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 odere-pro/claude-aws-architect --skill aws-recipe-authoringgit clone --depth 1 https://github.com/odere-pro/claude-aws-architectWrote 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/odere-pro/claude-aws-architect/aws-recipe-authoring)<a href="https://agentmods.dev/skills/odere-pro/claude-aws-architect/aws-recipe-authoring"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-recipe-authoring/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/odere-pro/claude-aws-architect/aws-recipe-authoring"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-recipe-authoring.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 | $0.00073 | $0.01926 |
| Opus 5 | $0.00036 | $0.00963 |
| Sonnet 5 | $0.00015 | $0.00385 |
| Haiku 4.5 | $0.00007 | $0.00193 |
Grade A, and why
aws-recipe-authoring 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 11d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Apply this skill any time a session touches a recipe bundle — authoring a new one, modifying an existing one, or using one to scope a piece of AWS work. The skill carries the full lifecycle so a single load covers the three workflows: build, update, use.
Trigger conditions:
- A new workflow profile is needed and no existing recipe covers it (build).
- An existing recipe references a skill, MCP, hook, or command that just changed (update).
- A user wants to scope a session to one workflow and is choosing between recipes (use).
- A reviewer is checking a PR that adds or modifies
recipes/*.recipe.json(review-as-update).
Do not apply this skill for general AWS architecture work; use the workflow recipe itself (cdk, cost, security, kb, bedrock-ai) and the /aws orchestrator.
Procedure
Build a new recipe
- Scope the bundle. One workflow profile per recipe. Avoid catch-all bundles. Confirm the gap by
ls recipes/— if an existing recipe is close, prefer updating it. - Pre-flight cross-references. Every referenced artefact must already exist. Run the commands in
references/build-checklist.mdto list available MCPs (from.mcp.json), skills (fromskills/), hooks (fromhooks/hooks.json), and commands (fromcommands/). A recipe pointing at unmerged work fails review. - Write the JSON. Use
references/recipe-schema.mdas the authoritative field-by-field spec. Filename must beclaude-aws-architect-<topic>.recipe.json; the innernamefield must match the filename stem. - Add substrate defaults. Every recipe should include the substrate skills
aws-mcp-routing,aws-spec-grounding,aws-grounding-cache; the substrate hookaws-secret-scanner; and the substrate commandsaws,aws-spec. Seereferences/build-checklist.mdfor when to extend. - Validate locally. Run
bash tests/gates/gate-06-recipes.shfor shape. Cross-reference resolution is currently author discipline at v0.1.0; the deeper validation lands when the/aws-recipecommand ships. - Document. Add a playbook at
docs/playbooks/<topic>-recipe-playbook.mdwith AWS-200, AWS-300, and AWS-500 scenarios. Add a row to the reference table indocs/recipes-guide.md§6. - Commit.
feat(recipes): add claude-aws-architect-<topic> bundle. The PR description must list gate 6.
What ships with it
4 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.
- 11d ago First seen · 85 lines · 73 tokens per session scan A 033b61950f70
aws-recipe-authoring is a skill published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,926 once invoked, about $0.0004 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
deployment
Hosting, deployment, CI/CD, and going live. Activated when Claude works with deployment configs, Dockerfiles, Vercel/Netlify configs, or deployment-related commands.
ec2
AWS EC2 virtual machine management — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation. Trigger on ANY of these, even when EC2 isn't named explicitly: - Launching or provisioning: "spin up a server"…
ecs
AWS ECS container orchestration for running Docker containers. Use when deploying containerized applications, configuring task definitions, setting up services, managing clusters, or troubleshooting container issues.
cloudformation
AWS CloudFormation infrastructure as code for stack management. Use when writing templates, deploying stacks, managing drift, troubleshooting deployments, or organizing infrastructure with nested stacks.
cloudwatch
AWS CloudWatch monitoring for logs, metrics, alarms, and dashboards. Use when setting up monitoring, creating alarms, querying logs with Insights, configuring metric filters, building dashboards, or troubleshooting application issues.
eks
AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.