KubeSphere Multi-Tenant Management
kubesphere/kubesphere
Creates and queries KubeSphere users, workspaces and projects and assigns built-in roles, defaulting to least privilege and never deleting anything.
Operate servers and services with read-only-first diagnosis, explicit authorization, auditable inventory, operation records, rollback, and verification.
Install Ops
$ npx skills add holon-run/holon --skill ops -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install holon-run/holon ops --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ops .claude/skills/ops && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ops" agent skill from https://github.com/holon-run/holon/tree/main/skills/ops into .claude/skills/ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/holon-run/holon/tree/main/skills/opsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add holon-run/holon --skill ops -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install holon-run/holon ops --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ops .agents/skills/ops && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ops" agent skill from https://github.com/holon-run/holon/tree/main/skills/ops into .agents/skills/ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add holon-run/holon --skill ops -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install holon-run/holon ops --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ops .cursor/skills/ops && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ops" agent skill from https://github.com/holon-run/holon/tree/main/skills/ops into .cursor/skills/ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/holon-run/holon.git --path skills/ops--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add holon-run/holon --skill ops -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install holon-run/holon ops --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ops .gemini/skills/ops && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ops" agent skill from https://github.com/holon-run/holon/tree/main/skills/ops into .gemini/skills/ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install holon-run/holon opsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add holon-run/holon --skill ops -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ops .github/skills/ops && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ops" agent skill from https://github.com/holon-run/holon/tree/main/skills/ops into .github/skills/ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add holon-run/holon --skill ops -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install holon-run/holon ops --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/holon-run/holon.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ops .opencode/skills/ops && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ops" agent skill from https://github.com/holon-run/holon/tree/main/skills/ops into .opencode/skills/ops/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ops", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ops- GitHub stars
- 153
- Token cost
- ~1.7k tokens
- SKILL.md length
- 635 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Operate servers and services with read-only-first diagnosis, explicit authorization, auditable inventory, operation records, rollback, and verification.
- Works in 7 steps: Identify the exact environment, hosts,… → Determine the authorization level before… → Prefer read-only discovery and preflight… → …
- Tasks that involve Authorization and RBAC
- SKILL.md covers Destructive service operations, Core rules, Inventory layout and Operation records, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Ops is an agent skill from holon-run/holon. Operate servers and services with read-only-first diagnosis, explicit authorization, auditable inventory, operation records, rollback, and verification.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering Authorization and RBAC. The repository describes itself as: An agent workbench for ongoing work: preserve goals and progress, connect events and schedules, and resume when the next condition is met. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Authorization and RBAC
Example prompts
- “/ops”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Identify the exact environment, hosts, services, source of truth, and
- Determine the authorization level before touching an external system
- Prefer read-only discovery and preflight checks. Do not infer repair
- Before a change, state targets, expected effect, risk, commands or API
- Use a canary and bounded batches for multi-resource work. Verify each batch
- Record actual actions, sanitized evidence, results, and deviations.
- Verify service health and intended state after the action. Roll back only
What it can do on your machine
Read from SKILL.md and the folder at commit 671bd7a. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Ops loads about 1.7k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 635 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from holon-run/holon at commit 671bd7a, republished under its Apache-2.0 licence (© holon-run). 635 words, ~1,683 tokens.
Download SKILL.mdSave it as
.claude/skills/ops/SKILL.md (or your agent's skills folder).- name
- ops
- description
- Operate servers and services with read-only-first diagnosis, explicit authorization, auditable inventory, operation records, rollback, and verification.
Operations
Use this skill for platform-neutral server and service operations. It defines the workflow and record formats; environment-specific skills and tools own Linux, SSH, containers, Kubernetes, IaC, cloud, and observability commands.
Destructive service operations
When an operation can stop or replace the process performing the operation,
schedule it through an external supervisor or transient unit rather than
running it synchronously in the service cgroup. Persist a unique operation id
and an explicit planned → scheduled phase before dispatch. Recovery must
use the idempotency record to verify the target, not replay the destructive
command. Never substitute nohup, &, or sleep for a durable lifecycle
boundary.
Core rules
- Identify the exact environment, hosts, services, source of truth, and operator request.
- Determine the authorization level before touching an external system:
- L0: local inventory and documentation only.
- L1: read-only checks within an explicitly confirmed scope.
- L2: reversible changes, requiring per-action approval unless covered by a scoped, expiring, revocable runbook authorization.
- L3: disruptive, privileged, network, IAM, DNS, data, secret, bulk, or irreversible work, requiring confirmation of the exact action.
- Prefer read-only discovery and preflight checks. Do not infer repair authority from diagnosis or urgency.
