Lobstack- Observability
Audit a codebase for unmetered model calls
Find model calls that bypass the gateway and therefore appear on no bill anyone reads, and detect the opposite fault of counting one call twice.
SKILL.md · MIT - Observability
Report spend from the usage API
Answer what an organisation spent, on which models and keys, and what failed, from the Lobstack usage API rather than by estimating.
SKILL.md · MIT
The rest of the developer skills.
- Cost
Read a Lobstack receipt
Read the receipt Lobstack returns on every model call — cost_usd, savings_usd, baseline_reason — and report cost from it instead of estimating.
SKILL.md · MIT - Cost
Pick a model tier, not a flagship
Choose the cheapest model tier that can actually do the task instead of defaulting to a flagship, and verify the choice before spending on it.
SKILL.md · MIT - Cost
Keep an agent inside a budget
Hold an agent, job or run inside a hard dollar budget using the per-call cost the Gateway returns, and handle the 402 when an allowance runs out.
SKILL.md · MIT - Cost
Write a cost-aware system prompt
Write or review a system prompt that does not quietly multiply the bill — bounded output, no re-sent bulk, tool schemas counted as the input tokens they are.
SKILL.md · MIT - Gateway
Debug a Gateway 400, 402 or 429
Diagnose a Lobstack Gateway failure from its status and error class and decide whether retrying can possibly help.
SKILL.md · MIT - Migration
Migrate an SDK call to the Gateway
Move existing OpenAI or Anthropic SDK code onto the Lobstack Gateway by changing the base URL and the key, and verify it actually routed.
SKILL.md · MIT - Migration
Put Cursor or Aider behind the Gateway
Route Cursor, Aider, Continue or any OpenAI-compatible tool through the Lobstack Gateway with a local proxy, and see a cost line per request.
SKILL.md · MIT - Authoring
Author an Agent Skill
Write a SKILL.md an agent will actually load and follow — trigger-shaped description, valid frontmatter, progressive disclosure, no credentials.
SKILL.md · MIT