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 voxel51/fiftyone-skills --skill fiftyone-troubleshootgit clone --depth 1 https://github.com/voxel51/fiftyone-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/voxel51/fiftyone-skills/fiftyone-troubleshoot)<a href="https://agentmods.dev/skills/voxel51/fiftyone-skills/fiftyone-troubleshoot"><img src="https://agentmods.dev/badge/skills/voxel51/fiftyone-skills/fiftyone-troubleshoot/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/voxel51/fiftyone-skills/fiftyone-troubleshoot"><img src="https://agentmods.dev/badge/skills/voxel51/fiftyone-skills/fiftyone-troubleshoot.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 | $0.00059 | $0.04058 |
| Opus 5 | $0.00030 | $0.02029 |
| Sonnet 5 | $0.00012 | $0.00812 |
| Haiku 4.5 | $0.00006 | $0.00406 |
Grade C, and why
fiftyone-troubleshoot scanned grade C with 1 finding 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 13d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/.fiftyone/var/ # only after user confirms How it starts
The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FiftyOne Troubleshoot
Overview
Diagnose and fix common FiftyOne pain points. Match the user's symptom to the Issue Index, explain the root cause and proposed fix, get approval, then apply.
Shell commands in this skill are written for macOS/Linux. On Windows (non-WSL), adapt using PowerShell equivalents or use WSL.
Designed to grow: add new issues at the bottom as they are encountered.
Prerequisites
- FiftyOne installed:
pip install fiftyone - MCP server running (optional, for plugin-related fixes)
Key Directives
1. Always explain, propose, and confirm before acting
NEVER run a fix without first:
- Explaining what is wrong and why
- Describing what the fix will do
- Asking the user to confirm: "Should I apply this fix?"
Wait for explicit user confirmation before executing anything that modifies files, config, or data.
2. Never touch user datasets — FiftyOne is the source of truth
- Except when given explicit and direct instructions by the user:
- NEVER modify, edit, delete, or clone user datasets as part of troubleshooting
- NEVER call
fo.delete_dataset() - NEVER truncate, wipe, or alter dataset contents or sample fields to diagnose an issue
- Use FiftyOne's read-only API to inspect state:
fo.list_datasets(),fo.load_dataset(),len(dataset),dataset.get_field_schema()— these are safe - FiftyOne's state (datasets, fields, brain runs) is the ground truth; read it, never rewrite it to "fix" a problem
3. Never directly manipulate MongoDB
- NEVER use
pymongo,db.drop_collection(), or raw MongoDB shell commands - All data operations must go through the FiftyOne Python API
4. Never modify config or files silently
- NEVER change
database_uri,database_name, or any config file without showing what will change and getting approval - NEVER append to shell profiles (
.zshrc,.bash_profile, virtualenvactivate) without showing the exact line change and getting explicit user confirmation to apply
What ships with it
1 file 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.
- 13d ago First seen · 533 lines · 59 tokens per session scan C 75ef221b923f
fiftyone-troubleshoot is a skill published in the GitHub repository voxel51/fiftyone-skills (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 4,058 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.