A workflow for diagnosing failed pull-request checks, the automated build, test, or security jobs that run on a code change. It inspects check results and logs, then applies a focused fix based on the failing job.

Use it when a pull request has failing GitHub Actions or linked external checks. It helps investigate build, test, and security failures and work toward a passing result.

It replaces guesswork with the actual failure details from the pull request and its automation runs. It also checks the workflow definitions so the fix matches how the project is built and tested.

fix-ci — Skill for Cursor by fmflurry/settings-opencode

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 fmflurry/settings-opencode --skill fix-ci

Clone the repo

git clone --depth 1 https://github.com/fmflurry/settings-opencode

Made for: Cursor.

Or install fmflurry-harness, the plugin that ships this one along with the rest of its 21 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fmflurry/settings-opencode/fix-ci/github.svg)](https://agentmods.dev/skills/fmflurry/settings-opencode/fix-ci)

Your own site

<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/fix-ci"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/fix-ci/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/fix-ci"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/fix-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,245 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.01245
Opus 5.5	$0.00012	$0.00498
Sonnet 5.5	$0.00006	$0.00249
Haiku 4.5	$0.00003	$0.00125

Measured 13d ago against content hash 18dfa67d2426, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fix-ci 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 13d 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/fmflurry-harness/skills/fix-ci/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix CI

If the current project has .claude/skills/fix-ci/SKILL.md or .opencode/skills/fix-ci/SKILL.md, read it and its references/; project specifics override this generic version.

Trigger

A branch or PR has failing CI checks and needs a fast, iterative path to green.

Workflow

1. Resolve the PR

Extract PR metadata:

gh pr view --json number,url,headRefName,baseRefName

If gh cannot map the SSH host alias (e.g., gh-pro), provide --repo <owner/repo> derived from:

git remote get-url origin

2. Inspect Checks

List all PR-attached checks:

gh pr checks --json name,bucket,state,workflow,link

Identify the first failed or erroring check. Use bucket to filter to actionable states (not "completed" or "skipped").

3. Inspect Logs

For GitHub Actions runs, extract logs:

gh run view <run-id> --log-failed

For external checks (Sonarqube, etc.), follow the link field to the check's page.

4. Derive Routing from Workflow Files

Before applying a fix, read the workflow file(s) to understand the job structure and owner:

GitHub Actions: Read .github/workflows/*.yml. For the failing job, extract:
- Job name and runs-on platform
- steps with run: commands (these are your repro steps)
- needs: (job dependencies)
- secrets: and Docker image requirements
Azure Pipelines: Read azure-pipelines.yml. For the failing stage/job:
- Stage name and job pool (platform)
- steps with script: commands (these are your repro steps)
- Service connections and Docker image requirements

From this analysis, build a job → repro command → owner map. Examples per tech stack:

Stack	Repro Command	Owner
TS/Angular/Node	`npx tsc --noEmit`	build-error-resolver
Node linting	`npm run lint` or `pnpm run lint`	build-error-resolver
.NET build	`dotnet build --nologo -clp:ErrorsOnly`	build-error-resolver
.NET test	`dotnet test`	tdd-guide or coder
Node tests	`npm test` or `pnpm test`	tdd-guide or coder
E2E (Playwright, Cypress, etc.)	`npm run e2e` (or project-specific)	e2e-runner
Secret scanning (gitleaks)	Workflow log excerpt	STOP, security-reviewer; rotate any exposed secret
SAST/Security scanner (opengrep, SonarQube, etc.)	Check logs	security-reviewer
Dependency/supply-chain gates	Check workflow output	Ask human (new dependencies need review)
Branch-name checks	Workflow rule output	Ask human (rename requires new PR)

Read the full file on GitHub · 122 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.

13d ago First seen · 122 lines · 29 tokens per session scan A 18dfa67d2426

Subscribe to this mod's changes

fix-ci is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,245 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-03.

CI and CD Debugging DevOps and cloud

repair-github-ci

Fix failing GitHub CI / Actions checks via fixgithubprci and push to the existing PR head, or fix a branch's failing CI via a linked repair worktree.

Tracer-Cloud/opensre · 40 tokens

mcore-create-issue

Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.

NVIDIA/skills · 26 tokens

debug-task

Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time, or missing outputs after a cache hit. Also covers pipeline hangs, tasks…

moonrepo/moon · 203 tokens

operating-github-ci-fixer

Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.

Tracer-Cloud/opensre · 48 tokens

meta-long-running-build-watchdog

Watches a long-running command via tmux, lets sub-agent diagnose failures and propose a fix, and records the diagnosis to memory. Designed for overnight model fine-tunes, CI image builds, or repeated regression suites that may fail intermittently.

opensquilla/opensquilla · 131 tokens

tracely

Instrument AI agents with Tracely and turn their production traces into CI gates. Use when the user mentions Tracely, tracely-ai, tracelysdk, the tracely CLI, or asks to trace/observe an AI agent, add LLM evaluators or LLM-as-a-judge columns, debug why a trace or conversation isn't showing up, wire agent regression…

Jwuthri/Tracely-ai · 120 tokens