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-sdlc-workflowgit 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-sdlc-workflow)<a href="https://agentmods.dev/skills/odere-pro/claude-aws-architect/aws-sdlc-workflow"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-sdlc-workflow/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-sdlc-workflow"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-sdlc-workflow.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 | $0.00059 | $0.01495 |
| Opus 5 | $0.00030 | $0.00747 |
| Sonnet 5 | $0.00012 | $0.00299 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
aws-sdlc-workflow 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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Apply this skill at the orchestrator's entry point for every user prompt that may produce SDLC artefacts (requirements.md, design.md, tasks.md, component contracts, diagrams). The orchestrator agent is the sole consumer; L3 specialists do not invoke this skill — they are the targets of the fan-out it defines. Do not apply this skill to non-AWS prompts or to interactive clarification turns that don't produce artefacts.
Trigger conditions:
- The user has just sent a prompt and the orchestrator must decide depth (shallow vs full).
- The orchestrator is about to fan out L3 specialists and needs to know which to invoke and in what message.
- Multiple specialists have returned and the orchestrator must merge their outputs into a single response.
- A specialist disagreement surfaced during merge and the orchestrator must apply the priority rules.
- A mid-turn user clarification has shifted the prompt's classification and the orchestrator must re-evaluate depth.
Procedure
- Classify the prompt depth. Apply the escalation heuristic in
references/phases.mdin the listed order: explicit override → SDLC-artefact intent → verb-of-creation → verb-of-inquiry → default. The heuristic is content-classified, not length-classified; a one-line prompt naming "design" still escalates to full depth. - Pick the phase. Vibe (sub-second routing), discovery (
requirements.md), design (design.md+ contracts + diagrams), plan (tasks.md), validate (lint passes). At v0.1.0 each phase invokes exactly one specialist; the single-message multi-Agent-call rule (step 3 below) is in place and becomes load-bearing when v0.2 splits the implementation specialist into three. - Fan out specialists in parallel. When depth is full, invoke all eligible specialists in a single message with multiple
Agenttool calls. Sequential specialist invocations are a defect — they defeat the fan-out budget and slow the user-visible response. Detail inreferences/parallel-fanout.md. - Merge specialist outputs. Apply the conflict-resolution priority rules in order: security correctness → factual correctness → cost ceiling → architecture convergence → recency. Detail in
references/merge-rules.md. - Surface unresolved conflicts. Disagreements that the priority rules cannot resolve appear in the merged response under
## Open Questions. The orchestrator does not silently pick a side; the user resolves. - Log every conflict resolution. Every conflict, resolved or not, becomes a
conflict_resolutionentry in the grounding ledger. The format is owned byaws-grounding-cache; this skill provides the content (which specialists, which options, which rule fired).
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.
- 9d ago First seen · 61 lines · 59 tokens per session scan A 0cd25ca4213b
aws-sdlc-workflow is a skill published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,495 once invoked, about $0.0003 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"…
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.
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.
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.