g. colima start) and stop — do not guess.
With the daemon up, record the engine version: docker version --format '{{.Server.Version}}'. It determines volume-prune behavior (see Step 3).
Also note whether the daemon is VM-backed (Colima/Lima, or any setup where the daemon runs inside a VM whose disk is a file on the host — colima status succeeding is the common signal). This enables the trim scope (Steps 2–4).
Step 2: Report reclaimable size
docker system df
docker buildx ls
Show the docker system df breakdown (images, containers, local volumes, build cache) with the reclaimable column.
On a VM-backed daemon, also account for the host-side disk image. Everything docker system df shows lives inside a VM disk that is a sparse file on the host (Colima: ~/.colima/_lima/_disks/<profile>/datadisk). Blocks freed by pruning inside the guest are NOT returned to the host until the guest filesystem issues discards — so the host file's allocated size keeps the high-water mark of every past build. Measure both sides: apparent size (ls -lh <disk>) vs actually allocated (du -sh <disk>), and compare the allocated size with what the guest really uses (colima ssh -- df -h /var/lib/docker). A large gap means the trim scope alone can return that space to the host, even with nothing left to prune. Record the allocated size as the baseline for Step 5.
Critically, account for non-default buildx builders. docker system prune only prunes the build cache of the default builder. A docker-container-driver builder (common with multi-arch / Colima setups) keeps its cache inside an in-use state volume named after the builder's node — buildx_buildkit_<node>_state (e.g. builder multi with node multi0 → buildx_buildkit_multi0_state; a multi-node builder has one such volume per node). That volume shows as active in docker system df, so neither docker system prune nor docker volume prune reclaims it — only docker buildx prune does. This is frequently the single largest reclaimable item. For each non-default builder from docker buildx ls, note its cache (the size of its buildx_buildkit_*_state volume(s) in docker system df -v is a good proxy).
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 · 68 lines · 116 tokens per session scan B 561ce8db10ea
docker-prune is a skill published in the GitHub repository lexfrei/ccc (9 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 116 tokens to every session and 1,425 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.