Borrowing it
Nothing to install: this file belongs to JadenRazo/CloudCostMCP. 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/JadenRazo/CloudCostMCP/main/AGENTS.mdgit clone --depth 1 https://github.com/JadenRazo/CloudCostMCPWrote 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/jadenrazo/cloudcostmcp/agents-md)<a href="https://agentmods.dev/instructions/jadenrazo/cloudcostmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jadenrazo/cloudcostmcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/jadenrazo/cloudcostmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jadenrazo/cloudcostmcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01131 | $0.01131 |
| Opus 5.5 | $0.00452 | $0.00452 |
| Sonnet 5.5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
CloudCostMCP 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 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.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CloudCostMCP
Help users understand multi-cloud infrastructure costs with explainable estimates,
visible assumptions and stable MCP/CLI interfaces. Estimates are not billing
guarantees. Work from the selected revision; in sparse checkouts use
git ls-tree -r --name-only HEAD and git show HEAD:<path> before declaring code
missing. Prefer current implementation, package scripts and workflows over stale
examples in contributor documentation.
Find the relevant source
| Task | Start here |
|---|---|
| IaC parsing, variables, modules | src/parsers/index.ts, format-detector.ts, the relevant parser/extractor, test/unit/parsers/, test/fixtures/ |
| Provider prices and freshness | src/pricing/pricing-engine.ts, provider adapters, src/data/loader.ts, src/data/freshness.ts, data/*-pricing/metadata.json, test/unit/pricing/, test/unit/data/ |
| Cost arithmetic and comparisons | src/calculator/, src/mapping/, src/types/pricing.ts, src/currency.ts, corresponding unit tests |
| MCP, CLI and reports | src/tools/, src/schemas/, src/server.ts, src/cli.ts, src/reporting/, VERSIONING.md |
| Pricing maintenance or release | scripts/refresh-pricing.ts, scripts/check-freshness.ts, docs/PRICING_HEALTH.md, .github/workflows/ |
Preserve meaning and contracts
- Preserve
parse_warningsand resource identity through parsing. Check variable, count/for_each and module cases when changing extraction. Keep module path containment and bounded inputs; consulttest/unit/security/for those changes. Do not describe unresolved or skipped inputs as a complete inventory. - AWS/Azure have live and fallback paths; GCP deliberately uses bundled pricing.
Preserve source, confidence, notes and freshness disclosures. Keep data vintage
(
last_updated) distinct from refresh verification (last_verified); use the shared freshness policy rather than inventing a threshold or relabeling old data as current. Unknown metadata is reported stale. - Missing pricing is not proof of zero cost. Preserve low-confidence zero-cost warnings and non-live pricing disclosures. The cost engine currently logs and drops rejected calculations: do not claim complete coverage or an existing fail-closed completeness check. For affected behavior, test missing/stale data and partial failures as well as successful lookups.
- Trace quantity × unit price through the relevant calculator. Respect hourly
versus monthly/storage units and configured monthly hours (compute defaults
to 730); a per-vCPU price is not a whole-instance price. Preserve the estimate
factory's rounding and yearly calculation. Synthetic egress remains included
in totals when enabled and disclosed through warnings/
estimated_egress_monthly. - Calculators price in USD. Currency conversion uses static rates in
src/currency.ts; retain original USD totals and exchange-rate vintage where emitted. Do not describe these rates as live FX. - Follow
VERSIONING.mdfor the stable tool names, schemas, output types, binaries and documented CLI flags. Preserve JSON text result envelopes andisErrorhandling insrc/tools/index.ts, CLI success/failure behavior, and stderr logging so MCP stdout remains JSON-RPC. Keep tools read-only with respect to user infrastructure and source files; local pricing caches exist.
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 · 85 lines · 1,131 tokens per session scan A f2586c889a0b
CloudCostMCP AGENTS.md is an instructions file published in the GitHub repository JadenRazo/CloudCostMCP (0 stars, last pushed 5d ago), licensed MIT. It adds 1,131 tokens to every session, about $0.0045 per session on Opus 5.5. 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 2026-10-10.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).