github

A connection to GitHub, a service for hosting code and reviewing changes. It investigates commits, pull requests, deployments, and workflow runs, and can suggest or apply targeted code fixes.

In plain words
What is it for?
Finding connected repositories, reviewing correlated commits and pull requests, checking GitHub Actions deployments, inspecting diffs, and proposing or making file edits.
Why use it?
It links an incident to recent code changes and deployments, helping identify what may have caused the problem and where a fix belongs.

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/arvo-ai/aurora/github
Any agent
npx skills add Arvo-AI/aurora --skill github
Clone the repo
git clone --depth 1 https://github.com/Arvo-AI/aurora

Made for: Claude Code, Codex.

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,518 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 $0.00024 $0.01518
Opus 5 $0.00012 $0.00759
Sonnet 5 $0.00005 $0.00304
Haiku 4.5 $0.00002 $0.00152

Measured 2d ago against content hash c2c02db016f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github 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 2d 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.

server/chat/backend/agent/skills/integrations/github/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Integration

Overview

GitHub integration for investigating code changes during Root Cause Analysis and managing code fixes. Connected account: {username}

Instructions

Multi-Repo Discovery

  • Multiple repositories may be connected. Call get_connected_repos FIRST to list them with descriptions.
  • Each repo has an LLM-generated summary describing what it contains — use these to pick the right repo for your task.
  • If only one repo is connected, github_rca auto-selects it. If multiple, you MUST pass repo='owner/repo'.

Tool Usage (use in this order)

  1. get_connected_repos — Discover available repos + descriptions. Always call first.
  2. github_rca(repo='owner/repo', action=...) — Investigate code changes for RCA:
    • deployment_check — GitHub Actions workflow runs (failures, suspicious timing)
    • commits — Recent commits with automatic 2-hour incident correlation
    • diff (requires commit_sha) — File-level changes for a specific commit
    • pull_requests — Merged PRs in the time window
    • Pass incident_time (ISO 8601) for automatic time window correlation
  3. github_fix(file_path=..., edits=[{old_string, new_string, replace_all?}, ...], fix_description=..., root_cause_summary=...) — Suggest a code fix via anchored search-and-replace edits (stored for user review, not auto-applied). First call get_file_contents to read the current file so you can copy the exact old_string (with enough surrounding context to be unique).
  4. github_apply_fix(suggestion_id=...) — Create a PR from an approved fix (only after user reviews)
  5. github_commit(repo=..., commit_message=...) — Push generated Terraform (.tf) files from the IaC workflow to GitHub. This is NOT a general-purpose commit tool — it only pushes .tf files from the terraform working directory.

MCP Tools (for direct GitHub API operations beyond RCA)

  • Files: get_file_contents, create_or_update_file, push_files, get_repository_tree
  • Size limit: create_or_update_file and push_files enforce a 50 KB per-file cap. Files exceeding this limit will be rejected. Do NOT attempt to work around this via terminal commands or other tools — the limit is intentional.
  • Updates: When updating an existing file, the new content must be at least 50% of the original file size (for files over 10 KB). This prevents accidental truncation.
  • Branches: create_branch, list_branches, list_commits, get_commit
  • PRs: create_pull_request, list_pull_requests, merge_pull_request, get_pull_request_files
  • Issues: create_issue, list_issues, search_issues, add_issue_comment
  • Actions: list_workflow_runs, get_workflow_run, get_job_logs, run_workflow
  • Security: list_code_scanning_alerts, list_dependabot_alerts, list_secret_scanning_alerts
  • All MCP tools require owner and repo parameters (split from 'owner/repo').

Read the full file on GitHub · 96 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. 2d ago First seen · 96 lines · 24 tokens per session scan A c2c02db016f8

Subscribe to this mod's changes

github is a skill published in the GitHub repository Arvo-AI/aurora (401 stars, last pushed 4d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,518 once invoked, about $0.0001 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