github

A GitHub connection for finding repositories, reading issues, pull requests, files, and code, and—with approval—creating branches, changing files, and opening pull requests.

In plain words
What is it for?
Use it to inspect repositories, issues, pull requests, branches, files, and code; create a branch, update files, or open a pull request when you approve the change.
Why use it?
It avoids switching between the coding agent and GitHub for routine repository and collaboration tasks. It is intended for reading project information, not detailed code analysis.

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/aws-samples/sample-strands-agent-with-agentcore/github
Any agent
npx skills add aws-samples/sample-strands-agent-with-agentcore --skill github
Clone the repo
git clone --depth 1 https://github.com/aws-samples/sample-strands-agent-with-agentcore

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 722 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 $0.00039 $0.00722
Opus 5 $0.00019 $0.00361
Sonnet 5 $0.00008 $0.00144
Haiku 4.5 $0.00004 $0.00072

Measured 2d ago against content hash f7da8862525d, 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.

chatbot-app/agentcore/skills/github/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub

Available Tools

Read

  • github_search_repos(query, max_results?): Search GitHub repositories.
  • github_get_repo(owner, repo): Get repository details (description, stars, language, topics).
  • github_list_issues(owner, repo, state?, labels?, max_results?): List issues. state: open | closed | all.
  • github_get_issue(owner, repo, issue_number): Get a single issue with comments.
  • github_list_pulls(owner, repo, state?, max_results?): List pull requests.
  • github_get_pull(owner, repo, pull_number): Get a single pull request with diff summary.
  • github_get_file(owner, repo, path, ref?): Get file contents. ref defaults to default branch.
  • github_search_code(query, max_results?): Search code across GitHub (use repo:owner/name to scope).

Write (requires user approval)

  • github_create_branch(owner, repo, branch, from_branch?): Create a new branch.
  • github_push_files(owner, repo, branch, files, message): Create or update files. files: list of {path, content}.
  • github_create_pull_request(owner, repo, title, body, head, base?): Open a pull request.

Usage Guidelines

  • Never perform write operations autonomously. Only call github_create_branch, github_push_files, or github_create_pull_request when the user has explicitly requested or approved the action. If the user's intent is ambiguous, ask for confirmation before proceeding.
  • Always read existing files with github_get_file before modifying them.
  • Before calling any write tool, explain exactly what will change (branch name, target files, PR details) and wait for user agreement.
  • For multi-file changes: create a branch → push all files in one github_push_files call → open PR.
  • Use github_search_code with repo:owner/name qualifier to scope searches to a specific repository.

UI Guidance (from tools-config)

GitHub Tool Usage:

  • github_search_repos: Search GitHub repositories by keyword
  • github_get_repo: Get repository details (description, stars, language, topics)
  • github_list_issues: List issues (state: open|closed|all, filter by labels)
  • github_get_issue: Get a single issue with all comments
  • github_list_pulls: List pull requests
  • github_get_pull: Get a single PR with diff summary
  • github_get_file: Read file contents from a repo (specify ref/branch if needed)
  • github_search_code: Search code across GitHub (use repo:owner/name to scope)
  • github_create_branch: Create a new branch (write — requires approval)
  • github_push_files: Create or update files on a branch (write — requires approval)
  • github_create_pull_request: Open a pull request (write — requires approval)

Read the full file on GitHub · 53 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 · 53 lines · 39 tokens per session scan A f7da8862525d

Subscribe to this mod's changes

github is a skill published in the GitHub repository aws-samples/sample-strands-agent-with-agentcore (191 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 722 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.