Borrowing it
Nothing to install: this file belongs to alexei-led/spotinfo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alexei-led/spotinfo/master/CLAUDE.mdgit clone --depth 1 https://github.com/alexei-led/spotinfoWrote 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/alexei-led/spotinfo/claude-md)<a href="https://agentmods.dev/instructions/alexei-led/spotinfo/claude-md"><img src="https://agentmods.dev/badge/instructions/alexei-led/spotinfo/claude-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 5.1 | $0.11588 | $0.11588 |
| Opus 5 | $0.05794 | $0.05794 |
| Sonnet 5 | $0.02318 | $0.02318 |
| Haiku 4.5 | $0.01159 | $0.01159 |
Grade C, and why
spotinfo CLAUDE.md scanned grade C with 2 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 7d 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.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
spotinfo: failed to get spot savings: aws candidate acquisition: score enrichment failed: region us-east-1: spot placement scores unavailable: requires AWS credentials and the ec2:GetSpotPlacementScores permission: … dia Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `make check-deps` - Verify system has required dependencies (wget) How it starts
The opening of the file, as written. The whole thing — 768 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
spotinfo is a Go CLI tool and MCP server for exploring Spot machine prices across AWS, GCP
and Azure. Every cloud ships a reviewed snapshot compiled into the binary, so every cloud
answers with no credentials; each also has a live path that degrades back to the snapshot
rather than failing.
Two commands, both cloud-neutral, both served by the same provider-neutral seam
(internal/cloud).
spotinfo list— filter and show every match, with a risk column. Requires nothing and answers "what is there".spotinfo recommend— rank the top N against a stated requirement. Requires--architecture,--min-vcpuand--min-memory-gib, and answers "what should I run".
They share a vocabulary, not a purpose. Folding them would force three required flags onto a browse command.
Bare spotinfo prints help and exits 1 (no command given; run "spotinfo list" to browse or "spotinfo recommend" to rank) — except when a mode flag is set: --mcp and --version
are dispatched from the root Action and keep working. Only six flags are global: --mcp,
--debug, --quiet, --json-log, --help/-h and --version/-v. Every other flag belongs
to a subcommand and must follow it.
AWS is the only cloud that publishes a redistributable interruption figure, so GCP and Azure
report risk.status: "unavailable" — never a zero, never a low bucket — and serve only the
risk-free cost workload. GCP can fetch a per-project preemption rate with --live-risk
— see the note under Data Sources; it is visible but never filterable.
The flag vocabulary
One name per concept, decided in cmd/spotinfo/vocabulary.go and nowhere else. That file
is the single source: the flag constants, the unified defaults, the retired-name map and the
CLI-to-MCP derivation rule. cmd/spotinfo/vocabulary_test.go walks the command tree built by
newSpotinfoApp() and asserts each command declares exactly the entries marked for it, so
adding a flag anywhere else fails a test rather than shipping a second name for one idea.
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.
- 7d ago First seen · 768 lines · 11,588 tokens per session scan C a03a960f240b
spotinfo CLAUDE.md is an instructions file published in the GitHub repository alexei-led/spotinfo (163 stars, last pushed 6d ago), licensed Apache-2.0. It adds 11,588 tokens to every session, about $0.0579 per session on Opus 5. A static security scan graded it C with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.