AWS Startups is an official AWS repository containing plugins, skills, tools, and other resources for people building startup products on Amazon Web Services. Its add-ons support startup-focused architecture, migration, and development work on AWS.
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 awslabs/startups --skill gcp-to-awsgit clone --depth 1 https://github.com/awslabs/startupsWrote 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/awslabs/startups/gcp-to-aws)<a href="https://agentmods.dev/skills/awslabs/startups/gcp-to-aws"><img src="https://agentmods.dev/badge/skills/awslabs/startups/gcp-to-aws/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/awslabs/startups/gcp-to-aws"><img src="https://agentmods.dev/badge/skills/awslabs/startups/gcp-to-aws.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 60 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 37 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 39 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 40 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 41 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 42 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 44 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 45 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 46 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 47 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 91 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 93 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 94 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 95 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 96 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 98 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 101 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 102 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 37 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 39 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 40 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00320 | $0.09208 |
| Opus 5 | $0.00160 | $0.04604 |
| Sonnet 5 | $0.00064 | $0.01842 |
| Haiku 4.5 | $0.00032 | $0.00921 |
Grade A, and why
gcp-to-aws 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 10d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GCP-to-AWS Migration Skill
Philosophy
- Re-platform by default: Select AWS services that match GCP workload types (e.g., Cloud Run → Fargate, Cloud SQL → RDS).
- Extract before ask: When Terraform, billing, or app code already answers a Clarify question, resolve it with
chosen_by: "extracted"and present it on the Assumption Sheet for confirmation — never re-ask it as a full question unless the user converts it ("ask me about X") or corrects it. - Dev sizing unless specified: Default to development-tier capacity (e.g., db.t4g.micro, single AZ). Upgrade only on user direction.
- No human one-time migration costs: Do not present human labor, professional services, or people-time work as dollar estimates or "one-time migration cost" budget categories. Vendor charges grounded in data (for example GCP data transfer egress in the infra estimate when billing exists) are allowed.
- Multi-signal approach: Design phase adapts based on available inputs — live gcloud discovery and/or Terraform IaC for infrastructure, billing data for service mapping, and app code for AI workload detection. When live and IaC both run, live is authoritative for current state and disagreements surface as drift, never silently resolved.
- BigQuery /
google_bigquery_*: The skill does not recommend a specific AWS analytics or warehouse service. During Clarify, if discovery shows BigQuery (IaCgoogle_bigquery_*and/or billing rows for BigQuery), you must surface the specialist advisory before Design (seereferences/phases/clarify/clarify.md). Design output usesDeferred — specialist engagement; keep directing the user to their AWS account team and/or a data analytics migration partner through Design, Estimate, and docs (seereferences/phases/design/design-infra.mdBigQuery specialist gate).
Definitions
- "Load" = Read the file using the Read tool and follow its instructions. Do not summarize or skip sections.
$MIGRATION_DIR= The run-specific directory under.migration/(e.g.,.migration/0226-1430/). Set during Phase 1 (Discover).
What ships with it
60 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.
- data/sdk-capability-map.json 1.5 KB
- references/clustering/terraform/classification-rules.md 7.4 KB
- references/clustering/terraform/clustering-algorithm.md 7.9 KB
- references/clustering/terraform/depth-calculation.md 4.5 KB
- references/clustering/terraform/typed-edges-strategy.md 4.6 KB
- references/design-refs/ai-anthropic-to-bedrock.md 3.6 KB
- references/design-refs/ai-gemini-to-bedrock.md 20 KB
- references/design-refs/ai-openai-to-bedrock.md 25 KB
- references/design-refs/ai.md 4.8 KB
- references/design-refs/compute.md 14 KB
- references/design-refs/database.md 9.1 KB
- references/design-refs/design-ref-agentic-to-agentcore.md 19 KB
- references/design-refs/design-ref-harness.md 8.3 KB
- references/design-refs/elastic-beanstalk.md 20 KB
- references/design-refs/fast-path.md 23 KB
- references/design-refs/index.md 6.8 KB
- references/design-refs/messaging.md 3.5 KB
- references/design-refs/networking.md 5.5 KB
- references/design-refs/security.md 4.0 KB
- references/design-refs/storage.md 4.7 KB
- references/phases/clarify/clarify-ai-only.md 31 KB
- references/phases/clarify/clarify-ai.md 62 KB
- references/phases/clarify/clarify-compute.md 18 KB
- references/phases/clarify/clarify-database.md 12 KB
- references/phases/clarify/clarify-global.md 25 KB
- references/phases/clarify/clarify.md 94 KB
- references/phases/design/design-ai.md 45 KB
- references/phases/design/design-billing.md 13 KB
- references/phases/design/design-infra.md 19 KB
- references/phases/design/design.md 6.8 KB
- references/phases/discover/discover-app-code.md 43 KB
- references/phases/discover/discover-billing.md 7.3 KB
- references/phases/discover/discover-iac.md 35 KB
- references/phases/discover/discover-live.md 39 KB
- references/phases/discover/discover-openai-api.md 20 KB
- references/phases/discover/discover-preview.md 23 KB
- references/phases/discover/discover.md 17 KB
- references/phases/estimate/estimate-ai.md 22 KB
- references/phases/estimate/estimate-billing.md 13 KB
- references/phases/estimate/estimate-infra.md 78 KB
- references/phases/estimate/estimate.md 13 KB
- references/phases/feedback/feedback-trace.md 4.7 KB
- references/phases/feedback/feedback.md 5.1 KB
- references/phases/generate/generate-ai.md 18 KB
- references/phases/generate/generate-artifacts-ai.md 35 KB
- references/phases/generate/generate-artifacts-billing.md 6.1 KB
- references/phases/generate/generate-artifacts-docs.md 27 KB
- references/phases/generate/generate-artifacts-infra.md 59 KB
- references/phases/generate/generate-artifacts-report.md 56 KB
- references/phases/generate/generate-artifacts-scripts.md 24 KB
- references/phases/generate/generate-billing.md 17 KB
- references/phases/generate/generate-infra.md 23 KB
- references/phases/generate/generate.md 9.3 KB
- references/phases/workshop/workshop-assemble.md 1.3 KB
- references/phases/workshop/workshop-compare.md 1.6 KB
- references/phases/workshop/workshop-refresh.md 3.7 KB
- references/phases/workshop/workshop-sheet.md 3.3 KB
- references/phases/workshop/workshop.md 3.1 KB
- references/shared/ai-migration-guardrails.md 9.6 KB
- references/shared/ai-model-lifecycle.md 11 KB
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.
- 10d ago First seen · 421 lines · 320 tokens per session scan A a9d6d82327e6
gcp-to-aws is a skill published in the GitHub repository awslabs/startups (17 stars, last pushed today), licensed Apache-2.0. It adds 320 tokens to every session and 9,208 once invoked, about $0.0016 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 skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…