Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/holon-run/holonnpx agentmods add skills/holon-run/holon/opsWrote 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/holon-run/holon/ops)<a href="https://agentmods.dev/skills/holon-run/holon/ops"><img src="https://agentmods.dev/badge/skills/holon-run/holon/ops.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 | $0.00027 | $0.01456 |
| Opus 5 | $0.00014 | $0.00728 |
| Sonnet 5 | $0.00005 | $0.00291 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
ops 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 today.
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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
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.
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.
- today First seen · 179 lines · 27 tokens per session scan A bdce92218c36
ops is a skill published in the GitHub repository holon-run/holon (135 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,456 once invoked, about $0.0001 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 2026-09-07.
Other skills, from other repositories
google-workspace-setup
One-time setup for gws: install, OAuth, scopes, auto-approve.
attachments
Move bytes between Gini upload space, external URLs, and workspace files. Used by every attachment / file-upload / file-download flow regardless of the target system (Linear, GitHub, S3, Notion, etc.).
google-docs
Google Docs via gws: read, append text, structured batch edits.
google-forms
Google Forms via gws: create forms, add items, read responses.
google-sheets
Google Sheets via gws: read/write cells, append rows, structured batch edits.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.