OpenELIS-Global-2: Command for Claude Code

.specify/oe/commands/fix-ci.md

fix-ci is a command for Claude Code from DIGI-UW/OpenELIS-Global-2. It costs 0 tokens per session (7,083 once invoked), scanned A, original, MPL-2.0.

An automated command for investigating failed continuous-integration (CI) checks, making targeted fixes, and checking the results again.

In plain words
What is it for?
Use /fix-ci to work on the current branch, a pull request, a specific CI run, or a named branch. It reviews logs and test artifacts, validates fixes locally, pushes them, and rechecks CI.
Why use it?
It removes the need to repeatedly download logs, diagnose failures, push changes, and monitor CI by hand. It continues until the checks pass or needs human help.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is DIGI-UW/OpenELIS-Global-2's own configuration. It tells Claude Code how to work on OpenELIS-Global-2 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OpenELIS-Global-2 configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./src/test/resources/load-ci-fixtures.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to DIGI-UW/OpenELIS-Global-2. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DIGI-UW/OpenELIS-Global-2/develop/.specify/oe/commands/fix-ci.md
Clone the repo
git clone --depth 1 https://github.com/DIGI-UW/OpenELIS-Global-2

Made for: Claude Code.

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-ci

README.md
[![agentmods](https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/fix-ci.svg)](https://agentmods.dev/commands/digi-uw/openelis-global-2/fix-ci)
Your own site
<a href="https://agentmods.dev/commands/digi-uw/openelis-global-2/fix-ci"><img src="https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/fix-ci.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,083 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.07083
Opus 5 $0.00000 $0.03542
Sonnet 5 $0.00000 $0.01417
Haiku 4.5 $0.00000 $0.00708

Measured 8d ago against content hash 3162f2da2e3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

.specify/oe/commands/fix-ci.md · 769 lines

How it starts

The opening of the file, as written. The whole thing — 769 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix CI

When the user invokes /fix-ci (optionally with arguments), perform an autonomous, async-first CI remediation loop that:

  • Downloads CI failure logs and artifacts (screenshots, traces)
  • Diagnoses failures using evidence (logs, screenshots, code)
  • Applies targeted, minimal fixes
  • Validates locally before pushing
  • Pushes, waits 15 minutes, and re-checks CI
  • Iterates until CI is green or escalation is required

This command is action-oriented and autonomous: it runs the full loop without user interaction unless it hits an escalation boundary. The user can walk away and come back to a green CI or a clear diagnostic report.

User Input

$ARGUMENTS

Interpret arguments best-effort. Parse and validate each flag before use. Only construct shell commands using recognized flag values — never interpolate raw user text directly into shell commands. Support these patterns:

Target selection (mutually exclusive):

  • /fix-ci → current branch, latest failed run
  • /fix-ci --pr 123 → target a specific PR
  • /fix-ci --run-id 12345678 → target a specific run
  • /fix-ci --branch develop → target a specific branch

Behavior options:

Flag Default Description
--max-iterations N 5 Max fix-push-check cycles before escalating
--dry-run off Diagnose only — no fixes, no pushes
--local-e2e off Run full local E2E suite in parallel with CI after push
--reset-env off Reset local E2E environment (fixtures) before local runs
--compose-file <path> dev.docker-compose.yml Docker Compose file for local E2E (use build.docker-compose.yml to match CI exactly)
--flaky-retry N 0 Re-run suspected flaky tests N times before diagnosing
--skip-local-validate off Skip local validation (push immediately after fix)
--jobs <job-names> all Only fix specific jobs (e.g., --jobs "E2E / Playwright / Core" or --jobs "E2E / Cypress (Deprecated) / Core")
--notify off Force NOTIFY level (always summarize, even for AUTO)
--report-to-pr off Post resolution report as a PR comment when done

Read the full file on GitHub · 769 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.

  1. 8d ago First seen · 769 lines · 0 tokens per session scan A 3162f2da2e3e

Subscribe to this mod's changes

fix-ci is a command published in the GitHub repository DIGI-UW/OpenELIS-Global-2 (251 stars, last pushed yesterday), licensed MPL-2.0. It costs nothing until one of its globs matches a file; then it loads 7,083 tokens. 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.