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/vegastack/vegastack-cli/agents-mdgit clone --depth 1 https://github.com/vegastack/vegastack-cliWrote 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/instructions/vegastack/vegastack-cli/agents-md)<a href="https://agentmods.dev/instructions/vegastack/vegastack-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/vegastack/vegastack-cli/agents-md.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 | $0.01746 | $0.01746 |
| Opus 5 | $0.00873 | $0.00873 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
vegastack-cli AGENTS.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 3d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — vegastack-cli
This file is read by Codex, Cursor, Gemini, and any agent that follows the AGENTS.md convention. It tells the agent what this repo is, how to use it, and the rules.
What this repo ships
@vegastack/cli — an npm-installable knowledge harness for coding agents. After npm i -g @vegastack/cli and vegastack skills install, the agent gains:
- A bundled docs library for 31 Terraform providers (~9,000 markdown files, ~97 MB on disk after extract).
- A deterministic discovery CLI:
vegastack tf "<query>"returns a JSON envelope with ranked files, knowledge cards (recent-change facts), recipes (multi-provider scaffolds), and concept aliases. - An Anthropic Agent Skills Standard skill body at
skills/vegastack/SKILL.md— read this for the full agent-side mental model.
Skill router
This project ships ONE skill (vegastack) for v0.1.x. v0.2 may split it into:
tf-discover— resource/argument/import-id lookup (the heavy CLI invocation path)tf-recipes— cross-provider topology recipestf-knowledge— recent renames / deprecations / native-feature replacements
For v0.1.x, agents call vegastack tf "<query>" directly. The router pattern is documented here so v0.2's split is non-breaking: the dispatcher will live at this same router section and will only add new skill names, never rename or remove vegastack.
When to use it
Trigger on any of these:
- "create a
<resource>", "terraform for<service>", "how do I deploy X on Y" - "what arguments does
<resource>accept", "is<resource>deprecated", "import<resource>" - Multi-provider topology: zero-trust, scalable backend, GKE+Cloudflare, GitHub Actions → EKS
- Anything about recent provider changes (renames, deprecations, pricing shifts)
When in doubt, trigger. An invented resource name will fail terraform plan.
How to query
vegastack tf "<the user's natural-language Terraform request>"
The response is a single JSON envelope on stdout. Read these arrays in order:
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.
- 3d ago First seen · 115 lines · 1,746 tokens per session scan A 25f36ce0b3fb
vegastack-cli AGENTS.md is an instructions file published in the GitHub repository vegastack/vegastack-cli (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,746 tokens to every session, about $0.0087 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
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
gcnv-mcp-server AGENTS.md
Instructions for NetApp/gcnv-mcp-server, covering assistant briefing, non-negotiable code policy, session startup — ontap audit logging (must do), userintent parameter (when audit logging is enabled) and operating principles.
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.
devex AGENTS.md
Instructions for ParthKapoor-dev/devex: Summary Devex is a cloud development IDE with sandboxed “repl” sessions. The system is split into services. The core service handles auth and session orchestration, while the runner provides the interactive sandbox (WebSocket + PTY). Session data is persisted to S3-compatible…
equinix-fabric-mcp CLAUDE.md
Claude Code instructions for sliuuu/equinix-fabric-mcp, covering claude.md — equinix-fabric-mcp, canonical files, auth, add equinixclientid and equinixclientsecret and running.
Railway-mcp CLAUDE.md
Claude Code instructions for Travis-Gilbert/Railway-mcp, covering railway mcp server, quick reference, file map, architecture and key patterns.