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 monte-carlo-data/mc-agent-toolkit --skill troubleshoot-agent-tracesgit clone --depth 1 https://github.com/monte-carlo-data/mc-agent-toolkitWrote 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/monte-carlo-data/mc-agent-toolkit/troubleshoot-agent-traces)<a href="https://agentmods.dev/skills/monte-carlo-data/mc-agent-toolkit/troubleshoot-agent-traces"><img src="https://agentmods.dev/badge/skills/monte-carlo-data/mc-agent-toolkit/troubleshoot-agent-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/monte-carlo-data/mc-agent-toolkit/troubleshoot-agent-traces"><img src="https://agentmods.dev/badge/skills/monte-carlo-data/mc-agent-toolkit/troubleshoot-agent-traces.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 82 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 103 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00064 | $0.03980 |
| Opus 5 | $0.00032 | $0.01990 |
| Sonnet 5 | $0.00013 | $0.00796 |
| Haiku 4.5 | $0.00006 | $0.00398 |
Grade A, and why
monte-carlo-troubleshoot-agent-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 10d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monte Carlo Troubleshoot Agent Traces Skill
This skill investigates Monte Carlo AI agent alerts and traces — evaluation score drops, latency and token spikes, trajectory violations, and validation breaches — by classifying the alert, routing to the right playbook for the agent's backend, and guiding a systematic investigation with Monte Carlo's MCP tools. It runs Monte Carlo's trace troubleshooting agent (TTSA) in parallel with the manual investigation and merges both sets of findings.
Monte Carlo tool routing (required): Always call Monte Carlo MCP tools through this plugin's bundled server, whose fully-qualified tool names are
mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__<tool>(e.g.mcp__plugin_mc-agent-toolkit_monte-carlo-mcp__get_alerts). Bare tool names used in this skill (get_alerts,search,get_table, …) refer to that bundled server. If the session also has a separately-configuredmonte-carlo-mcpserver, do not route to it — it may point at a different endpoint or credentials.
Reference files live next to this skill file. Use the Read tool (not MCP resources) to access them:
- Alert-shape playbooks (WHAT to investigate):
references/agent-alert-evaluation.md,references/agent-alert-metric.md,references/agent-alert-trajectory.md,references/agent-alert-validation.md - Backend guides (HOW to investigate there / what signal exists):
references/agent-backend-clickhouse.md,references/agent-backend-cortex.md,references/agent-backend-genie.md,references/agent-backend-customer-otel.md,references/agent-backend-mlflow-sdk.md,references/agent-backend-mlflow-ka.md - Intake without an alert:
references/agent-direct-trace.md
When to activate this skill
Activate when the user:
- Mentions a Monte Carlo agent alert — agent evaluation, agent metric, agent trajectory, or agent validation
- Asks "why did my agent's eval score drop?" or "why is my agent slow/failing?"
- Wants to investigate a specific agent trace or conversation ("troubleshoot trace ")
- Asks about agent latency spikes, token explosions, error spikes, or quality regressions
- Says things like "investigate this agent alert", "debug my agent", "what's wrong with my agent"
What ships with it
12 files 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.
- README.md 5.8 KB
- references/agent-alert-evaluation.md 9.0 KB
- references/agent-alert-metric.md 6.1 KB
- references/agent-alert-trajectory.md 6.1 KB
- references/agent-alert-validation.md 6.0 KB
- references/agent-backend-clickhouse.md 6.6 KB
- references/agent-backend-cortex.md 6.0 KB
- references/agent-backend-customer-otel.md 5.2 KB
- references/agent-backend-genie.md 6.3 KB
- references/agent-backend-mlflow-ka.md 5.3 KB
- references/agent-backend-mlflow-sdk.md 5.0 KB
- references/agent-direct-trace.md 5.6 KB
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.
- 10d ago First seen · 209 lines · 64 tokens per session scan A 4ea165f23ca2
monte-carlo-troubleshoot-agent-traces is a skill published in the GitHub repository monte-carlo-data/mc-agent-toolkit (91 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 3,980 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 2026-08-30.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
debug-live
Guides root-cause investigations with debugging capabilities by setting breakpoints, starting a debug session, stepping through execution, inspecting variables, and tracing symptoms back to their origin. Prefer it for runtime bugs, failing tests, exceptions, crashes, hangs, wrong/null values, and unexpected output…
lcx-report-bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.