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 DNYoussef/context-cascade --skill ml-training-debuggergit clone --depth 1 https://github.com/DNYoussef/context-cascadeWrote 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/dnyoussef/context-cascade/ml-training-debugger)<a href="https://agentmods.dev/skills/dnyoussef/context-cascade/ml-training-debugger"><img src="https://agentmods.dev/badge/skills/dnyoussef/context-cascade/ml-training-debugger/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/dnyoussef/context-cascade/ml-training-debugger"><img src="https://agentmods.dev/badge/skills/dnyoussef/context-cascade/ml-training-debugger.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01855 |
| Opus 5.5 | $0.00000 | $0.00742 |
| Sonnet 5.5 | $0.00000 | $0.00371 |
| Haiku 4.5 | $0.00000 | $0.00186 |
Grade A, and why
ml-training-debugger 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 1mo 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/============================================================================/ /* ML-TRAINING-DEBUGGER SKILL :: VERILINGUA x VERIX EDITION / /============================================================================*/
name: ml-training-debugger version: 1.0.0 description: | [assert|neutral] Version: 1.0.0 [ground:given] [conf:0.95] [state:confirmed] category: specialists tags:
- specialists
- domain-expert author: ruv cognitive_frame: primary: honorific goal_analysis: first_order: "Execute ml-training-debugger workflow" second_order: "Ensure quality and consistency" third_order: "Enable systematic specialists processes"
/----------------------------------------------------------------------------/ /* S0 META-IDENTITY / /----------------------------------------------------------------------------*/
[define|neutral] SKILL := { name: "ml-training-debugger", category: "specialists", version: "1.0.0", layer: L1 } [ground:given] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ /* S1 COGNITIVE FRAME / /----------------------------------------------------------------------------*/
[define|neutral] COGNITIVE_FRAME := { frame: "Honorific", source: "Japanese", force: "Who is the audience?" } [ground:cognitive-science] [conf:0.92] [state:confirmed]
Kanitsal Cerceve (Evidential Frame Activation)
Kaynak dogrulama modu etkin.
/----------------------------------------------------------------------------/ /* S2 TRIGGER CONDITIONS / /----------------------------------------------------------------------------*/
[define|neutral] TRIGGER_POSITIVE := { keywords: ["ml-training-debugger", "specialists", "workflow"], context: "user needs ml-training-debugger capability" } [ground:given] [conf:1.0] [state:confirmed]
/----------------------------------------------------------------------------/ /* S3 CORE CONTENT / /----------------------------------------------------------------------------*/
What ships with it
17 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.
- agents/ml-debugger-specialist.prompt 14 KB
- examples/convergence-debugging.py 16 KB runs code
- examples/overfitting-detection.py 16 KB runs code
- examples/vanishing-gradients.py 13 KB runs code
- manifest.json 1.2 KB
- README.md 5.7 KB
- resources/readme.md 6.6 KB
- resources/scripts/gradient-debugger.py 15 KB runs code
- resources/scripts/loss-analyzer.py 13 KB runs code
- resources/scripts/overfitting-detector.js 13 KB runs code
- resources/scripts/training-monitor.sh 8.2 KB runs code
- resources/templates/debug-config.yaml 5.1 KB
- resources/templates/loss-curve-template.json 8.2 KB
- resources/templates/training-metrics.yaml 6.6 KB
- tests/test-gradient-analysis.py 9.5 KB runs code
- tests/test-loss-divergence.py 8.4 KB runs code
- tests/test-mode-collapse.js 9.9 KB runs code
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.
- 1mo ago First seen · 220 lines · 0 tokens per session scan A f95d776ca8bf
ml-training-debugger is a skill published in the GitHub repository DNYoussef/context-cascade (32 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,855 tokens. 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
debug-inference
Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed managed inference endpoint. Trigger…
spark-optimization
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.
notebooklm
Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API.…
oh-my-posh
Install, configure, or troubleshoot Oh My Posh/ohmyposh: shell init, themes, segments, Nerd Font icons, and prompt setup on PowerShell, zsh, bash, or fish.
spark-engineer
Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operations, configure…
rocketride-debugging-pipelines
Use when a RocketRide pipeline run failed, errored, or produced wrong/empty output, and you need to find the failing node and fix it. Reads run status and execution traces, diagnoses the cause, and routes back to design or configuration. Also use directly when asked to debug a run.