OpenELIS-Global-2: Command for Claude Code

.specify/oe/commands/download-ci-logs.md

download-ci-logs is a command for Claude Code from DIGI-UW/OpenELIS-Global-2. It costs 0 tokens per session (1,324 once invoked), scanned A, original, MPL-2.0.

A command that downloads continuous-integration logs, which are records from automated build and test jobs, using the current branch and failed jobs by default.

In plain words
What is it for?
Use /download-ci-logs with a pull-request number, branch, or run ID, or run it without a target to inspect failed jobs for the current branch after checking workflow status.
Why use it?
It helps you find the logs behind failing checks without having to choose the branch, pull request, or run manually when no specific target is given.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.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 →

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/download-ci-logs.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 download-ci-logs

README.md
[![agentmods](https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/download-ci-logs/github.svg)](https://agentmods.dev/commands/digi-uw/openelis-global-2/download-ci-logs)
Your own site
<a href="https://agentmods.dev/commands/digi-uw/openelis-global-2/download-ci-logs"><img src="https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/download-ci-logs/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.

agentmods 80×15 button for download-ci-logs

Your own site · 80×15
<a href="https://agentmods.dev/commands/digi-uw/openelis-global-2/download-ci-logs"><img src="https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/download-ci-logs.svg" alt="Reviewed on agentmods" width="80" 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 1,324 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 $0.01324
Opus 5 $0.00000 $0.00662
Sonnet 5 $0.00000 $0.00265
Haiku 4.5 $0.00000 $0.00132

Measured 11d ago against content hash 4417bb4863a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

download-ci-logs 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 11d 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/download-ci-logs.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Download CI Logs

When the user invokes /download-ci-logs with optional arguments, run the shim script so that CI logs are downloaded with safe defaults when the user does not specify a target.

Behavior

  • Explicit target: If the user passes --pr <number>, --branch <name>, or --run-id <id>, pass all arguments through to the downloader script.
  • Free text / no target: If the user passes only free text or no arguments, run the shim with current branch and failed-only (so the downloader is invoked with --branch <current-branch> and --failed).

Before downloading logs, ALWAYS run a holistic status check first:

# Show ALL workflows at a glance (same view as GitHub PR UI)
gh pr checks $(gh pr view --json number -q '.number') 2>/dev/null || \
  gh run list --branch "$(git branch --show-current)" --limit 10

This ensures you identify ALL failing workflows (Backend, Frontend, E2E, etc.) before downloading logs for just one. A formatting failure in 01 - Backend is just as blocking as an E2E failure in 03 - E2E.

OpenELIS E2E Pipeline — Finding the Right Run

This project's E2E tests run in a workflow_run-triggered workflow (E2E Tests) that fires after the 03 - E2E build workflow completes.

The E2E / Tests runs always show head_branch: develop in the API, even when testing PR code. This means:

  • gh run list --branch <pr-branch> will NOT find E2E test runs
  • You must use gh pr checks to find the E2E test run ID

To find the correct E2E run for a PR:

# Get the E2E / Tests run URL from the PR's check status
gh pr checks $PR_NUMBER 2>&1 | grep "03 Checkpoint - E2E[^-]"
# Output: 03 Checkpoint - E2E  fail  0  https://github.com/.../actions/runs/<RUN_ID>  ...

# Extract the run ID
RUN_ID=$(gh pr checks $PR_NUMBER 2>&1 | grep "03 Checkpoint - E2E[^-]" | grep -o 'runs/[0-9]*' | cut -d/ -f2)

# Then download logs for that specific run
.specify/scripts/bash/download-ci-logs-shim.sh --run-id $RUN_ID

Read the full file on GitHub · 129 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. 11d ago First seen · 129 lines · 0 tokens per session scan A 4417bb4863a4

Subscribe to this mod's changes

download-ci-logs is a command published in the GitHub repository DIGI-UW/OpenELIS-Global-2 (252 stars, last pushed today), licensed MPL-2.0. It costs nothing until one of its globs matches a file; then it loads 1,324 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.