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 ihatesea69/kiro-kit --skill experiment-trackinggit clone --depth 1 https://github.com/ihatesea69/kiro-kitWrote 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/ihatesea69/kiro-kit/experiment-tracking)<a href="https://agentmods.dev/skills/ihatesea69/kiro-kit/experiment-tracking"><img src="https://agentmods.dev/badge/skills/ihatesea69/kiro-kit/experiment-tracking/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/ihatesea69/kiro-kit/experiment-tracking"><img src="https://agentmods.dev/badge/skills/ihatesea69/kiro-kit/experiment-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00325 |
| Opus 5 | $0.00016 | $0.00162 |
| Sonnet 5 | $0.00007 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
experiment-tracking 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 7d 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
Experiment Tracking
Activate this skill when managing ML experiments and reproducibility.
When to Use
- Logging hyperparameters and metrics
- Comparing experiment runs
- Tracking model artifacts and versions
- Reproducing previous results
- Sharing experiment results with team
Tools
- MLflow: Open-source, self-hosted
- Weights & Biases: Cloud-hosted, rich UI
- DVC: Git-based data/model versioning
- Neptune.ai: Metadata management
Patterns
import mlflow
mlflow.set_experiment("text-classification")
with mlflow.start_run(run_name="bert-base-lr3e5"):
mlflow.log_params({
"model": "bert-base-uncased",
"lr": 3e-5,
"epochs": 10,
"batch_size": 32,
})
# Training...
mlflow.log_metrics({"val_f1": 0.89, "val_loss": 0.34})
mlflow.log_artifact("confusion_matrix.png")
mlflow.transformers.log_model(model, "model")
Rules
- Log everything: params, metrics, artifacts, environment
- Use meaningful run names and tags
- Track data versions alongside model versions
- Set random seeds and log them
- Never delete experiment history
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.
- 7d ago First seen · 53 lines · 33 tokens per session scan A e1dca51c3a72
experiment-tracking is a skill published in the GitHub repository ihatesea69/kiro-kit (18 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 325 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
nativeprompt
A prompt editor that adapts a user's request to the rules of a selected coding model, such as Claude Code, Codex, Gemini CLI, or GPT-5.
refine
Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode.
thegraph-mcp-skill
Use The Graph Subgraph MCP through UXC via native SSE with a fixed linked command for subgraph discovery, schema retrieval, deployment selection, and GraphQL query execution with help-first inspection and explicit auth handling.
qmd-mcp-skill
Use a local QMD knowledge base through UXC over MCP stdio, with daemon-backed session reuse and typed retrieval flows that avoid repeated model warmup and unnecessary query-expansion latency.
goal-test
A local experiment for testing a goal command that keeps an AI coding session working until a stated condition is judged complete. It uses a separate language model to evaluate the conversation after each assistant turn.
schliff
Deterministic linter and scorer for instruction files — SKILL.md, AGENTS.md, CLAUDE.md. No model in the loop: the same bytes score the same everywhere. Use for linting, scoring, auditing or CI-gating an instruction file, and for checking whether the commands a file promises actually resolve in the repo. Trigger…