Borrowing it
Nothing to install: this file belongs to 0hardik1/awsmux. 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/0hardik1/awsmux/main/AGENTS.mdgit clone --depth 1 https://github.com/0hardik1/awsmuxWrote 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/0hardik1/awsmux/agents-md)<a href="https://agentmods.dev/instructions/0hardik1/awsmux/agents-md"><img src="https://agentmods.dev/badge/instructions/0hardik1/awsmux/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 5.1 | $0.02647 | $0.02647 |
| Opus 5 | $0.01324 | $0.01324 |
| Sonnet 5 | $0.00529 | $0.00529 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
awsmux 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 6d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and new humans) working on this codebase.
What awsmux is
awsmux runs one AWS CLI command across a whole fleet of accounts/regions,
safely. It discovers profiles from the AWS shared config and credentials
files, verifies every target identity with STS before anything runs,
classifies each operation by risk, gates anything non-read-only behind an
immutable plan + human approval token, fans out with a worker pool, and
persists every run to a replayable history. Agents consume it over MCP (awsmux mcp); humans use the CLI.
Single Go module (github.com/0hardik1/awsmux, so go install works
against the public repo), Go 1.26. Dependencies: stdlib plus cobra,
nothing else — this is a deliberate design rule, not an accident. Do not
add dependencies (the MCP layer is hand-rolled JSON-RPC on purpose, and the
AWS shared-config INI parsing is hand-rolled on purpose).
Build, test, verify
go build ./... && go vet ./... && go test ./...
Run that before every commit, or use the make equivalents: make build
(binary at ./bin/awsmux), make test, make vet, make check-fmt, and
make lint (golangci-lint, version pinned in the Makefile). make setup
installs the git hooks and pre-warms the lint tool. Tests live next to the
code (internal/core/*_test.go, internal/mcpserver/*_test.go); they are
plain stdlib testing, no test frameworks, and need neither network nor
Docker.
To try the whole thing end to end with zero credentials and zero real AWS (needs Docker and the aws CLI):
make fleet-up # LocalStack + a 101-profile test fleet
source .tmp/fleet/env.sh && ./bin/awsmux targets
make e2e # build + fleet-up + smoke test
make fleet-down # remove the LocalStack container
Layout
main.go thin entry: os.Exit(cmd.Execute())
cmd/ cobra CLI layer, one file per command
root.go root command, ExitError, shared selector/exec flags
run.go plan.go approve.go apply.go the plan/approve/apply workflow
targets.go history.go replay.go discovery + history + replay
doctor.go `awsmux doctor` environment diagnostic
mcp.go `awsmux mcp` -> internal/mcpserver.Serve
interactive.go TTY checkbox target picker + typed confirmations
internal/core/ THE ENGINE - everything meaningful lives here
types.go all shared types + stable exit codes
discovery.go config + credentials INI parsing/merge, glob selectors
identity.go STS preflight, 5m cache, dedup, re-verification
classify.go verb -> risk class tables + service overrides
plan.go immutable plans, sha256 hash, ULID-style IDs
policy.go approval tokens, CheckApproval gate
executor.go worker pool, failure taxonomy, arg validation
store.go ~/.awsmux persistence (plans/, executions/, index.jsonl)
awscmd.go aws CLI invocation: AWSMUX_AWS_BIN override,
then PATH, then well-known install locations
doctor.go environment diagnostic behind `awsmux doctor`
internal/mcpserver/ MCP stdio server: 5 tools, hand-rolled JSON-RPC 2.0
server.go tools.go framing + tool schemas/handlers
results.go token-economy result shaping (grouping, paging)
registry.go in-flight async execution registry
internal/output/ table | json | jsonl rendering (jsonl = agent/CI contract)
scripts/fleet/ LocalStack test-fleet provisioner (stdlib-only dev tool)
scripts/e2e.sh smoke test run by `make e2e` and the CI e2e job
Makefile build/test/lint/fleet-up/e2e/hooks targets
.githooks/ pre-commit (fmt, vet, lint) + commit-msg (Conventional Commits)
.github/ CI workflow + dependabot
docs/ARCHITECTURE.md design decisions, plan-boundary sequence, test-fleet internals
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.
- 6d ago First seen · 196 lines · 2,647 tokens per session scan A 5b102dda434e
awsmux AGENTS.md is an instructions file published in the GitHub repository 0hardik1/awsmux (28 stars, last pushed 29d ago), licensed Apache-2.0. It adds 2,647 tokens to every session, about $0.0132 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
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.