- Before a change, state targets, expected effect, risk, commands or API actions, success criteria, rollback trigger, and rollback steps.
- Use a canary and bounded batches for multi-resource work. Verify each batch before proceeding.
- Record actual actions, sanitized evidence, results, and deviations.
- Verify service health and intended state after the action. Roll back only when authorized or when a confirmed runbook explicitly permits it.
Stop and ask when target identity, current state, authority, impact, rollback, or verification is unclear.
Inventory layout
Create only the files needed for the current environment:
work/
inventory/
sources.md
hosts/<host-id>/info.yaml
hosts/<host-id>/operations.md
services/<service-id>/info.yaml
services/<service-id>/operations.md
runbooks/
inspections/
operations/YYYY/YYYY-MM/
incidents/sources.md records each authoritative source, owner, refresh method, and last
confirmation. Prefer external sources of truth. AgentHome inventory is a cache
unless the operator explicitly designates it authoritative.
Use stable IDs and schema_version: 1. A host info.yaml should contain:
schema_version: 1
id: prod-web-01
display_name: Production Web 01
environment: production
status: active
owners: [platform]
criticality: high
location: {provider: example-cloud, region: us-east-1}
roles: [web]
access:
ssh_config_alias: prod-web-01
bastion_alias: prod-bastion
credential_ref: secret-manager://ops/prod-web
platform: {os: ubuntu, architecture: amd64}
services: [customer-web]
monitoring: {dashboards: [], alerts: []}
source:
kind: cmdb
ref: host/prod-web-01
last_synced_at: 2026-09-06T00:00:00Z
last_confirmed_at: 2026-09-06T00:00:00ZA service info.yaml should contain:
schema_version: 1
id: customer-web
display_name: Customer Web
environment: production
status: active
owners: [web-team]
criticality: high
service_type: systemd
runs_on: {hosts: [prod-web-01, prod-web-02]}
dependencies: [customer-api]
repository: github:example/customer-web
deployment_source: gitops:environments/prod/customer-web
runbook: work/runbooks/customer-web.md
monitoring: {dashboards: [], alerts: []}
backup: {policy_ref: backup/customer-web}
maintenance:
timezone: America/New_York
windows: []
source:
kind: gitops
ref: services/customer-web
last_synced_at: 2026-09-06T00:00:00Z
last_confirmed_at: 2026-09-06T00:00:00ZNever store a credential value. credential_ref may contain only a controlled
secret-manager reference or local connection alias. Keep permission policies
separate from resource facts so an inventory edit cannot expand authority.
When renaming or retiring a resource, preserve its stable ID through a redirect or tombstone so historical links remain valid.
Show full SKILL.md (257 more words)Show less
Operation records
Create one authoritative record per logical operation:
work/operations/YYYY/YYYY-MM/OP-<UTC timestamp>-<slug>.mdRecord:
- UTC time and operator-local time with IANA timezone
- WorkItem, incident, change, or request reference
- actor, target environment, host IDs, and service IDs
- request and authorization summary, including standing authorization scope
- purpose, risk level, preflight results, plan, and rollback plan
- actual commands or API actions, with secrets and sensitive output redacted
- exit status, changed resources, verification evidence, and final result
- rollback status, residual risk, follow-up owner, and due condition
Do not silently rewrite an error. Append a dated correction. Put large raw output in a controlled external log or attachment and retain only a summary and reference.
Append a concise link to each affected resource's operations.md:
## 2026-09
- `2026-09-06T10:30:00Z` · change · success ·
[OP-20260906T103000Z-restart-customer-web](../../../operations/2026/2026-09/OP-20260906T103000Z-restart-customer-web.md)
— Approved rolling restart; health checks passed.The resource timeline is an index, not a duplicate operation log.
Incidents
Use work/incidents/INC-<UTC timestamp>-<slug>.md for a material anomaly.
Record detection, impact, affected resources, evidence, timeline,
communications, mitigations, current state, owner, and next update. Keep facts
separate from hypotheses. Incident creation and notification do not authorize
remediation.
Scheduled inspections
Scheduled inspection is off by default. Before creating a timer or recurring job, confirm:
- scope and exclusions
- IANA timezone and frequency or wall-clock time
- allowed checks, concurrency, and timeouts
- reporting and anomaly-notification behavior
- maintenance and silence windows
- report-only versus explicitly named remediation runbooks
- review date, end date, and pause/revocation conditions
Persist the confirmed policy in work/inspections/policy.yaml. Reconfirm any
change to scope, schedule, notification, or remediation authority. Give every
run its own tracked lifecycle and dated inspection record. The default for an
anomaly is to report and open an incident, not to repair it.
