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 instructions/kubenoops/railctl/copilot-instructionsgit clone --depth 1 https://github.com/kubenoops/railctlWhat 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 | $0.00007 | $0.00007 |
| Opus 5 | $0.00003 | $0.00003 |
| Sonnet 5 | $0.00001 | $0.00001 |
| Haiku 4.5 | $0.00001 | $0.00001 |
Grade A, and why
railctl copilot-instructions.md 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- railctl CLAUDE.md — 100% identical, 0 lines differ
What it actually says
See .ai/instructions.md.
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 · 2 lines · 7 tokens per session scan A 4509f403fa5f
railctl copilot-instructions.md is an instructions file published in the GitHub repository kubenoops/railctl (2 stars, last pushed 3d ago), licensed MIT. It adds 7 tokens to every session, about $0.0000 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 instructions, from other repositories
defang CLAUDE.md
Instructions for DefangLabs/defang, a project described as: Defang CLI. Develop Once, Deploy Anywhere. Take your app from Docker Compose to a secure and scalable deployment on your favorite cloud in minutes.
kubectl-mcp-server CLAUDE.md
Instructions for rohitg00/kubectl-mcp-server, covering kubectl-mcp-server project memory, project overview, current state (as of 2026-02-02), latest release: v1.22.0 and release v1.22.0 changes.
terraform-lsp CLAUDE.md
Instructions for zircote/terraform-lsp, covering claude.md, project overview, setup, macos (homebrew) and key files.
OCI-draw.io-Architect CLAUDE.md
Instructions for sergio-farfan/OCI-draw.io-Architect, covering claude.md, project, repository contents, commands and package the plugin.
terraform-lsp copilot-instructions.md
Instructions for zircote/terraform-lsp, covering copilot instructions, priorities, commands, key files and hook patterns.
deploio-claude-plugin CLAUDE.md
Instructions for renuo/deploio-claude-plugin, covering claude.md, what this repo is, repository structure, key nctl command groups and skill architecture.