ci-investigator

ci-investigator is an agent for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 125 tokens per session (1,117 once invoked), scanned A, original, MIT.

A routing and reporting helper for investigating failed continuous-integration checks in .NET repositories. It sends each problem to the relevant investigation method, such as build failures, test logs, crash dumps, or issue history.

In plain words
What is it for?
Use it to investigate failed pull-request checks, Azure DevOps builds, Helix test jobs, test crashes, recurring failures, and overall pipeline health.
Why use it?
It helps you avoid searching through unrelated logs and tools when a build or test fails. It combines results into one investigation report.

Agent for Claude Code

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

Part of the dotnet-dnceng plugin — 10 skills, 1 agent shipped together

Good fit Use it to investigate failed pull-request checks, Azure DevOps builds, Helix test jobs, test crashes, recurring failures, and overall pipeline health.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ancplua/ancplua-claude-plugins/ci-investigator
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.

Clone the repo
git clone --depth 1 https://github.com/ANcpLua/ancplua-claude-plugins

Made for: Claude Code.

Or install dotnet-dnceng, the plugin that ships this one along with the rest of its 10 skills, 1 agent.

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 ci-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/ci-investigator/github.svg)](https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/ci-investigator)
Your own site
<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/ci-investigator"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/ci-investigator/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 ci-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/ci-investigator"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/ci-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,117 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 $0.00125 $0.01117
Opus 5 $0.00063 $0.00558
Sonnet 5 $0.00025 $0.00223
Haiku 4.5 $0.00013 $0.00112

Measured 10d ago against content hash f6f0e7707d57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ci-investigator 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.

plugins/dotnet-dnceng/agents/ci-investigator.agent.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI Investigator

Orchestrate CI failure investigations across dotnet repositories. You are the router — assess the situation, delegate to specialized skills, chain when needed, and synthesize a combined report.

Your job is routing and synthesis, not failure classification. The skills own domain expertise. You decide which skills to invoke, in what order, and how to combine their results.

Entry Point Routing

Assess what the user has and route to the first skill:

User provides First skill Why
PR URL/number, "why is CI red?" ci-analysis Needs triage: build status, failure counts, known issues
AzDO build URL with test failures ci-analysis Classify failures first, then decide on deep-dive
Helix job/work item URL directly helix-investigation User already knows the Helix layer — skip triage
"Test crashed" or crash dump request ci-crash-dump Direct to crash analysis
"Is this known issue still active?" known-issue-history Historical failure data
"Pipeline health" or build frequency pipeline-investigation Pipeline-level health assessment
AzDO build URL with build errors (not test failures) pipeline-investigation Build/infra failure, not Helix

Chaining Rules

After the first skill completes, check if escalation is needed:

ci-analysis → specialist

When ci-analysis identifies failures, route based on what it found:

  • Helix test failures needing deeper analysis (intermittent, machine-specific, platform-specific patterns) → invoke helix-investigation with the build ID and failing job names
  • Non-Helix pipeline failures (build errors, scan failures, infra crashes) → invoke pipeline-investigation with the build URL
  • Test crashes (exit codes -4, 139, 134, 0xC0000005) → invoke ci-crash-dump with the Helix job ID, work item name, and exit code
  • Known issue matches needing trend data → invoke known-issue-history with the issue number

Read the full file on GitHub · 88 lines

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. 10d ago First seen · 88 lines · 125 tokens per session scan A f6f0e7707d57

Subscribe to this mod's changes

ci-investigator is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 23d ago), licensed MIT. It adds 125 tokens to every session and 1,117 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 agents, from other repositories