© holon-run, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/ops of holon-run/holon.
Open the folder on GitHubat commit 671bd7a
Compare with similar skills
Ops next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ops this skillholon-run/holon | 153 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| KubeSphere Multi-Tenant Managementkubesphere/kubesphere | 17k | 1 repos | ~3.1k | Automated safety check: Pass | Custom licence | |
| Kubernetes SpecialistJeffallan/claude-skills | 12k | 1 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Executing Distributed System Testsshenli/distributed-system-testing | 231 | — | ~5.1k | Automated safety check: Notes | MIT | |
| Documentationhome-operations/kopiur | 113 | — | ~2.5k | Automated safety check: Pass | AGPL-3.0 | |
| Kubernetes Patternstimothywarner-org/claude-code | 224 | — | ~4.5k | Automated safety check: Pass | MIT |
Similar skills
Kubernetes Specialist
Jeffallan/claude-skills
Creates and checks Kubernetes manifests, Helm charts, RBAC and network policies, and helps debug pod problems, with kubectl checks and rollback steps.
Executing Distributed System Tests
shenli/distributed-system-testing
A skill your agent uses when running a previously designed distributed-systems test plan against a real or simulated cluster — driving fault injection, workload, chaos scenarios, linearizability /…
Documentation
home-operations/kopiur
How Kopiur writes and maintains user-facing docs — the MkDocs Material site under docs/ and the example manifests under deploy/examples/.
Kubernetes Patterns
timothywarner-org/claude-code
Kubernetes workload patterns, resource management, RBAC, probes, autoscaling, ConfigMap/Secret handling, and kubectl debugging for production-grade deployments.
- Official
Admin
grafana/skills
Manage Grafana Cloud accounts — organizations, stacks, RBAC roles and assignments, SSO/SAML/OAuth/GitHub auth, service accounts for CI/CD, user invites, team membership, and API-driven provisioning.
More from holon-run/holon
All 13 skills in this repoVideo Production
holon-run/holon
Assemble existing local images, videos, audio and subtitles into preview/final videos with FFmpeg, technical QC and provenance.
GitHub Issue Solve
holon-run/holon
Solve a GitHub issue by collecting context, implementing a fix, and opening or updating a pull request.
GitHub PR Fix
holon-run/holon
Fix a GitHub pull request by addressing feedback or CI failures, pushing changes, and publishing replies.
Code Health Audit
holon-run/holon
Audit code-health and technical-debt signals with evidence, rank proportionate interventions from focused cleanup to broad coordinated refactors, and draft implementation-ready plans without…
Code Review
holon-run/holon
Review a set of code changes using evidence-backed findings, explicit confidence, and a clear coverage summary.
Ghx
holon-run/holon
Guidance for safe, reliable GitHub CLI workflows across issues, pull requests, and reviews.
Related
Categories
Questions about Ops
What does Ops do?
Operate servers and services with read-only-first diagnosis, explicit authorization, auditable inventory, operation records, rollback, and verification. Ops is an agent skill from holon-run/holon. Operate servers and services with read-only-first diagnosis, explicit authorization, auditable inventory, operation records, rollback, and verification.
When should I use Ops?
Ops fits situations like: tasks that involve Authorization and RBAC.
How do I install Ops in Claude Code?
Run `npx skills add holon-run/holon --skill ops -a claude-code`. Or copy the skill folder (skills/ops in holon-run/holon) into .claude/skills/ops in your project. Claude Code loads it when a task matches its description.
How do I install Ops in Codex?
Run `npx skills add holon-run/holon --skill ops -a codex`. Or copy the skill folder (skills/ops in holon-run/holon) into .agents/skills/ops in your project. Codex loads it when a task matches its description.
Can I use Ops in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add holon-run/holon --skill ops -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ops, .gemini/skills/ops, .github/skills/ops and .opencode/skills/ops in your project.
What does Ops need to run?
SKILL.md names no scripts, command-line tools or credentials: Ops is instructions for the agent only.
Does Ops access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Ops safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Ops use?
Ops is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ops use?
About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Ops?
Skills that share tags, products or a category with Ops: KubeSphere Multi-Tenant Management (kubesphere/kubesphere, 17k stars), Kubernetes Specialist (Jeffallan/claude-skills, 12k stars), Executing Distributed System Tests (shenli/distributed-system-testing, 231 stars) and Documentation (home-operations/kopiur, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ops?
holon-run (a GitHub organization) maintains it in holon-run/holon, which has 153 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 8, 2026.
Source: holon-run/holon on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.