github-logs-analyze

github-logs-analyze is a skill for Claude Code, Codex from nanasess/eccube-dev-agents. It costs 6 tokens per session (815 once invoked), scanned A, original, MIT.

A tool for reading failed GitHub Actions jobs, the automated checks that run in a GitHub repository, and finding the failed tests and likely error cause.

In plain words
What is it for?
It helps inspect a job from its GitHub URL or ID, identify failed steps, and recognize common PHPUnit, Codeception, Jest, pytest, timeout, and memory errors.
Why use it?
It reduces the need to search through long build logs by hand when a check fails.

Skill for Claude CodeCodex

Part of the eccube-dev-agents plugin — 8 skills 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 skills/nanasess/eccube-dev-agents/github-logs-analyze
Any agent
npx skills add nanasess/eccube-dev-agents --skill github-logs-analyze
Clone the repo
git clone --depth 1 https://github.com/nanasess/eccube-dev-agents

Made for: Claude Code, Codex.

Or install eccube-dev-agents, the plugin that ships this one along with the rest of its 8 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.

agentmods badge for github-logs-analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/nanasess/eccube-dev-agents/github-logs-analyze.svg)](https://agentmods.dev/skills/nanasess/eccube-dev-agents/github-logs-analyze)
Your own site
<a href="https://agentmods.dev/skills/nanasess/eccube-dev-agents/github-logs-analyze"><img src="https://agentmods.dev/badge/skills/nanasess/eccube-dev-agents/github-logs-analyze.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 815 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 $0.00006 $0.00815
Opus 5 $0.00003 $0.00407
Sonnet 5 $0.00001 $0.00163
Haiku 4.5 $0.00001 $0.00081

Measured 3d ago against content hash 4f0224c5ff9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-logs-analyze 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.

plugins/eccube-dev-agents/skills/github-logs-analyze/SKILL.md · 96 lines

What it actually says

GitHub Actions ログ解析

GitHub Actions の失敗ログを解析し、失敗したテストとエラー原因を特定します。

手順

1. 引数解析

$ARGUMENTS から job 情報を抽出:

  • URL形式の場合: https://github.com/{owner}/{repo}/actions/runs/{run_id}/job/{job_id} から owner, repo, job_id を抽出
  • 数字のみの場合: job ID として扱う
  • owner/repo の特定:
    • URLから抽出できる場合はそれを使用
    • できない場合は gh repo view --json nameWithOwner -q .nameWithOwner でカレントリポジトリから取得

2. ジョブ情報取得

gh api repos/{owner}/{repo}/actions/jobs/{job_id} でジョブ詳細を取得:

  • Job名
  • 実行時間(started_at, completed_at)
  • ステータス(conclusion)
  • 各 step の名前とステータス
  • 失敗した step を特定

3. ログ取得と解析

gh api repos/{owner}/{repo}/actions/jobs/{job_id}/logs でログを取得し解析:

テストフレームワーク別の失敗パターン検出:

PHPUnit:

  • FAILURES! / ERRORS!
  • Tests: X, Assertions: Y, Failures: Z
  • 1) TestClass::testMethod
  • Failed asserting that ...

Codeception:

  • FAILURES!
  • Couldn't ... / Failed ...

Jest:

  • FAIL src/...
  • ● Test Suite > test name
  • Expected ... Received ...

pytest:

  • FAILED tests/...
  • E assert ...

一般的なエラーパターン:

  • Error: / Exception:
  • fatal: / panic:
  • タイムアウト: timeout / exceeded
  • メモリ不足: out of memory / Allowed memory size

4. 結果表示

## Job 概要
- Job名: <name>
- 実行時間: <duration>
- 失敗 Step: <step name>

## 失敗テスト一覧

❌ TestClass::testMethod
   エラー: <エラーメッセージ>
   ファイル: <path>:<line>

❌ TestClass::testMethod2
   エラー: <エラーメッセージ>
   ファイル: <path>:<line>

## エラー原因の推定
<原因の分析と修正提案>

5. job ID 未指定の場合

  1. gh run list --status=failure --limit=5 で最新の失敗 run を表示
  2. ユーザーに調査対象を選択してもらう
  3. 選択された run の jobs を gh run view {run_id} --json jobs で取得
  4. 失敗した job のログを解析

エラーハンドリング

  • job ID が見つからない場合: 正しい URL/ID 形式を案内
  • ログが空または取得できない場合: run レベルのログ取得を試行
  • リポジトリへのアクセス権がない場合: gh auth login を案内
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 · 96 lines · 6 tokens per session scan A 4f0224c5ff9f

Subscribe to this mod's changes

github-logs-analyze is a skill published in the GitHub repository nanasess/eccube-dev-agents (2 stars, last pushed 28d ago), licensed MIT. It adds 6 tokens to every session and 815 once invoked, about $0.0000 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 2026-08-31.

Related

Other skills, from other repositories