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/memory_leaknpx skills add DeepLink-org/probing --skill memory_leakgit 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/memory_leak)<a href="https://agentmods.dev/skills/deeplink-org/probing/memory_leak"><img src="https://agentmods.dev/badge/skills/deeplink-org/probing/memory_leak.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 | $0.00014 | $0.00277 |
| Opus 5 | $0.00007 | $0.00138 |
| Sonnet 5 | $0.00003 | $0.00055 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
memory_leak 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 4d 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
GPU memory leak detection
检测 python.torch_trace 中 allocated 是否随 step 单调上涨， 并结合 gpu.utilization 看设备级显存趋势。
Parameters
min_steps(integer, default10): Minimum steps required for trend analysisstep_skip(integer, default2): Skip first N steps (discovery / warmup)
Related skills
- 某模块 delta 大 → 检查是否 cache 了 tensor / 未 detach
- 仅 torch_trace 涨而 gpu.utilization 平稳 → 可能是统计口径问题
- Linux OOM → SELECT * FROM process.kmsg WHERE message LIKE '%oom%'
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.
- 4d ago First seen · 31 lines · 14 tokens per session scan A d2826896c720
memory_leak is a skill published in the GitHub repository DeepLink-org/probing (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 14 tokens to every session and 277 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-profiling
优化性能时使用。先测量定位再优化,不凭感觉。.
deck-presenter-mode
【模板: Presenter Mode Deck】 【意图】怕忘词的演讲者专用 deck, 含逐字稿 notes 与 popup teleprompter。 【布局】.
invoice
标准发票: 寄件/收件 + 明细 + 税 + 总额 + 付款指引.
xhs_note
小红书图文创作 / 笔记 / 种草文案 (xiaohongshu / red note) — 端到端：成文→配图(≥3 张竖版)→去AI化→在线预览打包交付。以图为主、文字辅助：标题四件套 + 碎句正文 + 话题标签，配 3:4 竖版卡片，最少 3 张图。honors user persona & style memory.
perf-host-analysis
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify…
perf-host-optimization
Profiles and optimizes TensorRT-LLM host/CPU overhead using lineprofiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.