thousandeyes-network-data-from-traceid

thousandeyes-network-data-from-traceid is a skill for Claude Code from thousandeyes/thousandeyes-ai-agents-toolkit. It costs 110 tokens per session (1,557 once invoked), scanned A, original, Apache-2.0.

A procedure for finding ThousandEyes network-test data from an existing distributed-trace ID. ThousandEyes is a service that monitors network and application performance.

In plain words
What is it for?
Use it when you have a trace ID to search observability systems, recover ThousandEyes context, and inspect matching test data.
Why use it?
It connects an application trace to the related network test, helping investigate whether a performance problem involved the network.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the thousandeyes plugin — 4 skills, 1 MCP server shipped together

Good fit Use it when you have a trace ID to search observability systems, recover ThousandEyes context, and inspect matching test data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-network-data-from-traceid
Install

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.

Any agent
npx skills add thousandeyes/thousandeyes-ai-agents-toolkit --skill thousandeyes-network-data-from-traceid
Clone the repo
git clone --depth 1 https://github.com/thousandeyes/thousandeyes-ai-agents-toolkit

Made for: Claude Code.

Or install thousandeyes, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote 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.

agentmods badge for thousandeyes-network-data-from-traceid

README.md
[![agentmods](https://agentmods.dev/badge/skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-network-data-from-traceid/github.svg)](https://agentmods.dev/skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-network-data-from-traceid)
Your own site
<a href="https://agentmods.dev/skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-network-data-from-traceid"><img src="https://agentmods.dev/badge/skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-network-data-from-traceid/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.

agentmods 80×15 button for thousandeyes-network-data-from-traceid

Your own site · 80×15
<a href="https://agentmods.dev/skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-network-data-from-traceid"><img src="https://agentmods.dev/badge/skills/thousandeyes/thousandeyes-ai-agents-toolkit/thousandeyes-network-data-from-traceid.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,557 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.01557
Opus 5 $0.00055 $0.00779
Sonnet 5 $0.00022 $0.00311
Haiku 4.5 $0.00011 $0.00156

Measured 11d ago against content hash 8de145e18410, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

thousandeyes-network-data-from-traceid 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.

plugins/thousandeyes/skills/thousandeyes-network-data-from-traceid/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Obtain ThousandEyes Network Data from TraceID

Use this skill to pivot from an existing distributed trace into the matching ThousandEyes test result. Treat ThousandEyes as the system of record for the recovered test data, and use Observability Platforms to discover the ThousandEyes context from the trace.

Required Behavior

  1. Use the client's built-in tool discovery for available ThousandEyes and Observability Platform tools. Inspect schemas or argument details before calling unfamiliar tools when that information is available.
  2. Verify that ThousandEyes MCP is available and that at least one Observability Platform integration or equivalent tooling path is available before starting.
  3. Build an inventory of every Observability Platform integration or equivalent tooling path available in the current session.
  4. Query every available Observability Platform by exact traceId. Do not stop after the first hit.
  5. For every matching trace, inspect trace-level, resource-level, and span-level attributes for tracestate and w3c.tracestate.
  6. If an Observability Platform lacks direct trace lookup but can search spans or logs by exact traceId, use that fallback and record it as fallback correlation.
  7. Parse the tracestate value as a W3C vendor-state list and extract the te= member.
  8. URL-decode the ThousandEyes value before reading query parameters.
  9. Recover accountId from __a, testId from testId, agentId from agentId, and executionTime from startTime. Treat executionTime as the round selector for the exact ThousandEyes test execution.
  10. Use the recovered identifiers to query ThousandEyes test details and the exact result window, preferring the same agent and the closest execution time.
  11. If ThousandEyes tools expose time-based round selection instead of a literal roundId, use startTime to select the matching round or result. Do not invent a roundId.
  12. Return both the observability evidence chain and the recovered ThousandEyes data.

Read the full file on GitHub · 100 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 100 lines · 110 tokens per session scan A 8de145e18410

Subscribe to this mod's changes

thousandeyes-network-data-from-traceid 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 110 tokens to every session and 1,557 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

ce-debug

Diagnosis loop for bugs and failing behavior. Use when asked to debug or fix failing or slow behavior.

EveryInc/compound-engineering-plugin · 23 tokens

ce-sweep

Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes merged to main, and emit an lfg-ready plan. First run sets up sources; supports mode:non-interactive for scheduled runs.

EveryInc/compound-engineering-plugin · 62 tokens

ce-riffrec-feedback-analysis

Analyze recorded product feedback into evidence for bugs and requirements. Use when a Riffrec capture or other screen, voice, or notes artifact needs interpretation. Use for Riffrec setup, capture, or sharing help when no recording exists yet.

EveryInc/compound-engineering-plugin · 55 tokens

openprd-experience-diagnostic-candidate-eval-20260606230321

A draft project-learning guide for turning recurring debugging evidence into reusable development knowledge. It focuses on agent, hook, harness, quality, and growth workflow changes.

mileson/openprd · 36 tokens

openprd-experience-diagnostic-candidate-eval-20260606232925

A draft project skill for turning diagnostic evidence into reusable engineering knowledge. It covers when to record recurring problems, clues, and fixes from agent, hook, or testing workflows.

mileson/openprd · 36 tokens

openprd-experience-diagnostic-candidate-eval-20260706202136

Use when the current task overlaps this draft project experience and you should verify fit before reusing it.

mileson/openprd · 37 tokens