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 agentmods add skills/deeplink-org/probing/module_bottlenecknpx skills add DeepLink-org/probing --skill module_bottleneckgit clone --depth 1 https://github.com/DeepLink-org/probingWhat 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 | $0.00015 | $0.00294 |
| Opus 5 | $0.00008 | $0.00147 |
| Sonnet 5 | $0.00003 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
module_bottleneck 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.
What it actually says
PyTorch module bottleneck
基于 python.torch_trace 的 post-hook duration，找出最近 step 中最耗时的模块。 与 torch.profiler 互补：这是长期采样、模块级、低开销视图。
Parameters
recent_steps(integer, default10): Analyze the last N training stepsstage_filter(string, defaultpost forward): Hook stage to aggregate (post forward | post step)
Related skills
- 打开 Torch 火焰图 (profiling/torch) 看调用栈分布
- 分布式变慢 → skill: slow_rank
- 需要 CPU 栈 → SET probing.pprof.sample_freq=99, profiling/pprof
What ships with it
1 file 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.
- 3d ago First seen · 31 lines · 15 tokens per session scan A 5288d6d302c0
module_bottleneck is a skill published in the GitHub repository DeepLink-org/probing (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 15 tokens to every session and 294 once invoked, about $0.0001 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.
Other skills, from other repositories
performance-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.
performance-profiling
优化性能时使用。先测量定位再优化,不凭感觉。.
performance-engineer
Enforces measure-profile-optimize order, preventing intuition-driven optimization of non-bottlenecks.
k8s-performance
Kubernetes 高 CPU/内存/IO、应用响应慢的完整诊断-修复-验证 Skill.
performance-optimizer
Analyze and optimize code performance, identify bottlenecks, and suggest improvements.
evalscope
LLM evaluation & inference performance testing via the evalscope CLI. Translates natural language requests into evalscope commands for: (1) Model accuracy evaluation — runs 160+ benchmarks against local checkpoints or API endpoints (OpenAI-compatible, Anthropic, LiteLLM); (2) Performance stress testing — TTFT, TPOT…