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 Galbaz1/video-research-mcp --skill mlflow-tracesgit clone --depth 1 https://github.com/Galbaz1/video-research-mcpWrote 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/galbaz1/video-research-mcp/mlflow-traces)<a href="https://agentmods.dev/skills/galbaz1/video-research-mcp/mlflow-traces"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/mlflow-traces/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/galbaz1/video-research-mcp/mlflow-traces"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/mlflow-traces.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 | $0.00037 | $0.01662 |
| Opus 5 | $0.00018 | $0.00831 |
| Sonnet 5 | $0.00007 | $0.00332 |
| Haiku 4.5 | $0.00004 | $0.00166 |
Grade A, and why
mlflow-traces 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 11d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MLflow Trace Management — video-research-mcp
Overview
Query, tag, evaluate, and manage MLflow traces captured from video-research-mcp Gemini API calls. Uses mcp__mlflow-mcp__* MCP tools — no code writing needed for most operations.
Core principle: Search first, then act. Always verify before destructive operations.
Quick Reference
| Task | Tool | Key Params |
|---|---|---|
| Find traces | search_traces |
experiment_id, filter_string, extract_fields |
| Get details | get_trace |
trace_id, extract_fields |
| Tag trace | set_trace_tag |
trace_id, key, value |
| Log score | log_feedback |
trace_id, name, value, rationale |
| Run scorers | evaluate_traces |
experiment_id, trace_ids, scorers |
| List scorers | list_scorers |
— |
Canonical Field Paths
CRITICAL — only use fields that actually exist:
| Path | Content | Common mistake |
|---|---|---|
info.trace_id |
Trace identifier | — |
info.state |
Status: OK, ERROR | NOT info.status |
info.request_time |
Timestamp | NOT info.timestamp_ms |
info.execution_duration_ms |
Duration in ms | NOT info.execution_duration |
info.request_preview |
First ~100 chars of request | — |
info.response_preview |
First ~100 chars of response | — |
info.tags |
All tags as object | Use info.tags.* for all |
data.spans.*.name |
Span names | Must include data. prefix |
data.spans.*.status_code |
Span status | NOT data.spans.*.status |
data.spans.*.inputs |
Span inputs | Moderate size |
data.spans.*.outputs |
Span outputs | Moderate size |
extract_fields Discipline
Always use extract_fields. Video-research-mcp traces contain video URIs, cached content references, full Gemini prompts/responses. A single get_trace without extract_fields can flood your context window.
// BAD - pulls everything
get_trace({ trace_id: "tr-..." })
search_traces({ experiment_id: "2" })
// GOOD - selective fields
get_trace({ trace_id: "tr-...",
extract_fields: "info.*,data.spans.*.name,data.spans.*.status_code" })
search_traces({ experiment_id: "2", max_results: 10,
extract_fields: "info.trace_id,info.state,info.execution_duration_ms" })
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.
- 11d ago First seen · 169 lines · 37 tokens per session scan A f68ebe463b56
mlflow-traces is a skill published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,662 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 2026-08-30.
Other skills, from other repositories
hmem-new-error
Create a new E-entry (bug/error) in hmem with the strict 5-level scaffold. Use when the user wants to log a bug, file a report, or document an error ('Bug loggen', 'log this error', 'Fehler eintragen'), or before any writememory with prefix='E'.
Safe Android Reverser
Safely fingerprint, route, decompile, inspect Flutter AOT, query program evidence, and reconstruct Android network/auth/crypto behavior through one capability-aware MCP control plane.
spotify-mcp-doctor
Diagnose and repair NovaLux12/spotify-mcp-server failures — auth, permissions, devices, rate limits, OpenClaw wiring. Use when Spotify tool calls fail or setup stalls.
feedback-nudge
Use when the user wants to report a bug, request a feature, or send feedback to the Zooza engineering team. Also offer proactively after a successful commit operation (max once per week).
troubleshooting
Troubleshooting guide for ComfyUI MCP connection issues, model errors, workflow failures, and security warnings. Use when users encounter errors or unexpected behavior.
eg-fix-bug
Fix a bug with Codex using problem doc, independent diagnosis, failing test, fix, review, and validation.