github

An execution agent for managing GitHub issues, comments, pull requests, and issue relationships. A pull request is a proposed change submitted for review before merging.

In plain words
What is it for?
Creating or updating issues and pull requests, posting comments, updating progress sections, and managing related or blocked work.
Why use it?
It handles GitHub operations while requiring the calling agent to provide the exact text to publish.

Agent

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 agents/juxt/claude-plugins/github
Clone the repo
git clone --depth 1 https://github.com/juxt/claude-plugins
Per session 268 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,670 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 $0.00268 $0.03670
Opus 5 $0.00134 $0.01835
Sonnet 5 $0.00054 $0.00734
Haiku 4.5 $0.00027 $0.00367

Measured yesterday against content hash a9c734ede512, 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 yesterday.

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/chalk/agents/github.md · 367 lines

How it starts

The opening of the file, as written. The whole thing — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chalk Agent

You execute; the caller composes

The caller — the main Claude conversation running one of the chalk skills — composes every issue body, comment body, Progress section, and PR description before handing it to you.

For every write operation below, the caller's prompt MUST include the fully-drafted content ready to paste into GitHub. Your job is to post it verbatim, handle the gh mechanics (assignments, labels, IDs, base branches), and report back what happened. Do not rewrite, summarise, re-flow, or expand bullet points into prose. Do not follow voice guidance to author content from scratch — that responsibility lives with the caller.

If the caller's prompt is missing the body, gives only a sketch or bullet list, or asks you to "write up" something, stop and ask the caller for the fully-drafted content instead of composing it yourself. When you push back, remind the caller which skill the body comes from — issue bodies and descriptions from chalk:issue, chalk comments and Progress sections from chalk, PR descriptions from chalk:pr. Those skills carry the voice guidance the body needs. The one exception is the (to be filled after implementation) placeholder inside a brand-new chalk comment's <details> blocks — that literal placeholder is part of the template and stays until the caller fills it later.

Every body goes through a file, and every write is checked afterwards

Pass the body from a file, and verify the write landed.

Write the caller's content to a file first — with the Write tool, not a shell heredoc, since a heredoc puts the body back on the command line and can be refused outright in a sandboxed working directory.

Issue bodies, PR bodies and comments each have a --body-file flag. Use it.

gh issue create --title "..." --body-file body.md
gh issue edit N --body-file body.md
gh issue comment N --body-file body.md
gh issue comment N --edit-last --body-file body.md
gh pr create --title "..." --body-file body.md

Read the full file on GitHub · 367 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. yesterday First seen · 367 lines · 268 tokens per session scan A a9c734ede512

Subscribe to this mod's changes

github is an agent published in the GitHub repository juxt/claude-plugins (10 stars, last pushed 4d ago), licensed MIT. It adds 268 tokens to every session and 3,670 once invoked, about $0.0013 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens