agentbox: Skill for Claude Code

.claude/skills/accessing-github/SKILL.md

accessing-github is a skill for Claude Code from fletchgqc/agentbox. It costs 58 tokens per session (251 once invoked), scanned A, original, Apache-2.0.

A skill for running Git operations and working with GitHub through the command line or API.

In plain words
What is it for?
Use it for branches, commits, pushes, pulls, merges, issues, pull requests, and other GitHub operations.
Why use it?
It gives the agent defined procedures for repository changes and GitHub tasks, including commits and pull requests.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is fletchgqc/agentbox's own configuration. It tells Claude Code how to work on agentbox itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentbox configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fletchgqc/agentbox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fletchgqc/agentbox/main/.claude/skills/accessing-github/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fletchgqc/agentbox

Made for: Claude Code.

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 accessing-github

README.md
[![agentmods](https://agentmods.dev/badge/skills/fletchgqc/agentbox/accessing-github/github.svg)](https://agentmods.dev/skills/fletchgqc/agentbox/accessing-github)
Your own site
<a href="https://agentmods.dev/skills/fletchgqc/agentbox/accessing-github"><img src="https://agentmods.dev/badge/skills/fletchgqc/agentbox/accessing-github/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for accessing-github

Your own site · 80×15
<a href="https://agentmods.dev/skills/fletchgqc/agentbox/accessing-github"><img src="https://agentmods.dev/badge/skills/fletchgqc/agentbox/accessing-github.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 251 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00058 $0.00251
Opus 5.5 $0.00023 $0.00100
Sonnet 5.5 $0.00012 $0.00050
Haiku 4.5 $0.00006 $0.00025

Measured 2mo ago against content hash 93557d3c2d84, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

accessing-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 2mo 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/skills/accessing-github/SKILL.md · 17 lines

What it actually says

GitHub Integration

  • Always use gh CLI for GitHub operations when possible. Authentication is automatically taken care of by the GH_TOKEN environment variable.
  • Fall back to GitHub API when gh CLI isn't suitable

When committing code

  • Create a git commit message which summarises the changes being committed. Include what was changed and why the changes were made, using the conversation history to determine the why if possible.

Challenge your "why"

  • After drafting a "why" part, challenge yourself: would a reader be able to easily determine this themselves from the "what"? If so, don't include the "why", since it is superfluous.

Improvements

  • If you solve any problems with github integration, for example with gh authentication not working out of the box, summarise for the user what problem you solved and how after you finish the task. This information will be used to improve the skill in future.
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. 2mo ago First seen · 17 lines · 0 tokens per session scan A 93557d3c2d84

Subscribe to this mod's changes

accessing-github is a skill published in the GitHub repository fletchgqc/agentbox (120 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 251 once invoked, about $0.0002 per session on Opus 5.5. 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.