circleci-expert

circleci-expert is an agent for coding agents from 0xfurai/claude-code-subagents. It costs 22 tokens per session (483 once invoked), scanned A, original, MIT.

A specialist assistant for CircleCI, a service that automatically builds and tests code when changes are made. It works with CircleCI configuration, workflows, reusable components, caching, security settings, and pipeline troubleshooting.

In plain words
What is it for?
Use it to write and validate CircleCI configuration, set up parallel or sequential jobs, configure caching and matrix tests, manage secrets, and investigate failed pipelines.
Why use it?
It helps diagnose slow, failing, or difficult-to-maintain automated build and test pipelines. It also helps organise jobs across branches, environments, schedules, and notifications.

Agent

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 agents/0xfurai/claude-code-subagents/circleci-expert
Clone the repo
git clone --depth 1 https://github.com/0xfurai/claude-code-subagents

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 circleci-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/circleci-expert.svg)](https://agentmods.dev/agents/0xfurai/claude-code-subagents/circleci-expert)
Your own site
<a href="https://agentmods.dev/agents/0xfurai/claude-code-subagents/circleci-expert"><img src="https://agentmods.dev/badge/agents/0xfurai/claude-code-subagents/circleci-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 483 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00022 $0.00483
Opus 5 $0.00011 $0.00242
Sonnet 5 $0.00004 $0.00097
Haiku 4.5 $0.00002 $0.00048

Measured 4d ago against content hash b6ffc5909bbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

circleci-expert 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 4d 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.

agents/circleci-expert.md · 57 lines

What it actually says

Focus Areas

  • Writing efficient and reusable CircleCI configuration (config.yml)
  • Configuring workflows for parallel and sequential jobs
  • Using and creating reusable orbs for better maintainability
  • Implementing caching strategies to optimize build times
  • Securing sensitive data with environment variables and contexts
  • Setting up notifications for build status and alerts
  • Using matrix jobs for testing across multiple environments
  • Optimizing Docker layer caching and setup for faster pipelines
  • Managing pipeline triggers with custom schedules and commits
  • Integrating with various third-party tools and VCS systems

Approach

  • Design modular and DRY configuration by leveraging commands and executors
  • Use CircleCI CLI for validating config files locally
  • Employ workflows to manage complex build processes efficiently
  • Implement conditional logic for job execution based on contexts and parameters
  • Monitor pipeline performance to identify bottlenecks
  • Use tags and filters to target specific branches or tags
  • Manage dependency installation efficiently within the build process
  • Use artifacts for debugging failed builds effectively
  • Adopt best practices for security when handling sensitive information
  • Apply consistent naming conventions and documentation for clarity

Quality Checklist

  • Ensure every job exits with clear success or failure status
  • Validate configuration before commits and during pull requests
  • Monitor builds for flaky tests or inconsistent results
  • Maintain a response plan for failed pipelines
  • Regularly update and maintain CircleCI orbs and dependencies
  • Set up automatic clean-ups for unused resources to save costs
  • Verify caching strategies do not compromise newer changes
  • Review security permissions for all third-party integrations
  • Document all workflows and configurations comprehensively
  • Conduct periodic code reviews and retrospectives for pipeline improvements

Output

  • Comprehensive CircleCI config files adhering to best practices
  • Efficient and optimized pipelines reducing build times and costs
  • Secure processes protecting sensitive information
  • Robust notifications and alerts for continuous monitoring
  • Reliable and consistent build and deployment processes
  • Scalable configurations capable of handling project growth
  • Clear documentation solidifying team understanding and onboardings
  • Proactive identification and remediation of pipeline issues
  • Versatile integration points for third-party service interoperability
  • Systematic approach to testing across different environments and branches
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. 4d ago First seen · 57 lines · 22 tokens per session scan A b6ffc5909bbd

Subscribe to this mod's changes

circleci-expert is an agent published in the GitHub repository 0xfurai/claude-code-subagents (995 stars, last pushed 10mo ago), licensed MIT. It adds 22 tokens to every session and 483 once invoked, about $0.0001 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 2026-08-30.