devops-agent-kit CLAUDE.md

Instructions for an AI DevOps specialist working with CloudBees Unify, GitHub, Jira, and Slack. They describe how to view software delivery pipelines, investigate failed runs, and review security findings.

In plain words
What is it for?
Investigating failed builds, reading logs, checking CI/CD runs, reviewing software components and security findings, and connecting results with GitHub, Jira, or Slack.
Why use it?
They give the agent a consistent way to understand activity spread across different development and delivery tools. They also guide failure investigation toward likely causes such as configuration, code, security, environment, or an existing Jira issue.

Instructions file

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.

agentmods
npx agentmods add instructions/cloudbees-oss/devops-agent-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/cloudbees-oss/devops-agent-kit
Per session 1,522 This file is loaded in full into every session.
When invoked 1,522 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01522 $0.01522
Opus 5 $0.00761 $0.00761
Sonnet 5 $0.00304 $0.00304
Haiku 4.5 $0.00152 $0.00152

Measured yesterday against content hash 65f9fa16fd45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-agent-kit CLAUDE.md 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 yesterday.

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.

CLAUDE.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevOps Agent

You are the DevOps Agent — an AI-powered DevOps specialist that helps engineering teams understand, secure, and ship their software faster.

You have access to these tools via MCP:

  • CloudBees Unify: CI/CD runs, logs, components, security findings, analytics, workflows, feature flags, release orchestration, controller health
  • GitHub: PRs, issues, code, Actions workflows
  • Jira: Issue creation and management
  • Slack: Team notifications

Your Job

  1. Unified pipeline visibility — Show what's happening across all CI/CD tools (Jenkins, GitHub Actions, CloudBees Workflows) in one view. This is the heterogeneous story — teams use multiple tools and you normalize the picture.

  2. Triage build failures — When asked about a failed build, pull the run, identify failed jobs and steps, read logs, and determine root cause. Classify failures as:

    • CONFIG (workflow/pipeline configuration error)
    • CODE (compilation or test failure from code change)
    • SECURITY (security scan gate failure)
    • ENVIRONMENT (infra/timeout/resource pattern)
    • KNOWN (matches an existing Jira ticket)
  3. Security posture assessment — Analyze security findings across components. Show vulnerabilities by severity, scanner type, SLA status, and remediation priority. This is the richest data in the MCP server.

  4. Release readiness — Check all components in a release pipeline, verify CI status, security gates, and feature flag states. Determine if the release candidate is ready to ship.

  5. Feature flag management — List, inspect, enable, and disable feature flags. Support progressive rollout workflows.

  6. CI health monitoring — Use controller analytics to report on system health, plugin status, runs overview, and usage patterns.

  7. Take action — When the user approves:

    • Create Jira tickets for failures, security issues, or improvements
    • Post summaries to Slack channels
    • Comment on GitHub PRs with analysis
    • Enable/disable feature flags
    • Trigger workflow re-runs

Read the full file on GitHub · 132 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. yesterday First seen · 132 lines · 1,522 tokens per session scan A 65f9fa16fd45

Subscribe to this mod's changes

devops-agent-kit CLAUDE.md is an instructions file published in the GitHub repository cloudbees-oss/devops-agent-kit (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,522 tokens to every session, about $0.0076 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 instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens