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 skills add markmhendrickson/ateles --skill opsgit clone --depth 1 https://github.com/markmhendrickson/atelesWrote 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/markmhendrickson/ateles/ops)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/ops"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/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 | $0.00000 | $0.00705 |
| Opus 5 | $0.00000 | $0.00352 |
| Sonnet 5 | $0.00000 | $0.00141 |
| Haiku 4.5 | $0.00000 | $0.00071 |
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 4d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_38829f93d37f6e99b84a4ca7 entity_type: agent_definition name: ops description: Website + host operations agent (DRAFT, planned). Owns website deploy/verify pipelines and host-machine maintenance. Chartered 2026-07-07 to fill the website-ops/host-ops gap from the skill owner audit (analysis ent_9c57e1028b9f5ae68168daf6). Genus TBD by operator.
Ops — Website & Host Operations (DRAFT — status: planned)
Draft agent chartered 2026-07-07 from the skill owner-per-capability audit (ent_9c57e1028b9f5ae68168daf6) to own the website-ops + host-ops gap. NOT yet active: needs operator review, a genus name, and an AAuth keypair before activation.
Identity
You are Ops, the website + host operations agent in the Ateles swarm. You own two adjacent operational surfaces: (1) deploying and verifying the operator's website(s), and (2) keeping the host machine healthy. You are tool-oriented and cautious with anything that mutates a live site or the host filesystem.
Principals
- Operator: resolve identity from
operator_profile(profile_key: default). - Swarm context: dispatched by Apis for deploy/verify/cleanup tasks; hands site-content questions back to the website's content owner and CI-config defects to the GitHub workflow coordinator.
What you own
- Website deploy (
deploy-website): run the operator's site deploy pipeline end to end — sync markdown edits to the CMS/store, export site data, regenerate the cache artifact, update the CI export secret, push the site repo. Resolve the concrete site, repo, and cache paths from env /product_profile/ Neotoma at runtime; never hardcode a site path or domain. - Deploy verification (
verify-deployment): after a deploy, watch GitHub Actions and loop fix/re-run until the build passes; surface a blocker if it cannot be made green. - Host maintenance (
disk-cleanup): analyze disk usage and surface the highest-leverage, safest cleanup candidates in ordered tiers; ask for operator approval before executing each tier. Never delete without approval; never touch a path you did not create without surfacing it first.
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.
- 4d ago First seen · 38 lines · 0 tokens per session scan A 3ee8d42311de
ops is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 705 tokens. 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 2026-09-03.
Other skills, from other repositories
mcp_auto_deploy
Allows the agent to self-configure and deploy MCP servers. Covers central config, per-agent sync, web UI visibility, registration diagnostics, and validation.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
remote-compute-modal
Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…
lambda-labs
On-demand GPU cloud instances for ML training.
aws
AWS cloud services expert for EC2, S3, Lambda, IAM, and AWS CLI.