check-ci

check-ci is a command for Claude Code from kaeawc/auto-mobile. It costs 38 tokens per session (1,257 once invoked), scanned A, original, Apache-2.0.

A command for diagnosing the automated checks attached to a GitHub pull request. These checks run tests and other validations against a specific version of the proposed code.

In plain words
What is it for?
Use it with a pull-request number or the current branch to inspect checks, read failed job logs, and reproduce likely problems locally.
Why use it?
It distinguishes real failures from checks that are still running, skipped, cancelled, or unrelated to the current code. It can connect failed logs to likely causes and suggest a safe next step.

Command for Claude Code

Part of the auto-mobile plugin — 18 skills, 9 commands, 1 hook, 1 MCP server shipped together

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/kaeawc/auto-mobile/check-ci
Clone the repo
git clone --depth 1 https://github.com/kaeawc/auto-mobile

Made for: Claude Code.

Or install auto-mobile, the plugin that ships this one along with the rest of its 18 skills, 9 commands, 1 hook, 1 MCP server.

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 check-ci

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaeawc/auto-mobile/check-ci.svg)](https://agentmods.dev/commands/kaeawc/auto-mobile/check-ci)
Your own site
<a href="https://agentmods.dev/commands/kaeawc/auto-mobile/check-ci"><img src="https://agentmods.dev/badge/commands/kaeawc/auto-mobile/check-ci.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,257 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 $0.00038 $0.01257
Opus 5 $0.00019 $0.00629
Sonnet 5 $0.00008 $0.00251
Haiku 4.5 $0.00004 $0.00126

Measured 5d ago against content hash c18030485d28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check-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 5d 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.

.claude/commands/check-ci.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage a PR's CI: head-scoped check state, failing-job logs (live or complete), causal classification, local reproduction, and the safe next step. Takes a PR number, or resolves one from the current branch.

scripts/ci/pr-failing-job-logs.sh "$ARGUMENTS"

What the script does

The script branches on bucket (gh's normalized state) rather than grepping human-readable output, then walks run → jobs → each failed job's log. A finished job's log is readable while sibling jobs still run, so it never waits on the slowest leg; when a job hasn't finished its log 404s and the script falls back to per-step status. Logs land in scratch/ at ~100KB each — read the extracted error lines first.

Triage workflow

  1. Resolve the PR number and snapshot headRefOid, baseRefOid, mergeability, and merge state. Use that SHA for every subsequent query. An empty legacy combined status is inconclusive, not green.
  2. Collect gh pr checks <pr> --json name,state,bucket,link,workflow plus paginated repos/<owner>/<repo>/commits/<head-sha>/check-runs. Branch on bucket: only fail is a failure — skipping and cancel are not. Flag duplicate check names with different conclusions on the same head (a cancelled older run beside a successful newer one); the stale one is what parks automerge.
  3. Enumerate runs for that head SHA, then each run's jobs. Ignore runs for older SHAs. Queued and in-progress jobs stay pending — they are never implicitly green.
  4. For a completed failed job: gh run view <run-id> --job <job-id> --log-failed, or gh api repos/<owner>/<repo>/actions/jobs/<job-id>/logs — the latter works as soon as that job finishes, even while sibling jobs still run, so it does not wait on the slowest leg. For a job still executing, gh api .../actions/jobs/<job-id> returns per-step status naming the running or failed step. gh api --follow does not exist; use --paginate.
  5. If the log is truncated or lacks the failure body, list the run's artifacts and read the relevant one. If gh run download is unauthorized, state that exact blocker — do not infer a root cause from partial evidence.
  6. Classify every red result as PR-caused, pre-existing on main, transient/infrastructure, or unproven, grounded in the job log, the changed paths, and current origin/main. Re-run a job only when the evidence supports transience. Never change code for an unrelated or unproven failure.
  7. Reproduce a PR-caused failure locally with the narrowest authoritative command.
  8. After any push, restart at step 1 — every check, thread, and comment was scoped to the previous SHA.

Read the full file on GitHub · 99 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. 5d ago First seen · 99 lines · 38 tokens per session scan A c18030485d28

Subscribe to this mod's changes

check-ci is a command published in the GitHub repository kaeawc/auto-mobile (46 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 1,257 once invoked, about $0.0002 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.