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/ericyuan2007/gpuplane/monitor-experimentnpx skills add EricYuan2007/GPUPlane --skill monitor-experimentgit clone --depth 1 https://github.com/EricYuan2007/GPUPlaneWrote 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/ericyuan2007/gpuplane/monitor-experiment)<a href="https://agentmods.dev/skills/ericyuan2007/gpuplane/monitor-experiment"><img src="https://agentmods.dev/badge/skills/ericyuan2007/gpuplane/monitor-experiment.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 | $0.00060 | $0.00926 |
| Opus 5 | $0.00030 | $0.00463 |
| Sonnet 5 | $0.00012 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
monitor-experiment 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
monitor-experiment
Watch a training run and intervene on anomalies. The control plane's EventDetector already classifies problems (OOM, loss-NaN, loss-spike, overfitting, GPU-underutilization, disk-low, agent-disconnect); this skill is about consuming those signals and acting, not re-deriving them.
Default watch loop
Poll at minute cadence (not seconds — training is slow and the user is often away). Each tick:
get_run_summary(run_id)— readprogress.percent,convergenceof the primary metric (trend/improving/stalled),health.warnings.list_events(run_id=…, severity=critical, limit=20)— anything new since the last tick needs attention.infoevents (CHECKPOINT_CREATED, EVALUATION_FINISHED) are progress, not problems.
If everything is healthy, report a one-line status to the user and stop — do not
spam. Only escalate on warning/critical.
Anomaly runbook
| signal (from diagnose_run / events) | action |
|---|---|
LOSS_NAN (critical) |
the run is poisoned — cancel_job(confirm=True) after telling the user; then explain_failure for the cause (bad LR, amp, data). |
OOM (critical) |
tail_logs to confirm, then recommend a smaller batch / gradient checkpointing / accumulation; cancel_job and retry_job once the user fixes the config. |
OVERFITTING_SUSPECTED |
don't cancel — flag it; compare_checkpoints to see if an earlier checkpoint is better, and suggest early-stopping. |
GPU_UNDERUTILIZED (warning, >10min) |
likely a data-loader bottleneck or CPU-bound step; tell the user to check num_workers / pin_memory, not a crash. |
AGENT_DISCONNECTED / JOB_LOST |
infra, not the model — check the agent host is up; retry_job once the agent reconnects. |
DISK_LOW |
checkpoints will fail to write — tell the user to clean checkpoints/ or move the run. |
Failure triage
When get_run_summary shows status=FAILED (or an OOM/NaN event fires):
explain_failure(run_id)— structuredlikely_cause+suggested_fixes. It already read the exit code, failure reason, classified events, and the log tail. Read itssuggested_fixesbefore doing anything else.tail_logs(job_id, stream=stderr, tail=200)only ifexplain_failure's cause is "unknown" — to grep the traceback yourself.- Present the cause + fixes to the user. Do not auto-retry after an OOM or NaN without the user fixing the config — it will fail the same way.
- Once fixed,
retry_job(job_id)(same id, new attempt) and resume watching.
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 · 70 lines · 60 tokens per session scan A c924751639b7
monitor-experiment is a skill published in the GitHub repository EricYuan2007/GPUPlane (0 stars, last pushed 8d ago), licensed Apache-2.0. It adds 60 tokens to every session and 926 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.