Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add seandkendall/kiro-config --skill reinvent-stack-toolkitgit clone --depth 1 https://github.com/seandkendall/kiro-configWrote 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/skills/seandkendall/kiro-config/reinvent-stack-toolkit)<a href="https://agentmods.dev/skills/seandkendall/kiro-config/reinvent-stack-toolkit"><img src="https://agentmods.dev/badge/skills/seandkendall/kiro-config/reinvent-stack-toolkit/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/skills/seandkendall/kiro-config/reinvent-stack-toolkit"><img src="https://agentmods.dev/badge/skills/seandkendall/kiro-config/reinvent-stack-toolkit.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 | $0.00077 | $0.01090 |
| Opus 5.5 | $0.00031 | $0.00436 |
| Sonnet 5.5 | $0.00015 | $0.00218 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
reinvent-stack-toolkit 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 8d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reinvent Stack Toolkit
Trust policy: every ARN, model ID, and pattern below was verified against this
account's real infrastructure as of the verified date above. Treat them as correct
without re-querying live AWS for roughly 90 days from that date. Only re-verify a
specific value live if it actually fails at build or deploy time (a stale ARN, a
rejected model ID, a changed API shape). If something here turns out stale, fix it here
and bump the date, so the next build doesn't re-pay the same research cost.
Observability is not covered here. The build prompt specifies it per project.
Verified ARNs & versions (quick reference)
Pinned values confirmed against live AWS docs/account state as of the verified date
above. Use these directly without re-querying; only re-verify if one fails at build or
deploy time, per the trust policy.
| Value | Pinned | Scope / caveat |
|---|---|---|
| ADOT Lambda layer for Python | arn:aws:lambda:<region>:901920570463:layer:aws-otel-python-<arch>-ver-1-32-0:7 (<arch> = amd64 or arm64) |
Python 3.8-3.13 only. This stack's Lambdas run python3.14 -- the layer is NOT compatible, confirmed by live failure (No module named 'aws_xray_sdk' at cold start). Keep this ARN on file for the day this stack's Python version drops to 3.13 or earlier, or for a sibling project pinned to an older runtime. For python3.14 today, skip ADOT entirely -- see references/pitfalls.md item 4 for the Powertools+aws-xray-sdk alternative this stack actually uses. |
amazon.nova-lite-v1:0 |
bare model ID (no inference profile needed) | Confirmed invokable on-demand directly via Converse in this account/region (us-east-1) as of 2026-07-14. Correction: amazon.nova-lite-v2:0 does not exist in this account/region and fails Converse with ValidationException: The provided model identifier is invalid. The newer amazon.nova-2-lite-v1:0 exists but is INFERENCE_PROFILE-only (needs us.amazon.nova-2-lite-v1:0 or global.amazon.nova-2-lite-v1:0) -- amazon.nova-lite-v1:0 is the correct bare on-demand ID. If a ValidationException about invalid model identifier appears again, re-run aws bedrock list-foundation-models --query "modelSummaries[?contains(modelId,'nova')].modelId" before trusting any pinned Nova ID here. |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago Changed ab2119ac55bb
- 13d ago First seen · 60 lines · 77 tokens per session scan A 5a80667e2d7e
reinvent-stack-toolkit is a skill published in the GitHub repository seandkendall/kiro-config (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,090 once invoked, about $0.0003 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 skills, from other repositories
aws-cdk
AWS CDK infrastructure development in TypeScript. Use when creating stacks, constructs, L2/L3 patterns, CDK testing, synth/deploy pipelines or organizing IaC code.
aws-serverless
Building production-ready serverless applications on AWS. Use when working with Lambda, API Gateway, SQS, SNS, DynamoDB Streams, SAM/CDK deployment or optimizing cold starts.
aws-terraform
AWS infrastructure with Terraform. Use when creating modules, managing remote state, writing tftest.hcl tests, refactoring IaC or following HashiCorp style guide.
aws-lambda-python
AWS Lambda development with Python. Use when writing Lambda handlers, packaging with layers, using boto3/Powertools, structured logging or optimizing Python Lambda performance.
aws-api
AWS API design, implementation and integration patterns. Use when creating or modifying API Gateway endpoints, OpenAPI contracts, authentication, error handling or event integrations.
aws-architecture
AWS architecture decisions, serverless patterns, event-driven design, service boundaries and Well-Architected Framework. Use when designing system architecture or making infrastructure tradeoffs.