monitor-experiment

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha fa3de7f8fd47 · 31 Oct 2026Report an issue or request a re-scan

• Publisherwanshuiyin GitHub userOwner of the repository this skill is read from
• Source folderwanshuiyin/auto-claude-code-research-in-sleep/skills/monitor-experimentThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdictfa3de7f8fd47A new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

---
name: monitor-experiment
description: Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.
argument-hint: "[server-alias or screen-name]"
allowed-tools: Bash(ssh *), Bash(echo *), Read, Write, Edit
---

# Monitor Experiment Results

> ⏱ **External cadence is appropriate here.** This skill waits on an external
> fact (job completion / progress), so it is a natural `/loop` / `CronCreate`
> surface: the wake reads status and self-judges only **machine-checkable**
> completion (exit code, file exists, epoch logged) — never quality. This is
> the additive external-wait shape in
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).
> If a scheduled wait here ends in a verdict step (e.g. then audit results),
> run that verdict **once** after the wait clears — not re-entered per tick.

Monitor: $ARGUMENTS

## Workflow

### Step 1: Check What's Running

**SSH server:**
```bash
ssh <server> "screen -ls"
```

**Vast.ai instance** (read `ssh_host`, `ssh_port` from `vast-instances.json`):
```bash
ssh -p <PORT> root@<HOST> "screen -ls"
```

Also check vast.ai instance status:
```bash
vastai show instances
```

**Modal** (when `gpu: modal` in CLAUDE.md):
```bash
modal app list         # List running/recent apps
modal app logs <app>   # Stream logs from a running app
```
Modal apps auto-terminate when done — if it's not in the list, it already finished. Check results via `modal volume ls <volume>` or local output.

### Step 2: Collect Output from Each Screen
For each screen session, capture the last N lines:
```bash
ssh <server> "screen -S <name> -X hardcopy /tmp/screen_<name>.txt && tail -50 /tmp/screen_<name>.txt"
```

If hardcopy fails, check for log files or tee output.

### Step 3: Check for JSON Result Files
```bash
ssh <server> "ls -lt <results_dir>/*.json 2>/dev/null | head -20"
```

If JSON results exist, fetch and parse them:
```bash
ssh <server> "cat <results_dir>/<latest>.json"
```

### Step 3.5: Pull W&B Metrics (when `wandb: true` in CLAUDE.md)

**Skip this step entirely if `wandb` is not set or is `false` in CLAUDE.md.**

Pull training curves and metrics from Weights & Biases via Python API:

```bash
# List recent runs in the project
ssh <server> "python3 -c \"
import wandb
api = wandb.Api()
runs = api.runs('<entity>/<project>', per_page=10)
for r in runs:
    print(f'{r.id}  {r.state}  {r.name}  {r.summary.get(\"eval/loss\", \"N/A\")}')
\""

# Pull specific metrics from a run (last 50 steps)
ssh <server> "python3 -c \"
import wandb, json
api = wandb.Api()
run = api.run('<entity>/<project>/<run_id>')
history = list(run.scan_history(keys=['train/loss', 'eval/loss', 'eval/ppl', 'train/lr'], page_size=50))
print(json.dumps(history[-10:], indent=2))
\""

# Pull run summary (final metrics)
ssh <server> "python3 -c \"
import wandb, json
api = wandb.Api()
run = api.run('<entity>/<project>/<run_id>')
print(json.dumps(dict(run.summary), indent=2, default=str))
\""
```

**What to extract:**
- **Training loss curve** — is it converging? diverging? plateauing?
- **Eval metrics** — loss, PPL, accuracy at latest checkpoint
- **Learning rate** — is the schedule behaving as expected?
- **GPU memory** — any OOM risk?
- **Run status** — running / finished / crashed?

**W&B dashboard link** (include in summary for user):
```
https://wandb.ai/<entity>/<project>/runs/<run_id>
```

> This gives the auto-review-loop richer signal than just screen output — training dynamics, loss curves, and metric trends over time.

### Step 4: Summarize Results

Present results in a comparison table:
```
| Experiment | Metric | Delta vs Baseline | Status |
|-----------|--------|-------------------|--------|
| Baseline  | X.XX   | —                 | done   |
| Method A  | X.XX   | +Y.Y              | done   |
```

### Step 5: Interpret
- Compare against known baselines
- Flag unexpected results (negative delta, NaN, divergence)
- Suggest next steps based on findings

### Step 6: Feishu Notification (if configured)

After results are collected, check `~/.claude/feishu.json`:
- Send `experiment_done` notification: results summary table, delta vs baseline
- If config absent or mode `"off"`: skip entirely (no-op)

## Key Rules
- Always show raw numbers before interpretation
- Compare against the correct baseline (same config)
- Note if experiments are still running (check progress bars, iteration counts)
- If results look wrong, check training logs for errors before concluding
- **Vast.ai cost awareness**: When monitoring vast.ai instances, report the running cost (hours * $/hr from `vast-instances.json`). If all experiments on an instance are done, remind the user to run `/vast-gpu destroy <instance_id>` to stop billing
- **Modal cost awareness**: Modal auto-scales to zero — no idle billing. When reporting results from Modal runs, note the actual execution time and estimated cost (time * $/hr from the GPU tier used). No cleanup action needed

Excerpt, first 5,025 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/wanshuiyin/auto-claude-code-research-in-sleep
git -C auto-claude-code-research-in-sleep checkout fa3de7f8fd47

Works in

1. 2026-10-31
   ✓SAFE B 89 / 100

   first audit · source fa3de7f8fd47

Questions about monitor-experiment

• github.com/wanshuiyin/auto-claude-code-research-in-sleep/tree/ma — the audited source at commit fa3de7f8fd47 and every finding aboveObserved · 31 Oct 2026

Spotted something wrong? Report a correction · Methodology