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 rjpruitt16/aquifer --skill aquifer-pilotgit clone --depth 1 https://github.com/rjpruitt16/aquiferWrote 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/rjpruitt16/aquifer/aquifer-pilot)<a href="https://agentmods.dev/skills/rjpruitt16/aquifer/aquifer-pilot"><img src="https://agentmods.dev/badge/skills/rjpruitt16/aquifer/aquifer-pilot/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/rjpruitt16/aquifer/aquifer-pilot"><img src="https://agentmods.dev/badge/skills/rjpruitt16/aquifer/aquifer-pilot.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 | $0.00069 | $0.03794 |
| Opus 5.5 | $0.00028 | $0.01518 |
| Sonnet 5.5 | $0.00014 | $0.00759 |
| Haiku 4.5 | $0.00007 | $0.00379 |
Grade A, and why
aquifer-pilot 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 3d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aquifer pilot
You're helping someone find out, with their own numbers, whether Aquifer helps their workload. Keep it simple:
- a branch, not a migration;
- a replica, staging or a shadow copy, never production;
- a few hours to a day of real-shaped traffic;
- a write-up they can share.
Start: how involved does your user want to be?
Ask first: "Do you want to be part of this, or should I go off, do the whole pilot, and come back with the results?" Most people want the second. Make that easy.
Either way, get these answers in one message before you start. They're the only things you can't safely decide alone:
- Where it's safe to run: the replica, staging or shadow copy you may send traffic to. Name what is production and off-limits.
- The budget: how long you may run (a few hours to a day) and what you may spend on machines, or "local only".
- The traffic: recorded traffic you may replay, or a description to model (rates, burst sizes, number of tenants).
- Permission to deploy: whether you may start Aquifer and a load generator on that infrastructure.
Then work in the mode they chose:
- Hands-off (the default): do steps 1–6 without asking again. When a choice is yours to make, pick the sensible default and write it down in the report's config section. Interrupt only to stop something unsafe: you're about to touch production, exceed the budget, or a pass looks like it's harming the replica. Come back with the report and the raw data behind it.
- Hands-on: show the plan after the fit check, and check in after the benchmark and after each pass.
If you can't find something you need (a missing metric, a backend you can't instrument), work around it and say how in the report. Stop and ask only if there's no workaround.
What Aquifer is (and isn't)
Aquifer is admission control for soft real-time work, and for webhook and WebSocket overload. It accepts a burst, persists it, and releases it at the pace the backend can take. The backend sets that pace through X-Aqueduct-* response headers. Tenants get their own queues, so one tenant's burst doesn't starve the others.
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.
- 3d ago First seen · 212 lines · 69 tokens per session scan A 2ae3daa7d493
aquifer-pilot is a skill published in the GitHub repository rjpruitt16/aquifer (15 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 3,794 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 2026-10-19.
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 security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
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 generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
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…
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".