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/rafaself/aws-mcp-gateway/agents-mdgit clone --depth 1 https://github.com/rafaself/aws-mcp-gatewayWrote 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/rafaself/aws-mcp-gateway/agents-md)<a href="https://agentmods.dev/instructions/rafaself/aws-mcp-gateway/agents-md"><img src="https://agentmods.dev/badge/instructions/rafaself/aws-mcp-gateway/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 | $0.01400 | $0.01400 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
aws-mcp-gateway 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 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository purpose
A minimal Cloudflare Worker MCP gateway for explicit, read-only AWS tools.
Hard boundaries:
- No generic AWS CLI execution tool.
- No arbitrary AWS API proxy.
- No AWS write/management operations in the current read-only scope.
- No secrets, local env files, tokens, credentials, or generated Wrangler state committed.
Workflow
- Work from the related GitHub issue when available.
- Keep PRs small and focused on the issue scope.
- Prefer TDD when practical: write a failing test first, implement the smallest safe change, then refactor.
- For non-trivial work, use the issue or spec as source of truth.
- Do not expand scope beyond the issue without documenting why.
- When blocked, leave a clear note with what was tried and what remains.
Development commands
pnpm install
pnpm run typecheck
pnpm test
pnpm run test:coverage
pnpm dev
Minimal local loop during development: typecheck, test, test:integrity.
Full pre-PR validation before opening a pull request: see README.md#testing (repo:safety, output:guardrail, verify:connector-contract, typecheck, test, test:integrity). CI also runs Gitleaks via .github/workflows/secret-scan.yml.
pnpm run typecheckis required before finishing any code changes.pnpm testis required when code or behavior changes.pnpm run test:coverageis recommended before larger PRs but not mandatory for trivial or docs-only changes.
Code organization
Source layout:
src/auth/ bearer auth and OAuth validation
src/auth/oauth/
src/aws/ AWS request client and service-specific clients
src/aws/cost-explorer/
src/aws/ec2/
src/aws/cloudwatch/
src/aws/lambda/
src/aws/logs/
src/aws/s3/
src/cache/ cache helpers
src/config/ env validation and gateway context
src/errors/ error classes and handling
src/mcp/ MCP server and tool registration
src/mcp/audit/ MCP tool audit payload builders
src/mcp/chatgpt/ ChatGPT catalog adapter
src/mcp/tools/definitions/ tool manifest factories
src/observability/ centralized runtime output sinks
src/security/ limits, dates, region validation, redaction helpers
src/test/ shared test setup and fixtures
infra/aws/ checked-in IAM policy template
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 · 149 lines · 1,400 tokens per session scan A cf902711bce8
aws-mcp-gateway AGENTS.md is an instructions file published in the GitHub repository rafaself/aws-mcp-gateway (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,400 tokens to every session, about $0.0070 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
aks-mcp copilot-instructions.md
Copilot instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.
microfeed AGENTS.md
AGENTS.md instructions for microfeed/microfeed, covering repository guidance, development workflow, instance management and cloudflare deployment, source architecture and theme repositories.
ebay-mcp AGENTS.md
Instructions for YosefHayim/ebay-mcp, covering agents.md, what this is, instruction sources, validation commands and module map (src/).
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.
flaim AGENTS.md
AGENTS.md instructions for jdguggs10/flaim, covering repo agent guide, scope, public/private boundary, important distinction: product assets vs repo instructions and start here.
mcp-migration-check AGENTS.md
AGENTS.md instructions for AlpayC/mcp-migration-check, covering working in this repository, shape, rules that are not negotiable, before you say it works and adding a rule.