ci-fix

A safety and triage procedure for .NET MAUI CI-fixer workflows. It examines who owns a CI issue—continuous-integration failures found during automated builds—and assigns one decision: Continue, Watch, Stop, or Skip.

In plain words
What is it for?
Use it when investigating or advancing CI-fix pull requests from scan issues, including ownership checks, scheduled sweeps, manual dispatches, and deciding whether to proceed, monitor, stop, or skip.
Why use it?
It prevents an automated fixer from changing an issue that a person already owns, duplicating an existing fixer PR, or acting on stale or unsafe evidence. The decision is based on ownership and current context before any action is proposed.

Skill for Claude CodeCodex

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 skills/dotnet/maui/ci-fix
Any agent
npx skills add dotnet/maui --skill ci-fix
Clone the repo
git clone --depth 1 https://github.com/dotnet/maui

Made for: Claude Code, Codex.

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,113 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 $0.00081 $0.01113
Opus 5 $0.00041 $0.00557
Sonnet 5 $0.00016 $0.00223
Haiku 4.5 $0.00008 $0.00111

Measured 3d ago against content hash 2a20518d8d80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ci-fix 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 3d 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.

.github/skills/ci-fix/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CI-fix triage protocol

Use this protocol before proposing a code change or emitting a CI-fixer safe output. The calling workflow supplies its branch, labels, title prefix, attempt limit, and allowed write surface; preserve those caller-specific restrictions.

Return a decision

For each candidate, state one terminal decision before taking an action:

  • Decision: Continue — no dedup or safety gate blocks current-evidence analysis.
  • Decision: Watch — exclusively an open workflow-owned CI-fix PR owns the issue; advance only that PR.
  • Decision: Stop — an explicit human PR owns the issue; do not monitor it or plan a fallback CI-fix PR.
  • Decision: Skip — the issue is stale, visual, already fixed, out of scope, or cannot be safely advanced.

Explain the concrete evidence for the decision. A search result is evidence to inspect, not a decision by itself.

Reason through all ownership evidence before emitting the decision. Return exactly one terminal decision; never emit a provisional decision and then correct it later in the response.

When the caller requests a strict decision format, complete the classification before writing any response text. Emit only the final decision and requested next action. Do not include a draft, correction, or alternate decision.

Deduplicate without false ownership

  1. An open CI-fix PR with the workflow's title prefix and exact Refs: dotnet/maui#<issue> is the only Watch case. Never open a second CI-fix PR for that issue.
  2. A merged CI-fix PR with that exact reference is a Skip case until current evidence establishes a new regression.
  3. A closed-unmerged CI-fix PR with that exact reference is a Skip case. A human closing the PR is a stop signal for the keep-one-PR loop.
  4. An open human PR is always a Stop case when its own title or body explicitly declares that it addresses the tracking issue. Do not monitor it or plan a fallback CI-fix PR. Accept a Refs: declaration or a closing/reference keyword such as Fix, Fixes, Fixed, Close, Closes, Closed, Resolve, Resolves, or Resolved followed by the issue reference, including #<issue>, dotnet/maui#<issue>, or https://github.com/dotnet/maui/issues/<issue>.

Read the full file on GitHub · 95 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 95 lines · 81 tokens per session scan A 2a20518d8d80

Subscribe to this mod's changes

ci-fix is a skill published in the GitHub repository dotnet/maui (23,317 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 1,113 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

analyze-ci-failures

Analyze CI failures on Azure SDK for .NET pull requests and post a comment with how-to-fix instructions. Use when a PR has failing checks, CI is red, or someone asks for help fixing CI.

Azure/azure-sdk-for-net · 49 tokens

azsdk-common-pipeline-analysis

Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…

Azure/azure-sdk-for-net · 192 tokens

azsdk-common-pipeline-fixer

Automatically fix Azure SDK CI/CD pipeline failures by applying code changes and verifying locally. USE FOR: "fix pipeline failure", "fix CI", "fix failing tests", "auto-fix and commit the fix", "fix build error", "fix mypy/pylint/type-check/lint errors", "auto-fix pipeline", "resolve pipeline failure". DO NOT USE…

Azure/azure-sdk-for-net · 150 tokens

dpg-migration

Migration logic for Azure SDK for .NET data-plane libraries migrating from AutoRest/Swagger to TypeSpec-based generation. Uses MCP tools from the generator-agent server for automated deterministic fixes.

Azure/azure-sdk-for-net · 41 tokens

csharp-azure-spector-coverage-gaps

Discovers and implements gaps in Spector test coverage for the Azure C# HTTP client emitter. Use when asked to find missing Spector scenarios, add Spector test coverage, or implement a specific Spector spec for the Azure C# emitter. Can also compare coverage between the Azure dashboard and the Standard (TypeSpec core)…

Azure/azure-sdk-for-net · 78 tokens

auto-build-repair

Headless, bounded repair of custom-code build failures in an already-generated Azure SDK PR. Thin wrapper over the shared azure-sdk-mcp:azsdkcustomizedcodeupdate engine in custom-code-only scope (editScope: CustomCode); the skill owns the iterate-until-green loop, capped by a per-language maxIterations read from…

Azure/azure-sdk-for-net · 149 tokens