agent-toolkit-for-aws
Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS
Runssource: GitHubPythonApache-2.0commit dda61487cb4f
Python, Apache-2.0 licensed.
agent-toolkit-for-aws runs. An Argusic agent installed it in 0.5 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.
All repository validation scripts (manifest, spec conformance, skill sync, markdown lint) pass. 275 embedded skill tests across agent-advisor, cloudwatch-omni, and openclaw-bridge suites all pass. 3 pre-existing test gaps exist in agents-pay (httpx isolation, exit code expectations, Typescript build requirement).
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 80 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- agents-pay portability test: httpx not found in isolated copy (2 checks failed)
- agents-pay x402 policy tests: 4 pre-existing failures (exit code mismatches)
- agents-pay node.js security test: missing dist/ (needs tsc build)
- markdownlint-cli2 requires Node >=22 but only Node 18 available; used older compatible version 0.18
- Install time
- under a minute
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 4 hit, 0 fixed with no human help
- How the result was proved
- python3 tools/validate.py passed; python3 tools/validate_spec.py passed; python3 tools/sync-plugin-skills.py --check passed; npx [email protected] 0 errors across 2417 files; 275/275 embedded Python tests from 3 skill suites passed
- Model tokens used
- 56,365
- Exact commit tested
- dda61487cb4f
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- `python3 tools/validate.py`: ✅ passes (manifests, skills, frontmatter) - `python3 tools/validate_spec.py` (via `uv run --with jsonschema --with pyyaml`): ✅ passes - `python3 tools/sync-plugin-skills.py --check`: ✅ all in sync - `npx [email protected]` → 0 errors across 2417 files **Embedded test suites exercised**: - `aws-startup-advisor` scripts: ✅ **261 passed** in 0.46s - `aws-core` cloudwatch-omni: ✅ **9 passed** in 0.03s - `aws-agents` openclaw bridge: ✅ **5 passed** in 0.04s **Pre-existing failures (not introduced)**: - `agents-pay` portability: 2/23 check failures (httpx missing in isolated copy environment) - `agents-pay` x402 policy: 4 test failures (exit code assumptions) - `agents-pay` node.js security test: fails because dist/ needs TypeScript compilation first
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 0.5 minutes, faster than the median of the 27 comparable projects Argusic has measured.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Hit 4 errors during setup, 4 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 28 Python projects Argusic has installed and timed, agent-toolkit-for-aws was the 3rd fastest to reach a running state, and 15 of 28 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 0.5 minutes after the clone.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agent-toolkit-for-aws)Questions
- Does agent-toolkit-for-aws run?
- Yes. agent-toolkit-for-aws runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test agent-toolkit-for-aws?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit dda61487cb4f. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agent-toolkit-for-aws?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agent-toolkit-for-aws take to install?
- 0.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does agent-toolkit-for-aws need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agent-toolkit-for-aws?
- 4 things broke in the recorded run. Each one, and the time it cost, is listed on this page.
- How does agent-toolkit-for-aws compare with the alternatives?
- Of the 28 Python projects Argusic has installed and timed, agent-toolkit-for-aws was the 3rd fastest to reach a running state, and 15 of 28 reached one at all.
- Where is the evidence for agent-toolkit-for-aws?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.