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 eigent-ai/agent-skills --skill ml-failure-auditgit clone --depth 1 https://github.com/eigent-ai/agent-skillsWrote 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/eigent-ai/agent-skills/ml-failure-audit)<a href="https://agentmods.dev/skills/eigent-ai/agent-skills/ml-failure-audit"><img src="https://agentmods.dev/badge/skills/eigent-ai/agent-skills/ml-failure-audit/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/eigent-ai/agent-skills/ml-failure-audit"><img src="https://agentmods.dev/badge/skills/eigent-ai/agent-skills/ml-failure-audit.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 | $0.00092 | $0.00799 |
| Opus 5 | $0.00046 | $0.00400 |
| Sonnet 5 | $0.00018 | $0.00160 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
ml-failure-audit 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 9d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ML Failure Audit
Purpose
Audit ML failures from supplied artifacts without assuming the headline explanation is true. Use this skill when the user provides a repo, logs, W&B/MLflow/TensorBoard exports, CI artifacts, config files, or reports and asks for a diagnosis, go/no-go decision, or structured output.
Core Workflow
-
Locate evidence
- Find the repo root, log files, metric exports, configs, test definitions, golden values, and any requested output schema.
- Treat raw logs, raw telemetry, configs, and source code as higher-trust than reports, PR text, summaries, or generated JSONs.
-
Classify the failure
- Separate model/convergence signals from correctness, data, config, runtime, infra, and metric-policy signals.
- Do not label a failure as model/convergence regression when only a performance, timeout, logging, or tolerance gate failed and correctness/loss checks passed.
-
Recompute key facts
- Extract the failing metric/test, passed checks, final run state, key training counters, and relevant metric values.
- Recompute numeric claims directly from raw artifacts when possible.
- Record formulas for derived values such as throughput, relative error, finish rate, loss deltas, or token counts.
-
Trace code paths
- Identify how the repo selects metrics/tests and how comparisons are made.
- Cite exact source files and, when useful, function names or line snippets.
-
Make a decision
- State whether this is a true ML regression, system correctness bug, infra/runtime issue, data/config issue, metric-policy issue, or unsupported claim.
- Recommend the minimal policy or engineering action that protects correctness without over-blocking valid runs.
-
Write outputs
- Follow the task's requested schema exactly.
- If no schema is given, write a concise report with: evidence, classification, calculations, recommendation, and validation checks.
Guardrails
- Do not run expensive GPU training unless the user explicitly requests it.
- Do not clone remote repos when a local checkout is supplied.
- Do not trust prose summaries until verified against raw artifacts.
- Do not infer OOM, convergence, stability, or success from missing logs alone.
- If the task asks for a file output, create the file; do not only answer in chat.
What ships with it
4 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.
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.
- 9d ago First seen · 72 lines · 92 tokens per session scan A 7e19af0c2d74
ml-failure-audit is a skill published in the GitHub repository eigent-ai/agent-skills (19 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 799 once invoked, about $0.0005 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
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.…
debug-inference
Debug why inference.local, direct external inference, or supervisor-only system inference is failing. Use when the user cannot reach a local model server, has provider base URL issues, sees inference verification failures, hits protocol mismatches, or needs to diagnose inference on local vs remote gateways. Trigger…
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.
eagle3-triage
Triage a failed EAGLE3 pipeline run. Identifies which step failed (data synthesis, hidden state dump, training, or benchmark), diagnoses root cause from logs, and suggests fixes. Use when user reports an EAGLE3 pipeline failure or asks why a specific step failed. Also helps debug new model support issues.
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…