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 agentmods add skills/jpd44/mesh44-plugins/cdk-stacknpx skills add jpd44/mesh44-plugins --skill cdk-stackgit clone --depth 1 https://github.com/jpd44/mesh44-pluginsWhat 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 | $0.00044 | $0.02046 |
| Opus 5 | $0.00022 | $0.01023 |
| Sonnet 5 | $0.00009 | $0.00409 |
| Haiku 4.5 | $0.00004 | $0.00205 |
Grade A, and why
cdk-stack 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 yesterday.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/app-kit:cdk-stack — render and deploy infra
This mirrors daily-deutsch/cdk/: S3 (private, OAC) → CloudFront (apex + www, ACM, www-to-apex redirect, SPA error rewrite) → Route 53 alias records → CodeStar GitHub connection → CodeBuild test + CodeBuild build/deploy → CodePipeline V2 with Source/Test/BuildAndDeploy stages.
Inputs
From the orchestrator: app_name, aws_account_id, github_owner (defaults to github.org from config), github_branch (defaults main), domain (string OR null), and three independent toggles:
needs_cognito(bool) — adds Cognito UserPool + UserPoolClientneeds_api(bool) — adds HTTP API Gateway + JWT authorizer + sample protected Lambda. Requiresneeds_cognito=true; refuse otherwise.needs_llm_lambda(bool) — adds the daily-deutsch-style unauth'd Bedrock Lambda Function URL
If domain is null the app is served from the CloudFront default URL only (no Route 53, no ACM cert, no www→apex redirect).
Steps
1. Copy the template
Pick templates/vite/cdk/ or templates/nextjs/cdk/ based on the user's stack choice. Copy into <app-path>/cdk/. Rename lib/stack.ts to lib/<app-name>-stack.ts (the import in bin/app.ts expects this). Then walk the tree and replace placeholders:
| Placeholder | Replacement |
|---|---|
{{APP_NAME}} |
kebab-case (daily-deutsch) |
{{APP_NAME_PASCAL}} |
PascalCase (DailyDeutsch) |
{{DOMAIN}} |
apex (daily-deutsch.com) |
{{AWS_ACCOUNT_ID}} |
child account ID |
{{GITHUB_OWNER}} |
github.org from config unless overridden |
{{GITHUB_BRANCH}} |
usually main |
Strip the blocks the user didn't pick. The template has these block-pair markers in lib/<app-name>-stack.ts and bin/app.ts. Block-pair stripping = delete everything from the // BEGIN_X line through the matching // END_X line, inclusive.
| Condition | Markers to keep | Markers to strip |
|---|---|---|
domain is a string |
BEGIN_DOMAIN / END_DOMAIN |
BEGIN_NO_DOMAIN / END_NO_DOMAIN |
domain is null |
BEGIN_NO_DOMAIN / END_NO_DOMAIN |
BEGIN_DOMAIN / END_DOMAIN |
needs_llm_lambda=false |
— | BEGIN_LLM_LAMBDA / END_LLM_LAMBDA (all occurrences). Also delete lambda/llm/ directory. |
needs_cognito=false |
— | BEGIN_COGNITO / END_COGNITO (all occurrences). |
needs_api=false |
— | BEGIN_API / END_API (all occurrences). Also delete lambda/hello-protected/ directory. |
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.
- yesterday First seen · 131 lines · 44 tokens per session scan A 98344e579582
cdk-stack is a skill published in the GitHub repository jpd44/mesh44-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 2,046 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.