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/comm_bottlenecknpx skills add DeepLink-org/probing --skill comm_bottleneckgit clone --depth 1 https://github.com/DeepLink-org/probingWrote 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/deeplink-org/probing/comm_bottleneck)<a href="https://agentmods.dev/skills/deeplink-org/probing/comm_bottleneck"><img src="https://agentmods.dev/badge/skills/deeplink-org/probing/comm_bottleneck.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00015 | $0.00458 |
| Opus 5 | $0.00008 | $0.00229 |
| Sonnet 5 | $0.00003 | $0.00092 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
comm_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 5d 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
Communication bottleneck
按 collective op 聚合延迟与传输量，定位通信热点。 适用于「计算不慢但 step 时间长」或「通信占比高」的场景。
数据层次（勿混淆计时语义）
| 层 | 表 | 计时 |
|---|---|---|
| NCCL profiler 插件（优先） | nccl.coll_perf、nccl.proxy_ops |
NCCL 原生事件，执行时间/带宽精准（见 timing_source） |
| Torch API 层插桩（回退） | python.comm_collective |
Python 墙钟，launch 层粗粒度；独有 global_step 上下文 |
Torch 侧插桩默认关闭（含多 rank）；需 PROBING_TORCH_COLLECTIVE_ENABLE=1 或 SET probing.torch.collective.enable=1。
Parameters
step_window(integer, default50):use_global(boolean, defaultTrue):
Related skills
- all_reduce 慢 → 检查 bucket 大小、overlap、FP16 compress
- 有
nccl.proxy_ops→ skill:nccl_culprit_victim（culprit/victim 归因） - RoCE 拥塞 → 查 rdma.mlx_hca 与交换机 ECN 配置
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.
- 5d ago First seen · 40 lines · 15 tokens per session scan A bb665f53b8c6
comm_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 458 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
api-data-fetcher
Fetch economic data from FRED, World Bank, and other APIs.
python-panel-data
Panel data analysis with Python using linearmodels and pandas.
code-simplifier
Simplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.
Python 数据分析
当需要用 Python/pandas 分析数据文件、做统计聚合或绘制图表时使用,提供标准代码模式与 runpython 使用规范。.
python-idioms
写 Python 时使用。地道、安全、可维护的 Python 写法。.
qmt-docs
QMT（迅投极速策略交易系统）Python 策略开发完整指南。涵盖策略编写、回测、实盘交易、API参考和代码示例。当用户需要开发 QMT 量化策略、查询 QMT API、从聚宽迁移至 QMT、编写实盘交易程序，或提及 QMT、迅投策略、QMT 回测时使用。.