talos-reset

A cloud-provider recovery workflow for Talos Linux nodes that cannot be reached through their normal management or Kubernetes connections. Talos is an operating system designed for Kubernetes clusters.

In plain words
What is it for?
It is for recovering unrecoverable nodes by using a cloud provider command-line tool to terminate or re-image instances while preserving attached resources where supported.
Why use it?
It provides a recovery path when TLS certificates, machine configuration, or missing management credentials prevent normal node commands from working.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cozystack/ccp/talos-reset
Any agent
npx skills add cozystack/ccp --skill talos-reset
Clone the repo
git clone --depth 1 https://github.com/cozystack/ccp

Made for: Claude Code, Codex.

Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,984 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00176 $0.03984
Opus 5 $0.00088 $0.01992
Sonnet 5 $0.00035 $0.00797
Haiku 4.5 $0.00018 $0.00398

Measured 2d ago against content hash 657746593f6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

talos-reset 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.

plugins/cozystack/skills/talos-reset/SKILL.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cozystack:talos-reset

Work in reasoning mode. Use the phrasing cozystack:talos-reset. Announce phase transitions: cozystack:talos-reset Phase N — <name>.

Note on language in this SKILL.md — every operator-facing prompt below is written in English for clarity. At runtime the skill matches the operator's natural language detected from prior conversation messages (or read from <config-dir>/.state.yaml operator_language when the wizard chain is in progress). Code identifiers, commands, file paths, and any text destined for GitHub stay canonical regardless of operator language.

When to use this skill

Use cozystack:talos-reset when none of the in-cluster paths work:

  • talosctl reset requires a valid TLS handshake — useless when cert-SAN is wrong, talosconfig is lost, or apid doesn't trust the workstation.
  • talosctl upgrade --image <X> needs the same TLS path.
  • kubectl drain + kubectl delete node only works if kube-apiserver is reachable.
  • A cluster that never reached bootstrap (talosctl bootstrap failed) has no etcd, no apiserver, no kubectl path at all.

When none of those apply, the node has to be re-imaged at the cloud-provider layer: terminate the instance, preserve the disks (so a re-bootstrap with --preserve keeps the zpool), and relaunch from the cozystack-tuned image. This skill orchestrates that without losing the operator's existing block volumes, VNIC attachments, or NSG rules.

Not for:

  • Cozystack-side problems (HRs failing, dashboard unreachable, certs not issuing) → use cozystack:debug.
  • Talos upgrades on a healthy cluster → use talosctl upgrade --preserve directly; no need for cloud-provider intervention.
  • Fresh installs with no pre-existing state → use cozystack:wizardcozystack:talos-bootstrap.

Core principles

  • Match the operator's natural language. Read <config-dir>/.state.yaml operator_language if available, detect otherwise.
  • Provider CLI is the operator's tool. The skill prints exact oci, aws, gcloud, or hcloud commands; the operator runs them. The skill never directly invokes the provider CLI without operator approval — every mutation is shown first.
  • Preserve by default. --preserve-disks and --preserve-vnics default true. The skill explicitly lists what it will preserve and what gets recreated.
  • Layer-pure operator output. The skill never says "returning control to wizard" — whoever invoked the skill figures out next steps from the printed NOTES.
  • One node at a time. Sequential terminate+relaunch preserves etcd quorum on 3+ CP clusters. For total cluster recovery (all CPs broken), the skill walks the operator through losing+regaining quorum explicitly.
  • Verify before declaring success. Post-relaunch the node must reach Talos maintenance mode (port 50000 responds to talosctl get disks --insecure) AND retain the preserved disks (existing zpool surfaced by talosctl get disks).

Read the full file on GitHub · 312 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2d ago First seen · 312 lines · 176 tokens per session scan A 657746593f6c

Subscribe to this mod's changes

talos-reset is a skill published in the GitHub repository cozystack/ccp (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 176 tokens to every session and 3,984 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

terraform-skill

Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…

agentscope-ai/QwenPaw · 62 tokens

huggingface-spaces

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't…

huggingface/skills · 106 tokens

cloud-architect

Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…

Jeffallan/claude-skills · 71 tokens

kagent-dev

Development guide for kagent's v1alpha3 Harness and AgentTemplate CRDs, AgentInstance gRPC control plane, upstream A2A integration, Substrate runtime provisioning, tests, generation, and PR workflow. Use for any implementation, debugging, review, or CI task in the kagent repository.

kagent-dev/kagent · 65 tokens

timoni

Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.

stefanprodan/timoni · 59 tokens

azmon-mirroredcatalogs-operations-cli

Brings Azure Monitor, Application Insights, and Log Analytics telemetry into Fabric as Eventhouse external delta tables and correlates it with business data. Use to onboard observability data, judge whether latency or availability affected revenue, or build a Real-Time dashboard and Operations Agent over it.

microsoft/skills-for-fabric · 66 tokens