MiniStack is a local emulator of Amazon Web Services that lets software use AWS-like services on a developer's own machine instead of connecting to AWS. It supports more than 60 services and works with tools such as Terraform, AWS CLI, and SDKs, while using actual database containers for some services.
Borrowing it
Nothing to install: this file belongs to ministackorg/ministack. 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/ministackorg/ministack/main/AGENTS.mdgit clone --depth 1 https://github.com/ministackorg/ministackWrote 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/ministackorg/ministack/agents-md)<a href="https://agentmods.dev/instructions/ministackorg/ministack/agents-md"><img src="https://agentmods.dev/badge/instructions/ministackorg/ministack/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/ministackorg/ministack/agents-md"><img src="https://agentmods.dev/badge/instructions/ministackorg/ministack/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 | $0.01200 | $0.01200 |
| Opus 5.5 | $0.00480 | $0.00480 |
| Sonnet 5.5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
ministack 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 13d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in MiniStack. Read CONTRIBUTING.md
before changing a service; it has the contribution process and examples.
Where to work
ministack/app.pyowns service registration, dispatch, and reset.ministack/core/router.pydetects services;ministack/core/responses.pycontains shared response and account/region helpers.ministack/services/contains service implementations. Start with the existing service module or package and its neighboring code.tests/test_<service>.pyis the usual test location; established services may have several test files.tests/conftest.pyholds client fixtures and the_SERIAL_TESTSlist.
Before changing behavior
- New AWS services and infrastructure changes (Dockerfiles, CI workflows,
pyproject.toml, dependencies) need a scoped GitHub issue before code is written. Check for overlapping work. Follow the scope agreed in the issue. - Keep additions focused on operations needed by a real use case. Do not add speculative API coverage or operations that return placeholder results.
- Check the behavior and wire format against available evidence. Never claim behavior was validated against AWS unless it was actually run against a real AWS account. Label the evidence precisely as a real AWS observation (record region and account context when relevant), official AWS documentation, botocore service model inspection, existing tests or code, or inference; documentation, model inspection, and tests are not AWS validation. Match errors, status codes, and retry behavior.
- If AWS has one fixed behavior, implement that behavior directly rather than adding a MiniStack setting. Add configuration only for choices MiniStack itself must make.
Service contracts
- For routing and response formats, inspect the existing handler,
core/router.py, and the relevant botocore model. Some services support multiple protocols. Preserve the wire format used by the operation being changed; seeCONTRIBUTING.mdfor examples. - A new service needs an entry in
SERVICE_REGISTRYinapp.pyand the routing needed incore/router.py. Follow an established service's module layout when extending it; not every helper or submodule needs its own routing pattern. - Every registered service module, including registered submodules, must
define
get_state(),load_persisted_state(data), andreset(). The registry andtests/test_persistence.pyenforce this contract. - Keep resources isolated by account and region where AWS does. Follow the existing scoped-state helpers and check that persistence saves all tenants, not only the current request's tenant.
- Keep AWS SDK clients out of service implementations. Use them in tests or for shape inspection during development. Follow nearby code for blocking Docker calls and avoid adding service locks without checking reentrant calls.
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.
- 13d ago Changed · +10 lines · +165 tokens per session aab5456d8839
- 21d ago Changed · +7 lines · +120 tokens per session 1ece18996c30
- 1mo ago First seen · 76 lines · 915 tokens per session scan A 60dc36f04775
ministack AGENTS.md is an instructions file published in the GitHub repository ministackorg/ministack (5,106 stars, last pushed yesterday), licensed MIT. It adds 1,200 tokens to every session, about $0.0048 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 2026-09-22.
ministack AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ministack AGENTS.mdministackorg/ministack | Instructions file | 5.1k | yesterday | MIT | A | 1,200 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |