fix-pipeline

fix-pipeline is a command for Claude Code from rohitg00/awesome-claude-code-toolkit. It costs 14 tokens per session (319 once invoked), scanned A, original, Apache-2.0.

A command for repairing broken continuous integration and delivery configuration, such as GitHub Actions or GitLab pipelines. It investigates the failing step, makes a small configuration fix, validates the syntax, and reports the change.

In plain words
What is it for?
Use it for dependency, test-environment, Docker, caching, timeout, retry, secret, and failure-notification problems in CI/CD configuration.
Why use it?
It helps locate and correct pipeline failures without changing tests just to hide the underlying problem or refactoring unrelated workflow code.

Command for Claude Code

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

Part of the ci-debugger plugin — 2 commands shipped together

About the project

Awesome Claude Code Toolkit is a curated collection of extensions and configuration for Claude Code, including agents, skills, commands, plugins, hooks, rules, templates, MCP configurations, and companion apps. It is for Claude Code users who want ready-made workflows and integrations for different development tasks. The catalogue add-ons are selected components from this toolkit.

rohitg00/awesome-claude-code-toolkit · 2,591 stars · on GitHub

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 commands/rohitg00/awesome-claude-code-toolkit/fix-pipeline
Clone the repo
git clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkit

Made for: Claude Code.

Or install ci-debugger, the plugin that ships this one along with the rest of its 2 commands.

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 fix-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/commands/rohitg00/awesome-claude-code-toolkit/fix-pipeline.svg)](https://agentmods.dev/commands/rohitg00/awesome-claude-code-toolkit/fix-pipeline)
Your own site
<a href="https://agentmods.dev/commands/rohitg00/awesome-claude-code-toolkit/fix-pipeline"><img src="https://agentmods.dev/badge/commands/rohitg00/awesome-claude-code-toolkit/fix-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 319 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 5.1 $0.00014 $0.00319
Opus 5 $0.00007 $0.00160
Sonnet 5 $0.00003 $0.00064
Haiku 4.5 $0.00001 $0.00032

Measured 6d ago against content hash d7cfae64fdca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fix-pipeline 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 6d 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/ci-debugger/commands/fix-pipeline.md · 34 lines

What it actually says

/fix-pipeline - Fix CI/CD Pipeline

Apply fixes to a broken CI/CD pipeline configuration.

Steps

  1. Read the CI/CD configuration file (.github/workflows/*.yml, .gitlab-ci.yml, etc.)
  2. Identify the failing step and its configuration
  3. Determine the fix based on the failure analysis
  4. For dependency issues: update versions, add caching, fix lock files
  5. For test failures: increase timeouts, add retry logic, fix test environment
  6. For Docker issues: fix Dockerfile, update base images, fix build context
  7. For credential issues: verify secret names, check expiration, update references
  8. Apply the configuration fix to the pipeline file
  9. Add or update caching configuration to speed up future builds
  10. Add failure notification steps if not already present
  11. Run a dry-run or validation of the pipeline config if the platform supports it
  12. Commit the fix and report what was changed and why

Rules

  • Make minimal changes to fix the issue; do not refactor the entire pipeline
  • Always validate the pipeline config syntax before committing
  • Add comments explaining non-obvious configuration choices
  • Do not change test expectations to make them pass; fix the underlying issue
  • Preserve existing caching strategies unless they are causing the failure
  • Keep pipeline execution time in mind; do not add expensive steps unnecessarily
  • Test the fix on a feature branch before merging to main
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. 6d ago First seen · 34 lines · 14 tokens per session scan A d7cfae64fdca

Subscribe to this mod's changes

fix-pipeline is a command published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,591 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 319 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.