pipeline-debug

pipeline-debug is a skill for Claude Code from hmcts/agentic-plugins-marketplace. It costs 36 tokens per session (1,487 once invoked), scanned A, original, MIT.

A guide for investigating Azure DevOps pipeline files, including shared templates and the variables they define. Azure DevOps is Microsoft's service for hosting code and running automated build and deployment jobs.

In plain words
What is it for?
Use it to debug failed pipelines, set up CI/CD for a new repository, trace variable values, and understand shared pipeline templates.
Why use it?
It helps explain why a pipeline failed and where a setting or step came from, even when the configuration is spread across several template files.

Skill for Claude Code

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

Part of the hmcts-sdlc-orchestrator plugin — 10 skills, 9 agents shipped together

Good fit Use it to debug failed pipelines, set up CI/CD for a new repository, trace variable values, and understand shared pipeline templates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hmcts/agentic-plugins-marketplace/pipeline-debug
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 hmcts/agentic-plugins-marketplace --skill pipeline-debug
Clone the repo
git clone --depth 1 https://github.com/hmcts/agentic-plugins-marketplace

Made for: Claude Code.

Or install hmcts-sdlc-orchestrator, the plugin that ships this one along with the rest of its 10 skills, 9 agents.

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 pipeline-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/hmcts/agentic-plugins-marketplace/pipeline-debug.svg)](https://agentmods.dev/skills/hmcts/agentic-plugins-marketplace/pipeline-debug)
Your own site
<a href="https://agentmods.dev/skills/hmcts/agentic-plugins-marketplace/pipeline-debug"><img src="https://agentmods.dev/badge/skills/hmcts/agentic-plugins-marketplace/pipeline-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,487 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 $0.00036 $0.01487
Opus 5 $0.00018 $0.00744
Sonnet 5 $0.00007 $0.00297
Haiku 4.5 $0.00004 $0.00149

Measured 7d ago against content hash da5586db1cf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pipeline-debug 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 7d 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/agents/hmcts-sdlc-orchestrator/skills/pipeline-debug/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pipeline Debug

Helps debug, understand, and configure Azure DevOps pipelines across CP repositories by tracing template references, variable resolution, and pipeline structure.

When to Use

  • User asks "why did my pipeline fail", "debug this pipeline", "trace this variable"
  • User wants to set up CI/CD for a new repo
  • User needs to understand how shared templates work
  • User wants to find which template defines a specific step or variable

Process

Step 1: Identify the Pipeline

Read the repo's azure-pipelines.yml (or azure-pipelines.yaml). This is the entry point.

Step 2: Trace Template References

CP pipelines use shared templates from cpp-azure-devops-templates. Template references look like:

resources:
  repositories:
    - repository: cppAzureDevOpsTemplates
      type: github
      name: hmcts/cpp-azure-devops-templates
      ref: refs/heads/main

stages:
  - template: pipelines/context-verify.yaml@cppAzureDevOpsTemplates

For each template reference:

  1. Read the template file from cpp-azure-devops-templates/
  2. Map the parameters passed from the calling pipeline to the template's parameter definitions
  3. Recursively follow any nested template references (stages → steps → tasks)

Step 3: Trace Variable Resolution

Variables are resolved in this order (later overrides earlier):

  1. Pipeline-level variables — defined in azure-pipelines.yml
  2. Variable groups — referenced by name, stored in Azure DevOps
  3. Template parameters — passed explicitly to templates
  4. Runtime expressions${{ variables.xxx }}, $[ variables.xxx ]
  5. Macro syntax$(variableName) resolved at runtime

Step 4: Identify Common Pipeline Types

Repo Type PR Template Merge Template Key Steps
Context services context-verify.yaml context-validation.yaml Maven build, SonarQube, JaCoCo
UI apps ui-verify.yaml ui-validation.yaml npm install, lint, test, build
Terraform modules terratest.yaml terraform init, validate, plan, test
Docker images image-publish.yaml Docker build, ACR push
Helm charts Custom in cpp-helm-chart Helm lint, package, ACR push
UI E2E tests (cpp-ui-e2e-serenity) azure-pipelines.yml (PR) azure-pipelines-dev01_regression.yml, *_BPO_regression.yml, *_migration.yml, *_migration_EDT.yml, *_migration-nows.yml, *_migration-ts.yml, azure-pipeline-cdci-dlrm.yml Maven verify, Serenity profiles, WebDriver browser provisioning, Serenity HTML reports
API integration tests (cpp-apitests) azure-pipelines.yaml (PR) apitests-pipeline.yaml Maven verify (Failsafe runs *IT.java), REST Assured + JUnit 5

Read the full file on GitHub · 135 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. 7d ago First seen · 135 lines · 36 tokens per session scan A da5586db1cf3

Subscribe to this mod's changes

pipeline-debug is a skill published in the GitHub repository hmcts/agentic-plugins-marketplace (3 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,487 once invoked, about $0.0002 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