INTERMEDIATE · 8 MODULES · 64 LESSONS

Claude Code in CI/CD Pipelines

Put Claude Code to work on every pull request in your pipeline, reviewing, fixing, and preparing releases with nobody at the keyboard, under tight limits on permissions and spend.

For you if
You already use Claude Code in your terminal and want it working on every PR without calling it by hand.
By the end
You'll know how to set up automated reviews in GitHub and GitLab, write your own pipeline agent, and protect it from malicious PRs.
You need
Claude Code on a paid plan or API key, GitHub Actions or GitLab CI experience, and a test repo.
  1. 01Claude Code in GitHub Actions8 LESSONS
    1. Introduction: the night-shift contractor
    2. Installing with `/install-github-app` and by hand
    3. Your first `@claude` workflow, line by line
    4. Authentication and secrets
    5. Automation mode: `prompt`, triggers and `claude_args`
    6. Outputs: `structured_output`, job summary and artifacts
    7. Costs: minutes, tokens and brakes
    8. Project: Claude on call at Colibrí
  2. 02Automated PR review8 LESSONS
    1. Introduction: a review the team wants to keep
    2. PR triggers and what Claude sees
    3. Inline comments
    4. Summary and suggest-only mode
    5. The team's conventions
    6. Large PRs: narrowing the scope
    7. Managed Code Review and the other options
    8. Project: Colibrí's review workflow
  3. 03claude -p in GitLab CI/CD and other CI systems8 LESSONS
    1. Module 3 introduction: claude -p outside GitHub
    2. claude -p in CI: bare mode, JSON output and exit codes
    3. GitLab CI/CD for a Claude job: stages, jobs, rules, variables and artifacts
    4. The GitLab pipeline with Claude: the official job, merge requests and credentials
    5. Permissions for unattended runs
    6. claude -p from Python and TypeScript scripts
    7. Other CI systems: the common recipe
    8. Project: porting Colibrí's review bot to GitLab
  4. 04The Claude Agent SDK in your own pipelines8 LESSONS
    1. Module 4 introduction: the Claude Agent SDK in your own pipelines
    2. Choosing: action, claude -p, Agent SDK, Messages API or Managed Agents
    3. The Agent SDK in Python inside a job
    4. The Agent SDK in TypeScript inside a job
    5. Permissions, hooks and budgets in the SDK
    6. Structured results and exit codes
    7. The no-agent alternative: one Messages API call
    8. Project: broken-CI triage agent for Colibrí
  5. 05Securing Claude in CI8 LESSONS
    1. Module 5 introduction: securing Claude in CI
    2. Threat model of an agent in CI
    3. Least privilege: job permissions, identities and tokens
    4. Secrets and short-lived credentials
    5. Prompt injection from PRs, forks, comments and logs
    6. Budget guards for unattended runs
    7. Auditing and observability
    8. Project: hardening Colibrí's workflows
  6. 06Delivery automation8 LESSONS
    1. Module 6 introduction: delivery automation
    2. Changelog from diffs, with validated JSON
    3. Readiness validation: Claude advises, checks decide
    4. Staging, production and approval gates
    5. PR descriptions and release notes
    6. Fixing broken CI with workflow_run
    7. Scheduled jobs
    8. Project: Colibrí's complete release workflow
  7. 07Security scanning and rollback8 LESSONS
    1. Module 7 introduction: security scanning and rollback
    2. Security scanning with Claude: the dedicated action, /security-review and your own prompt
    3. Integrating deterministic tools and triaging with Claude
    4. Automatic rollback with deterministic triggers
    5. Diagnosis after the rollback
    6. Findings as SARIF and annotations
    7. Incident summary and postmortem draft
    8. Project: security gate and rollback for Colibrí
  8. 08Project: Colibrí's complete pipeline8 LESSONS
    1. Project introduction: Colibrí's complete pipeline
    2. End-to-end pipeline design
    3. Stages 1 to 3: PR review, scanning and description
    4. Stages 4 to 6: release, readiness and deploy with approval
    5. Failure paths and observability
    6. Hardening and security review
    7. Documentation, cost and retrospective
    8. Final delivery and rubric
Reviews

What students say

These reviews are from enrolled students who completed at least 50% of the course. We moderate reviews only on content grounds (spam, offensive language, personal data), never for being critical or negative.

No approved reviews yet.

Be the first to share your experience!

SEC. 06 · THE STUDIO

Why this studio exists

For decades, building software belonged to technical profiles with years of training, and getting a digital product into the real world took companies months or years. No-code and AI have narrowed that gap, but the knowledge is still held by a few.

Tech Benders exists to open that knowledge up, so business teams and non-technical teams can put their ideas into production with the right technical decisions behind them. AI does what you ask of it. Without a technical base, what it builds may not scale with your company’s ecosystem, and its costs can run away over time.

The team knows the pains of large organizations and the speed at which they have to move. It brings solution architecture, data engineering, product built end to end from back end to front end, and daily work with AI. Software that solves what you need in days, not months, with the cost of AI kept in check.

Founders

The studioRead about Tech Benders →

Write to ushi@techbenders.io

Made with Wislab