TeleFuser: Skill for Claude Code

.claude/skills/optimize-pipeline/SKILL.md

optimize-pipeline is a skill for Claude Code from Tele-AI/TeleFuser. It costs 64 tokens per session (733 once invoked), scanned A, original, Apache-2.0.

A guide for improving an existing TeleFuser pipeline after its performance has been measured. TeleFuser is a repository for running model inference pipelines.

In plain words
What is it for?
Use it to tune latency, throughput, GPU memory, parallel processing, caching, quantization, compilation, or offloading while checking that results remain correct.
Why use it?
It helps identify the actual cause of slow runs, high memory use, out-of-memory errors, or poor multi-GPU use before changing performance settings.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is Tele-AI/TeleFuser's own configuration. It tells Claude Code how to work on TeleFuser itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TeleFuser configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Tele-AI/TeleFuser. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Tele-AI/TeleFuser/main/.claude/skills/optimize-pipeline/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Tele-AI/TeleFuser

Made for: Claude Code.

Wrote 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.

agentmods badge for optimize-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/tele-ai/telefuser/optimize-pipeline.svg)](https://agentmods.dev/skills/tele-ai/telefuser/optimize-pipeline)
Your own site
<a href="https://agentmods.dev/skills/tele-ai/telefuser/optimize-pipeline"><img src="https://agentmods.dev/badge/skills/tele-ai/telefuser/optimize-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 733 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.00733
Opus 5 $0.00032 $0.00367
Sonnet 5 $0.00013 $0.00147
Haiku 4.5 $0.00006 $0.00073

Measured 7d ago against content hash b10ab3443831, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

optimize-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 7d 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.

.claude/skills/optimize-pipeline/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimize a Pipeline

Require a correct, reproducible baseline before changing performance behavior. Read current implementations and canonical docs rather than relying on hard-coded speedup or memory estimates.

Define the target

Record the workload, model/checkpoint, task, shape, frame count, step count, dtype, attention backend, devices, warmup, measured latency/throughput, peak memory, and quality or parity criterion. Distinguish latency, throughput, capacity, and output cadence; they require different choices.

If no baseline exists, profile first. Use .claude/skills/profile-pipeline/SKILL.md and docs/en/profiler.md.

Reuse supported mechanisms

Inspect the closest model and pipeline before choosing an optimization. Consult the relevant current docs:

  • docs/en/ops.md and docs/en/attention.md
  • docs/en/parallel.md
  • docs/en/offload.md
  • docs/en/feature_cache.md
  • docs/en/torch_compile_compatibility.md
  • docs/en/configuration.md

Apply these constraints:

  • Route model operations through telefuser.ops; do not import Triton kernels directly from models/.
  • Preserve exact semantics when replacing an op: layout, normalization, RoPE, masks, causal behavior, scale, dtype, and numerical tolerances must match.
  • Use current AttentionConfig, ModelRuntimeConfig, ParallelConfig, FeatureCacheConfig, CompileConfig, QuantConfig, and OffloadConfig APIs as implemented in the repository.
  • Confirm that the target model and stage implement the selected parallel or optimization path. A config field existing does not prove model support.
  • Treat sparse attention, feature caching, quantization, distillation, and approximate computation as behavior or quality changes; require explicit user agreement and parity/quality evidence.
  • Do not add a new public interface, configuration system, environment variable, loader, or parallel abstraction as part of optimization without first demonstrating a missing extension point and obtaining approval.

Read the full file on GitHub · 59 lines

Changes

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.

  1. 7d ago First seen · 59 lines · 64 tokens per session scan A b10ab3443831

Subscribe to this mod's changes

optimize-pipeline is a skill published in the GitHub repository Tele-AI/TeleFuser (25 stars, last pushed 2d ago), licensed Apache-2.0. It adds 64 tokens to every session and 733 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 2026-08-30.

Related

Other skills, from other repositories

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

Orchestra-Research/AI-Research-SKILLs · 88 tokens

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

OpenRaiser/NanoResearch · 88 tokens

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

TTAWDTT/elegant-researcher-skill · 88 tokens

tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.

davila7/claude-code-templates · 32 tokens

ray-train

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

davila7/claude-code-templates · 63 tokens

torchforge-rl-training

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

davila7/claude-code-templates · 49 tokens