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/marcelobrake/aws-mcp/agents-mdgit clone --depth 1 https://github.com/marcelobrake/aws-mcpWhat 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 | $0.00297 | $0.00297 |
| Opus 5 | $0.00148 | $0.00148 |
| Sonnet 5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
aws-mcp 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 yesterday.
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.
What it actually says
AGENTS.md
Purpose
This repository exposes AWS data and control-plane actions to MCP clients. Treat every change as security-sensitive.
Development Rules
- Default to readonly behavior. Any new mutating capability must require explicit opt-in and document the blast radius.
- Never return plaintext secrets, decrypted SecureString values, or KMS plaintext without going through aws_mcp/sensitive_guard.py.
- When adding a new AWS escape hatch or a new tool that can reveal sensitive material, update both the tool schema and the generic aws_execute sensitive-operation map.
- Do not log request payloads, approval tokens, secret identifiers with values, or decrypted content.
- Keep telemetry opt-in only. Do not add fallback exporters that emit spans to stdout or stderr by default.
Local Workflow
- Run setup.sh in development clones so the repository installs hooks and local tooling.
- Before pushing, the repository pre-push hook runs scripts/security_scan.sh.
- If a scan tool is missing, install it instead of bypassing the hook.
Sensitive Access Policy
- Secrets Manager secret values require extra authentication.
- SSM SecureString reads with decryption require extra authentication.
- KMS operations that can reveal plaintext must use the same extra-auth path if added later.
Expected Validation
- Python syntax must stay valid.
- Security hooks must remain executable.
- README and example configuration must document any new security control.
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.
- yesterday First seen · 32 lines · 297 tokens per session scan A 569a438de176
aws-mcp AGENTS.md is an instructions file published in the GitHub repository marcelobrake/aws-mcp (0 stars, last pushed 5mo ago), licensed BSD-3-Clause. It adds 297 tokens to every session, about $0.0015 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
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.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.