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 thousandeyes/thousandeyes-ai-agents-toolkit --skill thousandeyes-test-trace-correlationgit clone --depth 1 https://github.com/thousandeyes/thousandeyes-ai-agents-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/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-test-trace-correlation)<a href="https://agentmods.dev/skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-test-trace-correlation"><img src="https://agentmods.dev/badge/skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-test-trace-correlation/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/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-test-trace-correlation"><img src="https://agentmods.dev/badge/skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-test-trace-correlation.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 | $0.00061 | $0.01597 |
| Opus 5 | $0.00030 | $0.00798 |
| Sonnet 5 | $0.00012 | $0.00319 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
thousandeyes-test-trace-correlation 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ThousandEyes Test Trace Correlation
Use this skill to diagnose a failing ThousandEyes synthetic test end-to-end. Prefer evidence from ThousandEyes first, then correlate into available Observability Platforms. Only edit code after explicit user approval.
Use This Skill When
- A ThousandEyes synthetic test is failing or flaky
- The user wants service-map analysis or trace-based correlation
- The user wants root-cause analysis tied to any Observability Platform available through MCP
- The user wants a fix proposal after diagnosis, or approves implementing the fix
Required Behavior
- Read MCP tool descriptor JSON before using any MCP tool.
- Start from the test definition before interpreting metrics.
- Pull recent failure signals before forming a hypothesis.
- For
http-servertests, always inspectdistributedTracing. - If distributed tracing is enabled, call
get_service_mapbefore jumping to Observability Platform correlation. - If service-map data is missing or partial, continue with trace-ID fallback.
- Enumerate every Observability Platform MCP integration available in the current session before Observability Platform correlation. Do this even when common platforms (for example, Splunk or Datadog) are present.
- Once a valid
traceIdis available, verify and evaluate that trace across every enumerated Observability Platform MCP integration that supports trace or telemetry correlation. - For each Observability Platform, also check telemetry tied to the ThousandEyes failing window. Do this even when direct trace lookup is available, because the extra telemetry helps explain the problem more completely.
- Do not stop after the first platform hit. Record positive hits, empty results, and platform/tool limitations.
- Tie Observability Platform findings back to both the ThousandEyes test and the recovered trace ID whenever possible.
- Ask for explicit approval before making code changes.
Inputs To Gather
- Test reference:
testIdor exact/partial test name - Optional account scope:
aid - Investigation window:
windoworstart_date/end_date(default24h) - Whether the user wants diagnosis only or diagnosis plus code fix
What ships with it
2 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.
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 · 128 lines · 61 tokens per session scan A a8ffc0b11a3b
thousandeyes-test-trace-correlation is a skill published in the GitHub repository thousandeyes/thousandeyes-ai-agents-toolkit (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,597 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 2026-08-31.
Other skills, from other repositories
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
ce-dogfood
Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges experience against product personas, and writes a durable dogfood report. Manual invocation only.
ce-test-browser
Run browser tests for pages affected by the current branch or PR. Use when asked to run or check browser tests for the current change.
ce-test-xcode
Test iOS apps in a simulator with XcodeBuildMCP. Use when iOS changes need simulator evidence before handoff.
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…