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 ANcpLua/ancplua-claude-plugins --skill helix-investigationgit clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsWrote 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/ancplua/ancplua-claude-plugins/helix-investigation)<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/helix-investigation"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/helix-investigation/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/ancplua/ancplua-claude-plugins/helix-investigation"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/helix-investigation.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 | $0.00158 | $0.04396 |
| Opus 5 | $0.00079 | $0.02198 |
| Sonnet 5 | $0.00032 | $0.00879 |
| Haiku 4.5 | $0.00016 | $0.00440 |
Grade C, and why
helix-investigation scanned grade C with 2 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 12d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://helix.dot.net/api/2019-06-17/jobs/{jobId}/workitems/{workItemName}/files" | python3 -c "import sys,json; [print(f['Name']) for f in json.load(sys.stdin)]" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
INVOKES: Helix and AzDO MCP tools, curl, gh CLI. How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Helix Investigation
Deep-dive into Helix test failures starting from an AzDO build leg. Goes beyond CI status checks to download raw console logs, compare passing vs failing runs, and identify root causes at the machine/device level.
When to Use This Skill
- User has an AzDO build URL with a failing test leg and wants to understand why
- User wants to see raw Helix console logs for a specific work item
- User notices a test fails intermittently and wants pass/fail comparison
- User asks "why does this test only fail on some machines?"
- User wants to correlate AzDO build → Helix job → work item → console output
- User mentions XHarness, device tests, or Helix timeouts
- User asks for a "top N" list of failures across a pipeline or time range
- User wants to know if failures are machine-specific or systemic
- User sees Android DEVICE_NOT_FOUND or emulator boot failures
Prerequisites
- Helix MCP tools (hlx-* prefix) for querying jobs, work items, and logs
- AzDO MCP tools (ado-* prefix) for querying builds and timelines
curlfor downloading raw log files when MCP search is insufficient- Access to
https://helix.dot.net/API endpoints
Workflow
Step 1: Start from the AzDO build
Given an AzDO build URL or pipeline definition + build ID:
- Query the build timeline to find the failing job/leg
- Identify the Helix job ID from the timeline records — look for
HelixJobIdin record properties or Helix URLs in the log output - Note the job name, queue, and failure category
AzDO Build → Timeline API → Failing job record → Helix job ID
⚠️ AzDO MCP tools may become unavailable mid-session. Fall back to the REST API:
https://dev.azure.com/{org}/{project}/_apis/build/builds/{buildId}/timeline?api-version=7.1
Step 2: Enumerate Helix work items
Query the Helix job for its work items. Each work item is a test group that ran on a specific machine.
Key fields to capture per work item:
- Work item name (e.g.,
iOS.CoreCLR.R2R.Test,System.Runtime.Tests) - Exit code (0 = pass, 143 = SIGTERM/timeout, 71 = infra error)
- Machine name (e.g.,
DNCENGMAC036,DNCENGTVOS-106) - Duration — long durations with exit 143 indicate timeout kills
- Failure category —
Crash,InfrastructureError, etc.
What ships with it
3 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.
- 12d ago First seen · 333 lines · 158 tokens per session scan C 1625fda18f86
helix-investigation is a skill published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 26d ago), licensed MIT. It adds 158 tokens to every session and 4,396 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.