Agent Toolkit for AWS is a collection of AWS-supported MCP servers, skills, plugins, commands, and hooks that help AI coding agents build, deploy, and manage applications on AWS. It is used by developers working with AWS services through agents such as Claude Code, Codex, Cursor, and Kiro. The catalogue entries are the toolkit's own agent extensions for AWS development and operations.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add aws/agent-toolkit-for-aws/plugin install aws-startup-advisorWrote 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/commands/aws/agent-toolkit-for-aws/usage-data)<a href="https://agentmods.dev/commands/aws/agent-toolkit-for-aws/usage-data"><img src="https://agentmods.dev/badge/commands/aws/agent-toolkit-for-aws/usage-data/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/commands/aws/agent-toolkit-for-aws/usage-data"><img src="https://agentmods.dev/badge/commands/aws/agent-toolkit-for-aws/usage-data.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 | $0.00014 | $0.00780 |
| Opus 5.5 | $0.00006 | $0.00312 |
| Sonnet 5.5 | $0.00003 | $0.00156 |
| Haiku 4.5 | $0.00001 | $0.00078 |
Grade A, and why
usage-data 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.
What it actually says
The user wants to see or change their usage-data setting for the AWS Startup Advisor plugin. They typed this themselves, so they have already asked for it. Do not argue for either answer, and do not ask them to confirm a choice they already stated in the argument.
One file decides everything: ~/.aws-startup-advisor/plugin-telemetry.json. There
is no environment variable. Opting out means setting "consentStatus" to
"OPT_OUT" in that file, which is what the notice tells the user and what the
script below does in one step — the script also keeps their install ID, so prefer
it over editing by hand.
Each block below is one command: run it whole, in a single shell invocation. The
two setup lines are repeated in every block on purpose — shell variables do not
survive between separate invocations, so a block that omitted them would run
python3 against an empty path.
${CLAUDE_PLUGIN_ROOT} has to appear as exactly that token to be substituted, so
it carries no shell default. If it does not resolve, the script path will not exist
and Python will say so: relay that and stop. Do not hunt for the files yourself and
do not hand-edit the record.
Act on $ARGUMENTS, case-insensitively, treating anything unrecognised as empty:
Empty or status
CONSENT="${CLAUDE_PLUGIN_ROOT}/scripts/telemetry/consent"
PY="$(command -v python3 || command -v python || echo 'py -3')"
$PY "$CONSENT/cli.py" status
Relay that output as-is, then mention they can pass opt-out, opt-in, or
show.
opt-out
CONSENT="${CLAUDE_PLUGIN_ROOT}/scripts/telemetry/consent"
PY="$(command -v python3 || command -v python || echo 'py -3')"
$PY "$CONSENT/opt_out.py"
No confirmation. Asking someone to confirm twice in order to decline is a dark pattern.
opt-in — show the notice first, since acknowledging it is what opting in
means:
CONSENT="${CLAUDE_PLUGIN_ROOT}/scripts/telemetry/consent"
PY="$(command -v python3 || command -v python || echo 'py -3')"
$PY "$CONSENT/cli.py" show
Reproduce that output VERBATIM: no summarizing, shortening, translating, reordering, or rewriting. It is a legal notice and the exact wording is the point. Then ask them to confirm, and only if they do:
CONSENT="${CLAUDE_PLUGIN_ROOT}/scripts/telemetry/consent"
PY="$(command -v python3 || command -v python || echo 'py -3')"
$PY "$CONSENT/accept.py"
show — print the notice, verbatim as above, and change nothing. It writes
nothing, so do not report it as having changed their setting.
Rules
- Never run
accept.pyunless the user asked to opt in or acknowledged the notice in this conversation. Printing the notice is not acknowledgement. - If a script exits non-zero, relay its stderr as-is. It says exactly what was not saved; guessing is worse.
- Opting out disables nothing. Every skill works identically either way. Say so if asked, and never imply otherwise.
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 First seen · 82 lines · 14 tokens per session scan A aef238704cd4
usage-data is a command published in the GitHub repository aws/agent-toolkit-for-aws (2,886 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 780 once invoked, about $0.0001 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 2026-10-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.