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.
git 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/agents/ancplua/ancplua-claude-plugins/ci-investigator)<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.
<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>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 | $0.00125 | $0.01117 |
| Opus 5 | $0.00063 | $0.00558 |
| Sonnet 5 | $0.00025 | $0.00223 |
| Haiku 4.5 | $0.00013 | $0.00112 |
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.
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
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 · 88 lines · 125 tokens per session scan A f6f0e7707d57
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.
Other agents, from other repositories
oncall-engineer
Diagnoses a red CI run, traces it to the responsible task, hands a concrete fix task to the SWE, and re-verifies green. Owns pipeline health; does not change application code.
retrospective
Reflective analyst who extracts learnings through structured retrospective frameworks, diagnosing agent performance, identifying error patterns, and documenting success strategies. Uses Five Whys, timeline analysis, and learning matrices. Use when you need root-cause analysis, atomicity scoring, or to transform…
ci-debugger
CI pipeline debugging specialist. Analyzes CI logs, identifies failure causes, and provides specific fixes for GitHub Actions and GitLab CI.
ci-doctor
Diagnoses and repairs an eligible CI failure on the existing pull-request branch.
debug
Debug your application to find and fix a bug. Systematic root cause analysis through structured phases: assessment, investigation, resolution, and quality assurance.
factory-ci-doctor
Diagnostician for one red GitHub Actions run. Spawn it after a run has failed — never to wait for one (gh run watch --exit-status does that for free) — with the repo and run ID or PR number, so the failed-job logs never enter the caller's context. It returns the culprit job/step, the offending log lines, and a TICKET…