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 magnus919/agent-skills --skill capacity-and-cost-engineeringgit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/capacity-and-cost-engineering)<a href="https://agentmods.dev/skills/magnus919/agent-skills/capacity-and-cost-engineering"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/capacity-and-cost-engineering/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/magnus919/agent-skills/capacity-and-cost-engineering"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/capacity-and-cost-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00168 | $0.03879 |
| Opus 5.5 | $0.00067 | $0.01552 |
| Sonnet 5.5 | $0.00034 | $0.00776 |
| Haiku 4.5 | $0.00017 | $0.00388 |
Grade A, and why
capacity-and-cost-engineering 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 1mo 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capacity and Cost Engineering
Connect demand, performance, reliability, and spend into defensible capacity and cost decisions. This skill models technical capacity, calculates unit cost at the infrastructure level, defines budget and quota controls, requires load/soak evidence for capacity claims, and makes cost-performance tradeoffs explicit — producing evidence that feeds production-readiness launch decisions and constrains or supports site-reliability-engineering SLO choices.
Connected dimensions
Demand (traffic and growth), performance (latency and throughput), reliability (SLOs and error budgets), and spend (cost) are treated as connected dimensions — a change in any one dimension affects the others. The skill's core method is tracing the connection:
| Dimension | Capacity impact | Cost impact |
|---|---|---|
| Demand (traffic, growth rate) | Drives compute, storage, network requirements | Drives baseline and projected spend |
| Performance (latency, throughput target) | Constrains resource headroom per request | Tighter targets increase unit cost |
| Reliability (SLO, error budget) | Requires redundancy, over-provisioning, or isolation | Higher SLOs increase cost non-linearly |
| Spend (budget, cost constraint) | Caps capacity; may force degraded-mode operation | Limits what SLO/performance targets are achievable |
A capacity decision that changes one dimension without modeling the others is incomplete. Every capacity model, unit-cost calculation, and budget decision in this skill must name at least one connection to another dimension with evidence or an explicit assumption.
Loading Guide
Load this skill when the task involves any of:
| Trigger | What to load |
|---|---|
| Project capacity from a growth forecast | SKILL.md + templates/capacity-model.md |
| Size capacity for a peak event (launch, Black Friday, seasonal) | SKILL.md + templates/capacity-model.md + templates/load-soak-test-plan.md |
| Calculate unit cost and connect to SLO or demand decisions | SKILL.md + templates/unit-economics-record.md |
| Define a budget threshold, spending alert, or hard cap | SKILL.md + templates/budget-quota-decision.md |
| Design quota or rate-limit enforcement in operational context | SKILL.md + templates/budget-quota-decision.md |
| Plan or review a load/soak test as capacity evidence | SKILL.md + templates/load-soak-test-plan.md |
| Resolve an SLO-cost tradeoff or cost-constrained reliability decision | SKILL.md + templates/slo-cost-tradeoff-record.md |
| Review a cost anomaly or attribute cost to services/teams | SKILL.md + templates/unit-economics-record.md |
| Model multi-tenant demand, skew, fairness, or tenant-variable unit cost | SKILL.md + references/multi-tenant-capacity-and-unit-cost.md + templates/tenant-capacity-model.md |
| Understand ownership boundaries with adjacent skills | SKILL.md + references/discovery-brief.md |
What ships with it
11 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.
- evals/evals.json 23 KB
- README.md 5.1 KB
- references/discovery-brief.md 14 KB
- references/multi-tenant-capacity-and-unit-cost.md 7.4 KB
- references/source-index.md 2.2 KB
- templates/budget-quota-decision.md 4.0 KB
- templates/capacity-model.md 3.9 KB
- templates/load-soak-test-plan.md 4.5 KB
- templates/slo-cost-tradeoff-record.md 4.2 KB
- templates/tenant-capacity-model.md 5.1 KB
- templates/unit-economics-record.md 3.6 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.
- 1mo ago First seen · 220 lines · 168 tokens per session scan A 1e75e1c3694c
capacity-and-cost-engineering is a skill published in the GitHub repository magnus919/agent-skills (154 stars, last pushed today), licensed MIT. It adds 168 tokens to every session and 3,879 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
routine
Manage CocoRoutine Snowflake task scheduling. Usage: $routine list, $routine schedule --cadence , $routine disable , $routine delete .
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
lambdasim
Run the studio's per-project NLP Lambda path locally with lambdasim, haven's AWS Lambda stand-in: functions, invokes and response streams answered on this stack's nlpgo. Use when someone says 'haven lambda', 'lambdasim', 'haven up +lambda', 'haven sim lambda', 'NLP Lambda locally', 'per-project Lambda'…
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
remote-compute-modal
Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.