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 ericrisco/rsc-harness --skill llm-pipelinegit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/llm-pipeline)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/llm-pipeline"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/llm-pipeline/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/ericrisco/rsc-harness/llm-pipeline"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/llm-pipeline.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 | $0.00083 | $0.02895 |
| Opus 5 | $0.00042 | $0.01448 |
| Sonnet 5 | $0.00017 | $0.00579 |
| Haiku 4.5 | $0.00008 | $0.00290 |
Grade A, and why
llm-pipeline 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 6d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llm-pipeline
Wire multiple LLM calls into a reliable, controllable production pipeline. You chain steps where one call's validated output feeds the next, put a router in front of providers so an outage fails over instead of taking you down, and engineer the cross-cutting concerns: timeouts, bounded retries, fallbacks, caching, and cost caps.
Treat the LLM as an unreliable network dependency, not a local function call. Every rule below follows from that: providers have outages, rate limits, and latency tails, so no single provider is a single point of failure and no call is allowed to run unbounded.
Do you even need a pipeline?
This skill is the orchestration around calls. If you only have one call, you are in the wrong place.
| Situation | Go to |
|---|---|
| Make one prompt better, few-shot, system-prompt design | ../prompt-engineering/SKILL.md |
| One call must return a typed object validated against a schema | ../structured-extraction/SKILL.md |
| The model decides its own next step / tool to call | ../building-agents/SKILL.md |
| Chunk/embed/retrieve context to stuff into a prompt | ../rag/SKILL.md |
| Pure spend ledger / attribution / dashboard | ../cost-tracking/SKILL.md |
| Fixed multi-step flow + reliability layer | here |
A pipeline is a DAG you designed. The moment the model picks its own next step, it is an agent — go build that instead.
Design the chain as a typed DAG
Each step is a pure-ish function: (typed input) -> (typed output via structured output). Chaining small single-purpose steps beats one mega-prompt — reported ~20% output-quality gain — because each step is debuggable, cacheable, and retryable in isolation.
Rules:
- The structured output of step N is the input contract of step N+1. Validate it (Pydantic / JSON Schema) at the seam. A schema-valid object that fails validation here never poisons the next call.
- Keep steps small and single-purpose. "Extract entities" and "classify sentiment" are two steps, not one prompt doing both. Smaller steps route to cheaper models and cache better.
- Mark independent steps for parallel fan-out. If step B and step C both only need step A's output, run them concurrently — see ../parallel/SKILL.md. Sequential only where there is a real data dependency.
- Tag each step idempotent or side-effecting. Retries and replays must be safe; a step that writes to a DB or sends an email is not safe to blindly retry.
What ships with it
5 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.
- 6d ago First seen · 151 lines · 83 tokens per session scan A 787a8783a5be
llm-pipeline is a skill published in the GitHub repository ericrisco/rsc-harness (78 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 2,895 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 2026-09-03.
Other skills, from other repositories
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
vllm
Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.
software-search
Designs application search systems. Use when choosing engines, indexing, relevance tuning, facets, autocomplete, or search analytics.
data-streaming
Designs streaming platforms for Kafka, Flink, CDC, and lakehouse ingestion. Use when planning event backbones, CDC pipelines, schema governance, or real-time lakehouse delivery.
gemini-webhooks
Receive and verify Google Gemini API webhooks. Use when setting up Gemini webhook handlers for batch jobs, video generation, or Interactions API function-calling LROs, debugging signature verification, or handling events like batch.succeeded, batch.failed, video.generated, or interaction.completed.
building-mcp-servers
Authors an MCP server with the official SDK and gates.