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/cozystack/ccp/cluster-upgradenpx skills add cozystack/ccp --skill cluster-upgradegit clone --depth 1 https://github.com/cozystack/ccpWhat 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 | $0.00040 | $0.02511 |
| Opus 5 | $0.00020 | $0.01256 |
| Sonnet 5 | $0.00008 | $0.00502 |
| Haiku 4.5 | $0.00004 | $0.00251 |
Grade A, and why
cluster-upgrade 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 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.
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.
cozystack:cluster-upgrade
Guided upgrade of a running Cozystack v1.x cluster. Source of truth: https://cozystack.io/docs/<vX.Y>/operations/cluster/upgrade/ (substitute the version selector value matching your target — e.g. v1.3).
Core principles
Release-notes-driven upgrade. Every release changes a specific set of components. Generic "all green" checks miss regressions in the areas that actually changed. Read the target's release notes, extract the change list, and run targeted pre/post checks — not just the default health checklist.
Match the operator's natural language. Detect from prior conversation messages (or read <config-dir>/.state.yaml operator_language if a wizard chain is in progress). Use it in every prompt, AskUserQuestion option, summary, and gate. Never ask "what language?" separately. Code identifiers, commands, file paths, and GitHub-public text stay in their canonical form.
One valid path → just do it. After the operator approved the risk summary at the upgrade stop gate, the skill runs helm upgrade + post-upgrade health checks + tenant verification back-to-back. Approval gates remain only for the named STOP GATEs in the workflow (risk summary, helm upgrade itself, final report) and for any rollback action (always destructive-risky).
Front-load the interview. Read the cluster + release notes + pre-flight checks up front and surface a single risk-summary screen with the upgrade plan, change-list, and any blockers. Approval of that screen is the only interview gate — subsequent phases (helm upgrade, post-upgrade checks) execute without re-prompting.
Layer-pure operator output. The skill never says "returning control to wizard" or any other orchestration commentary in the operator-facing summary. Whoever invoked the skill (a human directly, or a chain orchestrator) figures out what's next on their own. Internal documentation references are fine; wizard does not appear in text shown to the operator.
Workflow
What ships with it
5 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.
- 2d ago First seen · 182 lines · 40 tokens per session scan A 8b56890daa38
cluster-upgrade is a skill published in the GitHub repository cozystack/ccp (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,511 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
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.