Borrowing it
Nothing to install: this file belongs to antkawam/claude-code-aws-gateway. 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/antkawam/claude-code-aws-gateway/main/CLAUDE.mdgit clone --depth 1 https://github.com/antkawam/claude-code-aws-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/antkawam/claude-code-aws-gateway/claude-md)<a href="https://agentmods.dev/instructions/antkawam/claude-code-aws-gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/antkawam/claude-code-aws-gateway/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 | $0.01612 | $0.01612 |
| Opus 5 | $0.00806 | $0.00806 |
| Sonnet 5 | $0.00322 | $0.00322 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
claude-code-aws-gateway CLAUDE.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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code AWS Gateway (CCAG)
Self-hosted API gateway that routes Claude Code through your Amazon Bedrock account. Provides a centralized layer for teams to manage API keys, budgets, rate limits, and OIDC SSO, with a built-in admin portal for observability and configuration.
Build & Test
make build # Build gateway + CLI
make test # Unit tests (no dependencies)
make lint # Format check + clippy
make test-integration # Integration tests (needs Docker)
make check # All of the above (what CI runs)
make test-e2e # E2E HTTP tests (needs AWS credentials)
make dev # Start Postgres + gateway (auto-detects free ports)
make dev-seed # Start with mock analytics data
make dev-reset # Wipe Postgres and start fresh
make dev-down # Stop local dev environment
Project Structure
src/
main.rs - Gateway entry point, startup, background loops
cli/ - CLI operations tool (ccag binary)
main.rs - CLI entry point (clap)
config.rs - Admin API client, token management
commands/ - Subcommands: config, keys, users, teams, scim, status, logs
api/
mod.rs - Router, auth endpoints, setup script serving
handlers.rs - HTTP handlers (messages, count_tokens, health)
admin.rs - Admin API (keys, teams, users, spend, IDPs, endpoints, analytics)
cli_auth.rs - Browser-based OIDC login flow
proxy_login.sh - apiKeyHelper script (embedded at compile time)
config/mod.rs - GatewayConfig, routing prefix auto-detection
proxy/mod.rs - GatewayState (shared state)
auth/
mod.rs - In-memory key cache, key validation
oidc.rs - Multi-IDP OIDC JWT validation, JWKS caching
session.rs - HS256 session token signing/validation
ratelimit/mod.rs - Per-key sliding window rate limiter
db/ - Postgres pool, migrations, CRUD
org_analytics.rs - Cross-org analytics queries (~20 functions)
spend/mod.rs - Async spend tracker (buffer + flush)
budget/ - Budget enforcement and notifications
endpoint/ - Multi-endpoint pool and routing
stats.rs - Per-endpoint rolling-window throttle/error/request counters
telemetry/mod.rs - Prometheus metrics, OTLP export
translate/
models.rs - Model ID mapping (Anthropic <-> Bedrock)
request.rs - Request translation
response.rs - Response normalization
streaming.rs - SSE event formatting
scim/ - SCIM 2.0 provisioning (auth, discovery, users, groups, filter, types)
websearch/mod.rs - DuckDuckGo web search interception
static/index.html - Embedded admin portal SPA (dashboard, analytics, config)
infra/ - AWS CDK (TypeScript) for ECS Fargate + RDS + CW Dashboard
migrations/ - Postgres schema migrations (auto-run on startup)
docs/
configuration.md - Environment variables, runtime settings
metrics.md - Metric reference, Prometheus/OTLP config, Grafana examples
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 · 110 lines · 1,612 tokens per session scan A fc715cbc9240
claude-code-aws-gateway CLAUDE.md is an instructions file published in the GitHub repository antkawam/claude-code-aws-gateway (22 stars, last pushed 6d ago), licensed MIT. It adds 1,612 tokens to every session, about $0.0081 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 2026-08-30.
Other instructions, from other repositories
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).
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.
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).
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.